CN115729343A - Function adjusting method and related device - Google Patents

Abstract

The embodiment of the application discloses a function adjusting method, which comprises the following steps: the first radar data is acquired, the fine adjustment function is started when the duration of a first gesture indicated by the first radar data exceeds a first threshold, and fine adjustment for the target function can be performed based on a second gesture indicated by the second radar data. This application is based on the gesture duration as the foundation whether to open meticulous adjustment mode, then can let the gesture classification that independent gesture function used overlap with the gesture of awakening up, and then can reduce the required gesture classification when the function regulation that carries out the gesture realization.

Description

A function adjustment method and related device

technical field

The present application relates to the field of radar, and in particular to a function adjustment method and a related device.

Background technique

With the progress of society and the rapid development of material life, people's demand for more intelligent and convenient human-computer interaction methods is becoming stronger and stronger. Human-computer interaction is a study of the interactive relationship between the system and the user. The system can be a variety of machines, or computerized systems and software. Human-computer interaction technology has extremely high development potential and application value in application scenarios such as future terminals and smart cockpits.

The human-computer interaction method is continuously developing, which can be divided into contact interaction and non-contact interaction. Initially, the interaction method of keyboard or physical buttons has a high accuracy rate and no redundant operation, but the interaction is not intuitive and requires a complex device interface to cover all operations; the birth of the graphical user interface got rid of abstract commands, and interactive devices generally It is a mouse, but the control of the mouse device is separated from the display domain where the interface appears, so the user needs to perform indirect interactive operations on the target, which further increases the difficulty of interaction; the touch interactive interface realizes direct interactive operations, thus retaining While reducing part of the tactile feedback, it further reduces the user's learning and cognitive costs. However, when clicking on the touch screen, it is often difficult to accurately control the position of the landing point. The granularity of the input signal is far lower than the response granularity of the interactive elements. At the same time, its interactive form is still a two-dimensional interface; while the current non-contact interaction mainly includes voice control interaction, action interaction, etc. Among them, the strict requirements of voice-activated interaction on the noise environment limit its application scenarios.

As one of the important ways of human-computer interaction, gesture recognition has become a research hotspot and has been widely used in various fields. For example, in the vehicle environment, the accuracy of speech recognition is often not satisfactory due to the excessive environmental noise during driving and the possibility of multiple people talking in the vehicle. For the touch screen mode, the driver must shift his sight to operate, which affects driving safety. Therefore, in the vehicle environment, gesture recognition has a very high demand as a blind operation and non-contact interaction method.

Traditional gesture recognition technology is mainly carried out by using optical cameras. Optical images can clearly represent the shape and texture of gestures, but its limitations are also relatively large. First, optical cameras have poor effects under strong or dim light; secondly, they There is also a large restriction on the viewing distance, and the user must perform action recognition in a certain space, and there must be no obstacles; moreover, the storage cost and calculation cost of optical images are relatively high; in addition, optical technology exists Large risk of privacy leakage, unable to ensure security. In contrast, gesture recognition based on millimeter waves has shown its advantages, not only is not affected by lighting conditions, but also has a greatly improved range of use, and its low power consumption allows it to work well Integrated, and there is no issue involving user privacy.

Radar-based gesture recognition has the characteristics of high accuracy, good fluency, strong environmental adaptability, and privacy protection. It can be used for fine adjustment in the air, and has important application value in scenarios such as smart cockpits and future terminals. The output of the current single millimeter-wave gesture recognition system can only achieve single-instruction operations and cannot complete two-way precise adjustments to certain functions of the device. However, in the future, gestures will also be required to perform fine-tuning functions such as volume adjustment and map zooming.

Contents of the invention

In a first aspect, the present application provides a function adjustment method, the method comprising:

Obtain the first radar data;

It should be understood that the first radar data in this embodiment of the present application may refer to a reflected signal received by a receiving antenna in a radar system at an analog processing circuit, where the reflected signal is an analog signal. After obtaining the analog signal, the analog signal may be transmitted to an analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal.

It should be understood that the analog signal obtained by the analog processing circuit can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal. The first radar data in the embodiment of the present application can also refer to the above digitized The digital signal of is not limited here;

based on the first radar data indicating a first gesture, and the duration of the first gesture exceeds a first threshold, enabling an adjustment function for a target function;

Wherein, the first gesture may be a preset type of gesture (that is, a pre-configured gesture type that can enable a fine adjustment function), such as a hovering gesture, etc.;

After the first radar data is acquired, the motion characteristics (such as distance, speed, angle, etc.) of the user's gesture indicated by the first radar data may be analyzed from the signal layer, when the duration of the user's gesture exceeds the first threshold, and When the motion feature can indicate the first gesture, the adjustment function for the target function is turned on;

Wherein, after the first radar data is acquired, when the duration of the user's gesture exceeds the first threshold, part of the radar data can be intercepted from the first radar data, and a pre-trained neural network (or other gesture category recognition methods) can be used to identify Part of the radar data is used for gesture recognition, and when the recognition result is the first gesture, the adjustment function for the target function is turned on;

In a possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

Among them, the radar gestures (such as the first gesture, the second gesture, and the third gesture) in the embodiment of the present application are radar-based touch-independent gestures (radar-based touch-independent gesture), which can also be called " 3Dgesture (3D gesture), radar gesture refers to the nature of a gesture that is spatially distant from the electronic device (eg, the gesture does not require the user to touch the device, although the gesture does not preclude touch). A radar gesture itself may typically only have a two-dimensional active information component, such as a radar gesture consisting of an upper-left to lower-right swipe, but since a radar gesture is some distance from the electronic device (the "third" dimension or depth), The radar gestures in the embodiments of the present application can generally be regarded as three-dimensional;

In a possible implementation, some or all of the data in the first radar data may be radar data corresponding to the first gesture. After the first radar data is acquired, it is necessary to identify the The radar data, and further processing related to the first gesture (such as determination of the gesture category, determination of the duration of the gesture, etc.) can be performed on this part of the recognized radar data.

Among them, the fine adjustment may include the opening of the function and the adjustment of the degree of the function. The adjustment of the degree may be the increase or decrease of the value, the direction adjustment of the display position, the zoom adjustment of the display area, the adjustment of the position or form of the hardware, For example, fine adjustments may include volume adjustments, display brightness adjustments or zoom adjustments of displayed images, display interface movement adjustments, window height adjustments, front and rear position adjustments of seats in the cabin, and the like. Since it involves level adjustment of functions, the gesture of fine adjustment needs to last for a certain period of time to select the level of adjustment, and the duration is relatively long.

In a possible implementation, the timing can be started when the gesture data is detected, and if the duration of the gesture data is terminated before exceeding the first threshold, the independent gesture adjustment mode can be started.

Wherein, the independent gesture adjustment mode may include turning on or off the function, and since it does not involve the degree adjustment of the function, the independent gesture may be a single gesture with a short duration, such as waving left or right.

When the duration of the first gesture indicated based on the first radar data exceeds the first threshold, the radar data related to the first gesture in the first radar data can be identified for the gesture category (that is, the gesture category for the first gesture The recognition of the gesture category of the first gesture is performed because it is necessary to determine the function type of the subsequent fine adjustment based on the gesture category of the first gesture (that is, to determine the target function). It should be understood that the gesture category here may be understood as a hand shape category, and gestures of different gesture categories have different hand shape characteristics.

Obtain the second radar data;

Specifically, the processor may acquire the second radar data, where the second radar data may be obtained from a reflected signal of the user's gesture (second gesture);

In response to the activation of the adjustment function for the target function, according to the second radar data, determine a second gesture indicated by the second radar data and a motion characteristic of the second gesture;

It should be understood that there is also a preset mapping relationship between the first gesture and the second gesture. Specifically, the first gesture can be used to enable the adjustment mode of the target function corresponding to the gesture type of the first gesture. In the case of the adjustment mode of the target function, the user can only adjust the target function based on the gesture type (the gesture type of the second gesture) corresponding to the adjustment mode of the target function.

According to the motion characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

Among them, the adjustment range indicates the adjustment size of the fine adjustment, such as the size of the volume adjustment, the lift height of the window, etc., and the adjustment direction may indicate the adjustment direction of the fine adjustment, such as increasing or decreasing the volume, raising or lowering the vehicle, etc. , the adjustment speed indicates the adjustment size per unit time during fine adjustment, that is, the rate of change of the value of the adjustment, such as the rate of change of the volume during adjustment, the rate of raising the window, etc.

Wherein, in the scenario of fine adjustment, the above adjustment information can be combined with each other;

It should be noted that, in some implementations of fine adjustment, the fine adjustment can be performed only based on the adjustment direction, such as waving the left hand, indicating that the volume will be increased to the adjacent fixed position (for example, 100 is the maximum volume, and the fixed position It can be 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100), and each time you wave your hand to the left, you can increase it to the adjacent volume point (for example, increase it from 10 to 20). Waving right means to turn down the volume to the adjacent fixed point.

In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be enough in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of the waking up gesture are coherent. Taking the duration of the gesture indicated by the first radar data as the basis for whether to enable the fine-tuning mode is more in line with the user's thinking and usage habits, and reduces the learning cost of the user.

In a possible implementation, the first radar data is acquired before the second radar data.

In a possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or, the first radar data and the second radar data are Radar data acquired at intervals of a target time period on the domain, where the duration of the target time period is less than a second threshold. Wherein, the second threshold may be the time when the processor is processing the first radar data, and during this time, the adjustment function for the target function has not been activated.

In a possible implementation, the first gesture and the second gesture can also be continuous gesture actions of the user. The so-called continuous gesture actions can be understood as the hand shapes of the first gesture and the second gesture are the same (or The difference is very small), optionally, the first gesture may be a static gesture or a gesture whose movement range is smaller than a threshold, and since the second gesture needs to adjust the target function to a certain extent, the second gesture may be It is a gesture whose movement range is greater than the threshold.

In the embodiment of the present application, the hand shapes of the first gesture and the second gesture are the same, so that the gesture when the user wakes up the fine-tuning function and the gesture used when fine-tuning are the same hand-shaped gestures, which can make The user can accurately adjust the function with a small learning cost.

In a possible implementation, the first gesture is a finger pinching gesture, and the second gesture is a gesture of holding the fingers pinching and dragging; or, the first gesture is a palm hovering gesture, The second gesture is an upward gesture or a downward gesture; or, the first gesture is a palm hovering gesture, and the second gesture is a left and right waving gesture; or, the first gesture is a palm hovering gesture Gesture, the second gesture is a gesture of pushing back and forth; or, the first gesture is a gesture of making a fist, and the second gesture is a gesture of keeping the fist and moving; or, the first gesture is a palm For a jiggling gesture, the second gesture is a lifting gesture or a pressing gesture; or, the first gesture is a gesture of making a fist and extending a thumb, and the second gesture is maintaining the fist and extending a thumb. Thumbs up and push back and forth gesture. The gesture-semantic fit adjustment function of the above-mentioned second gesture conforms to user habits and can help reduce learning costs.

In a possible implementation, before enabling the adjustment function for the target function, the method further includes: based on a preset correspondence, determining that the gesture type of the first gesture corresponds to the target function , wherein the preset correspondence includes a mapping between gesture types and functions.

In a possible implementation, the gesture type of the first gesture is finger pinching, and the target function is to adjust the progress of the video or audio played by the application; or,

The gesture type of the first gesture is circle drawing, and the target function is volume adjustment; or,

The gesture type of the first gesture is palm hovering, and the target function is display brightness adjustment or zoom adjustment of a display image; or,

The gesture type of the first gesture is making a fist, and the target function is movement adjustment of the display interface; or,

The gesture type of the first gesture is palm flickering, and the target function is window height adjustment; or,

The gesture type of the first gesture is to make a fist and extend a thumb, and the target function is to adjust the front and rear positions of the seats in the vehicle cabin.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold, and then recognize that the gesture category of the user's gesture is finger pinching , and then you can turn on the function adjustment mode for adjusting the progress of the video or audio played by the application.

Specifically, the processor may recognize that there is a gesture of the user in the monitoring area of the radar system at a certain moment, and determine that the duration of the gesture of the user exceeds the first threshold, and then may recognize that the gesture category of the gesture of the user is circle drawing , and then you can turn on the function adjustment mode for volume adjustment.

Specifically, the processor can recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds the first threshold, and then can recognize that the gesture category of the user's gesture is palm hanging Stop, and then you can start the function adjustment mode for display brightness adjustment or display image zoom adjustment.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold, and then recognize that the gesture category of the user's gesture is a fist, Furthermore, a function adjustment mode for mobile adjustment of the display interface can be enabled.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds the first threshold, and then may recognize that the gesture type of the user's gesture is a light palm Shake, and then you can turn on the function adjustment mode of window height adjustment.

Specifically, the processor may recognize that there is a gesture of the user in the monitoring area of the radar system at a certain moment, and determine that the duration of the gesture of the user exceeds the first threshold, and then may recognize that the gesture category of the gesture of the user is fist and Stretch out your thumb, and then you can turn on the function adjustment mode for adjusting the front and rear positions of the seats in the cabin.

In the embodiment of the present application, when it is determined based on the first radar data that there is a first gesture and the duration of the first gesture exceeds a first threshold, the adjustment function for the target function may be enabled.

Specifically, when the adjustment function for the target function is turned on, certain feedback information may be presented, and the feedback information may indicate that the adjustment function for the target function has been turned on. Specifically, when the adjustment function for the target function is turned on, A target presentation corresponding to the target function may be performed, and the target presentation is used to indicate that the adjustment function for the target function has been turned on.

In a possible implementation, the target presentation may include: displaying controls for adjusting the target function. In the application scenario of a smart home, the target presentation can be performed on an electronic device with a display; in the scenario of a smart cockpit, the target presentation can be performed on the central control screen in the car cabin.

Taking the target function as the progress adjustment of the video or audio played by the application as an example, the target presentation may be the display of a progress bar.

Taking the target function as volume adjustment as an example, the target presentation may be the display of a volume adjustment control.

Taking the target function as display brightness adjustment as an example, the target presentation may be the display of a display brightness adjustment control.

Taking the target function as an example of displaying zoom adjustment of an image, the target presentation may be the display of a zoom control of an image.

Taking the target function as the mobile adjustment of the display interface as an example, the target presentation may be the display of the mobile controls of the display interface.

In a possible implementation, the target presentation may include: a vibration prompt of hardware related to the target function, for example, in the scenario of a smart car cabin, the target presentation may be a seat vibration prompt.

Taking the target function as an example of adjusting the front and rear positions of the seats in the vehicle cabin, the target presentation may be a vibration reminder of the seat to be adjusted.

In a possible implementation, the target presentation may include: a sound prompt, which may include a voice that the adjustment function for the target function has been turned on, for example, the progress of the video or audio played by the application with the target function is adjusted as For example, the target presentation can be to play the voice "The progress adjustment function of the video or audio played by the application has been turned on"; if the target function is volume adjustment as an example, the target presentation can be to play the voice "The volume adjustment function has been turned on"; If the target function is display brightness adjustment as an example, the target presentation can be to play the voice "The display brightness adjustment function has been turned on"; if the target function is the zoom adjustment of the displayed image, the target presentation can be to play the voice "The zoom function of the image is turned on". If the target function is the height adjustment of the car window as an example, the target presentation can be to play the voice "The window height adjustment function has been turned on"; if the target function is the front and rear position adjustment of the seat in the cabin, the target presentation The voice "The front and rear position adjustment function of the seat in the cabin has been turned on" can be played.

In a possible implementation, the indicating the first gesture based on the first radar data and the duration of the first gesture exceeds a first threshold includes: indicating the user's gesture based on the first radar data, And the duration of the user's gesture exceeds a first threshold, and according to the first radar data, it is determined that the user's gesture is a first gesture, and the first gesture is used to indicate to turn on the adjustment function.

In a possible implementation, part of the radar data may be intercepted from the first radar data, and according to the part of the radar data, it is determined that the user's gesture is the first gesture. Optionally, the part of radar data is the first N radar data in the first radar data. Different from gesture detection, gesture interception is to intercept some gestures of appropriate length during the process of gesture action for gesture recognition. Therefore, the interception length is the key to gesture interception, if the interception is too short or too long, this part of the gesture recognition will fail. Optionally, the gesture interception may be performed through a time interception method and a gesture feature interception method.

The time interception method is consistent with the idea of independent gesture judgment. From the perspective of time, N radar data (for example, N chirp signals are intercepted) are intercepted after the gesture starts, and gesture recognition is performed on the intercepted signals. The time interception method is simple, direct but effective, and its effectiveness comes from the following aspects: First, the gesture recognition algorithm based on the multi-dimensional feature fusion network based on the self-attention mechanism can be used in the subsequent determination of the gesture category. The length of the signal is not sensitive to the change of the signal length, similar to the characteristics of gestures, and the length of time (that is, the speed of gestures) is slightly different, which has little impact on the recognition results, and the length of the same gesture itself of different users is also different; A threshold, the judgment based on the duration can ensure that independent gestures will not be intercepted, and thus will not affect the recognition of independent gestures.

The gesture feature interception method refers to analyzing the characteristic changes of a specific gesture and completing the gesture interception. The interception length is not fixed and changes with the gesture situation. For example: Hover gesture interception can be completed from distance or speed changes, and the first circle of continuous circle drawing can be intercepted from distance, angle, and speed changes. Gesture feature interception can solve the difference in gesture length caused by different users and different gestures The influence of sex on interception, the interception of a single gesture is more accurate.

Based on the above description, the time interception method is applicable to situations where the time lengths of different wake-up gestures are similar; and the gesture feature interception method is suitable for different wake-up gestures having the same feature with similar features, and a single feature can be used to realize the interception of different wake-up gestures. In practical applications, which interception method to choose can be comprehensively considered according to the type and characteristics of the wake-up gesture.

In a possible implementation, the motion feature is a single salient feature of the gesture (such as distance, speed, angle feature, etc.), and the recognition of a certain type of gesture can be realized by analyzing the feature. Gesture type recognition based on the motion characteristics of gestures only needs to perform some feature analysis, without feature fusion and neural network, so it can simplify part of the gesture recognition work, reduce the amount of calculation, and improve real-time performance.

In a possible implementation, the determining that the user's gesture is a first gesture according to the first radar data includes: acquiring a motion feature of the user's gesture according to the first radar data, and Determining that the user's gesture is the first gesture according to the motion characteristics of the user's gesture; or, according to the first radar data, determining that the user's gesture is the first gesture through a pre-trained gesture classification network.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include: Distance information, where the distance information includes at least one of a change over time of a distance between the second gesture and the radar system, a change rate of the distance, and a change direction of the distance.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include: Velocity information, where the velocity information includes the variation of the moving velocity of the second gesture in the radar field with time.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include: Angle information, where the angle information includes a change over time of an angle between the second gesture and the radar system, where the angle includes an azimuth angle and/or an elevation angle.

In the embodiment of the present application, on the basis of gesture feature extraction, gesture features are finely quantified, including distance, speed, horizontal angle, pitch angle, and the like. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

In a possible implementation, after the adjustment of the target function based on the adjustment information, the method further includes: acquiring third radar data; indicating a third gesture based on the third radar data, closing For the adjustment function of the target function; the third gesture is a hand-off gesture or a hovering gesture.

In a second aspect, the present application provides a function adjustment method, the method comprising:

Acquiring target radar data, the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system; wherein, in the design where there is a wake-up gesture, the target radar data can be as described in the first aspect second radar data;

According to the target radar data, determine the motion feature of the target gesture; the feature type of the motion feature of the target gesture includes at least two of distance information, velocity information, or angle information, and the distance information includes the target gesture. The distance between the radar system and the radar system changes over time, the speed information includes the relative speed of the target gesture and the radar system changes over time, and the angle information includes the target gesture in the radar field The change in angle over time, said angle including azimuth and/or elevation angle;

According to the movement characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction and adjustment speed, and the target function is adjusted based on the adjustment information.

In existing implementations, time of flight (TOF) is used to achieve fine adjustment. Due to the limitation of TOF-related hardware, the sensitivity of fine adjustment and the accuracy of operation are very low. The embodiment of the present application adopts radar ( For example, the millimeter-wave radar) realizes fine adjustment, which can improve the accuracy of the operation, and when the fine adjustment of the function is performed, the adjustment action has at least a certain characteristic of significant change, such as distance or angle or speed. On the basis of the motion feature extraction, the gesture features are finely quantified, including distance, speed, horizontal angle, pitch angle, etc. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

In a possible implementation, the change of the distance over time includes:

At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time;

The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time.

In a possible implementation, the target gesture is a periodic gesture, and the change of the relative speed over time is used to determine the number of gesture cycles of the target gesture;

The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

It should be understood that for periodic gestures, other types of motion features may also be used for fine adjustment, which is not limited here.

In a possible implementation, the change of the angle over time includes:

At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time;

The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time.

In a possible implementation, before determining the motion feature of the target gesture according to the target radar data, the method further includes:

When the target gesture is a periodic gesture or a gesture whose relative velocity to the radar system is constantly changing, determining that the feature type of the motion feature of the target gesture includes the velocity information;

When the target gesture is a gesture whose distance from the radar system is constantly changing, determining that the feature type of the motion feature of the target gesture includes the distance information;

Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information.

For different gesture categories, the corresponding motion feature types can be obtained, which reduces the amount of data processing on the premise of ensuring accurate recognition.

In a third aspect, the present application provides a function adjustment device, the device comprising:

an acquisition module, configured to acquire the first radar data;

A function enabling module, configured to enable an adjustment function for a target function based on the first radar data indicating a first gesture and the duration of the first gesture exceeds a first threshold;

The acquisition module is also used to acquire the second radar data;

A function adjustment module, configured to determine, according to the second radar data, the second gesture indicated by the second radar data and the Movement characteristics; and,

According to the motion characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be enough in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of the waking up gesture are coherent. Taking the duration of the gesture indicated by the first radar data as the basis for whether to enable the fine-tuning mode is more in line with the user's thinking and usage habits, and reduces the learning cost of the user.

In a possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

In a possible implementation, the first radar data is acquired before the second radar data.

In a possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or,

The first radar data and the second radar data are radar data acquired at intervals of a target time period in the time domain, and the duration of the target time period is less than a threshold.

In a possible implementation, the first gesture and the second gesture are continuous gesture actions of the user.

In a possible implementation, the gesture types of the first gesture and the second gesture are the same, the first gesture is a static gesture or a gesture with a movement range smaller than a threshold, and the second gesture is a movement range Gestures greater than the threshold.

In a possible implementation, the first gesture is a gesture of pinching fingers, and the second gesture is a gesture of keeping the fingers pinched and dragging; or,

The first gesture is a palm hovering gesture, and the second gesture is an upward gesture or a downward gesture; or,

The first gesture is a palm hovering gesture, and the second gesture is a left and right waving gesture; or,

The first gesture is a palm hovering gesture, and the second gesture is a forward and backward push gesture; or,

The first gesture is a gesture of making a fist, and the second gesture is a gesture of keeping the fist and moving; or,

The first gesture is a flicking gesture of the palm, and the second gesture is an upward gesture or a downward gesture; or,

The first gesture is a gesture of making a fist and extending a thumb, and the second gesture is a gesture of maintaining the fist and extending a thumb and pushing back and forth.

In a possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture have a movement range greater than a threshold gesture.

In a possible implementation, both the first gesture and the second gesture are circle-drawing gestures.

In a possible implementation, the function enabling module is also used for:

Before enabling the adjustment function for the target function, based on a preset correspondence, it is determined that the gesture type of the first gesture corresponds to the target function, wherein the preset correspondence includes gesture type and Mapping between functions.

In a possible implementation, the gesture type of the first gesture is finger pinching, and the target function is to adjust the progress of the video or audio played by the application; or,

The gesture type of the first gesture is circle drawing, and the target function is volume adjustment; or,

The gesture type of the first gesture is palm hovering, and the target function is display brightness adjustment or zoom adjustment of a display image; or,

The gesture type of the first gesture is making a fist, and the target function is movement adjustment of the display interface; or,

The gesture type of the first gesture is palm flickering, and the target function is window height adjustment; or,

The gesture type of the first gesture is to make a fist and extend a thumb, and the target function is to adjust the front and rear positions of the seats in the vehicle cabin.

In a possible implementation, the device also includes:

A presenting module, configured to present a target corresponding to the target function before the adjustment of the target function based on the adjustment information, where the target presentation is used to indicate that the adjustment function for the target function has been enabled.

In a possible implementation, the target presentation includes at least one of the following:

a display of controls for making adjustments to said target function;

Vibration alerts for hardware associated with said target function; and,

Sound prompt.

In a possible implementation, the indicating the first gesture based on the first radar data and the duration of the first gesture exceeds a first threshold includes:

Based on the first radar data indicating the user's gesture, and the duration of the user's gesture exceeds a first threshold, according to the first radar data, determine that the user's gesture is a first gesture, and the first gesture It is used to indicate that the adjustment function is turned on.

In a possible implementation, the determining that the user's gesture is the first gesture according to the first radar data includes:

intercepting part of the radar data from the first radar data;

According to the part of the radar data, it is determined that the user's gesture is a first gesture.

In a possible implementation, the part of radar data is the first N radar data in the first radar data.

In a possible implementation, the determining that the user's gesture is the first gesture according to the first radar data includes:

According to the first radar data, acquiring a motion feature of the user's gesture, and determining that the user's gesture is a first gesture according to the motion feature of the user's gesture; or,

According to the first radar data, the user's gesture is determined to be the first gesture through a pre-trained gesture classification network.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

The distance information of the second gesture, the distance information including the change over time of the distance between the second gesture and the radar system, the change rate of the distance, and the change direction of the distance at least one of .

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

Velocity information of the second gesture, where the velocity information includes a change over time of a moving velocity of the second gesture in the radar field.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

Angle information of the second gesture, where the angle information includes a change over time of an angle between the second gesture and the radar system, and the angle includes an azimuth and/or an elevation angle.

In a possible implementation, the acquisition module is also used to:

acquiring third radar data after said adjusting said target function based on said adjustment information;

The device also includes:

A function closing module, configured to indicate a third gesture based on the third radar data, and close the adjustment function for the target function; the third gesture is a hand-off gesture or a hovering gesture.

In a fourth aspect, the present application provides a function adjustment device, the device comprising:

An acquisition module, configured to acquire target radar data, which is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system;

The motion feature determination module is configured to determine the motion feature of the target gesture according to the target radar data; the feature type of the motion feature of the target gesture includes at least two of distance information, velocity information or angle information, the The distance information includes the change over time of the distance between the target gesture and the radar system, the speed information includes the change over time of the relative speed between the target gesture and the radar system, and the angle information includes the The angle of the target gesture in the radar field changes over time, the angle includes an azimuth and/or an elevation angle;

A function adjustment module, configured to determine adjustment information according to the movement characteristics, the adjustment information includes at least one of adjustment range, adjustment direction and adjustment speed, and adjust the target function based on the adjustment information.

When fine-tuning the function, the adjustment action has at least one significant change feature, such as distance or angle or speed. The embodiment of the present application finely quantifies the gesture features on the basis of the motion feature extraction of gestures, including distance , speed, horizontal angle, pitch angle, etc. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

In a possible implementation, the change of the distance over time includes:

At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time;

The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time.

In a possible implementation, the target gesture is a periodic gesture, and the change of the relative speed over time is used to determine the number of gesture cycles of the target gesture;

The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

In a possible implementation, the change of the angle over time includes:

At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time;

The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time.

In a possible implementation, the motion feature determining module is further configured to: before determining the motion feature of the target gesture according to the target radar data, based on the target gesture being a periodic gesture or being determining the type of feature that characterizes the motion of the target gesture includes the velocity information when the relative velocity of the gesture to the radar system is changing;

When the target gesture is a gesture whose distance from the radar system is constantly changing, determining that the feature type of the motion feature of the target gesture includes the distance information;

Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information.

In a fifth aspect, the present application provides a function adjustment device, including: one or more processors and a memory; wherein, computer-readable instructions are stored in the memory;

The one or more processors read the computer-readable instructions to cause the computer device to implement the method of the first aspect and any optional method thereof, and the second aspect and any optional method thereof.

In a possible implementation, the device further includes a radar system for:

provide a radar field;

sensing reflections from users in the radar field;

analyzing reflections from the user in the radar field; and

Based on the analysis of the reflections, radar data is provided.

In the sixth aspect, the embodiment of the present application provides a computer-readable storage medium, which is characterized by comprising computer-readable instructions, and when the computer-readable instructions are run on a computer device, the computer device is made to execute the above-mentioned first aspect. and any optional method thereof, and the second aspect and any optional method thereof.

In the seventh aspect, the embodiment of the present application provides a computer program product, which is characterized in that it includes computer-readable instructions, and when the computer-readable instructions are run on a computer device, the computer device executes the above-mentioned first aspect and its Any optional method, and the second aspect and any optional method thereof.

In an eighth aspect, the present application provides a chip system, which includes a processor, configured to support an execution device or a training device to implement the functions involved in the above aspect, for example, send or process the data involved in the above method; or, information. In a possible design, the system-on-a-chip further includes a memory, and the memory is used for storing necessary program instructions and data of the execution device or the training device. The system-on-a-chip may consist of chips, or may include chips and other discrete devices.

In a ninth aspect, the present application provides a vehicle, including: one or more processors and a memory; wherein, computer-readable instructions are stored in the memory;

The one or more processors read the computer-readable instructions, so that the computer device implements the above-mentioned first aspect and any optional method thereof, and the second aspect and any optional method thereof ;

The vehicle also includes a radar system in the cabin for:

provide a radar field;

sensing reflections from users in the radar field;

analyzing reflections from the user in the radar field; and

Based on the analysis of the reflections, radar data is provided.

In a possible implementation, the cabin further includes a main driving position, a co-driving position, and a steering wheel fixed in front of the main driving position; wherein,

The radar system includes:

A first radar system comprising a first radar integrated circuit comprising:

at least one first transmit antenna;

at least one first receive antenna;

The first radar integrated circuit is located on the side of the steering wheel close to the passenger seat, wherein the steering wheel is not rotated by the user.

In a possible implementation, the at least one first transmitting antenna is used to provide a radar field to at least one of the following areas:

an area of the primary driver's seat that is close to the passenger seat; and,

The area between the main driver's seat and the passenger driver's seat.

In a possible implementation, the cabin also includes a main driver's seat, a co-pilot's seat and a center console;

The radar system includes:

A second radar system comprising a second radar integrated circuit comprising:

at least one second transmit antenna;

at least one second receive antenna;

The second radar integrated circuit is located on the side of the center console away from the direction of the front of the vehicle.

In a possible implementation, the at least one second transmitting antenna is used to provide a radar field to at least one of the following areas:

The area near the co-pilot's seat in the main driver's seat;

an area of the passenger seat close to the main driver's seat; and

The area between the main driver's seat and the passenger driver's seat.

In a possible implementation, the cabin further includes a main driver's seat, a passenger seat and an armrest box, and the armrest box is fixed in an area between the main driver's seat and the passenger seat;

The radar system includes:

A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including:

at least one third transmit antenna;

at least one third receive antenna;

The third radar integrated circuit is located on the side of the armrest box facing the main console.

In a possible implementation, the at least one third transmitting antenna is used to provide a radar field to at least one of the following areas:

The area near the co-pilot's seat in the main driver's seat;

an area of the passenger seat close to the main driver's seat; and

The area between the main driver's seat and the passenger driver's seat.

Among them, the radar system located on the right side of the steering wheel (such as the first radar system in the embodiment of the present application) emits the radar beam obliquely to the right. This deployment position is mainly for the driver to control, which can mainly reduce the driver's body and Signal interference caused by the movement of the arm to control the steering wheel.

Among them, the radar beam of the radar system (such as the second radar system in the embodiment of the present application) deployed near the center console is irradiated toward the middle, which can be used by the main and co-drivers at the same time, and the passenger's body interference is small.

Among them, the radar system (for example, the third radar system in the embodiment of the present application) located at the position of the armrest box illuminates the radar beam upwards, which can be used by the main driver and the co-pilot at the same time, and the passenger's body interference is small.

The embodiment of the present application allows the user to complete gesture control under the conditions of no contact, no line of sight transfer, and short arm movement distance, which ensures driving safety and convenient operation.

In a possible implementation, the vehicle further includes: a seat;

The one or more processors are further configured to read the computer-readable instructions, so as to control the seat to vibrate when the adjustment function for the target function is turned on.

In a tenth aspect, the present application provides a vehicle, including: a cabin; the cabin includes a radar system;

The radar system for:

provide a radar field;

sensing reflections from users in the radar field;

analyzing reflections from the user in the radar field; and

providing radar data based on the analysis of the reflection;

The radar system includes:

A first radar system comprising a first radar integrated circuit comprising:

at least one first transmit antenna;

at least one first receive antenna;

The first radar integrated circuit is located on the side of the steering wheel close to the passenger seat, wherein the steering wheel is not rotated by the user.

In a possible implementation, the at least one first transmitting antenna is used to provide a radar field to at least one of the following areas:

an area of the primary driver's seat that is close to the passenger seat; and,

The area between the main driver's seat and the passenger driver's seat.

In a possible implementation, the cabin also includes a main driver's seat, a co-pilot's seat and a center console;

The radar system includes:

A second radar system comprising a second radar integrated circuit comprising:

at least one second transmit antenna;

at least one second receive antenna;

The second radar integrated circuit is located on the side of the center console away from the direction of the front of the vehicle.

In a possible implementation, the at least one second transmitting antenna is used to provide a radar field to at least one of the following areas:

The area near the co-pilot's seat in the main driver's seat;

an area of the passenger seat close to the main driver's seat; and

The area between the main driver's seat and the passenger driver's seat.

In a possible implementation, the cabin further includes a main driver's seat, a passenger seat and an armrest box, and the armrest box is fixed in an area between the main driver's seat and the passenger seat;

The radar system includes:

A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including:

at least one third transmit antenna;

at least one third receive antenna;

The third radar integrated circuit is located on the side of the armrest box facing the main console.

In a possible implementation, the at least one third transmitting antenna is used to provide a radar field to at least one of the following areas:

The area near the co-pilot's seat in the main driver's seat;

an area of the passenger seat close to the main driver's seat; and

The area between the main driver's seat and the passenger driver's seat.

Among them, the radar system located on the right side of the steering wheel (such as the first radar system in the embodiment of the present application) emits the radar beam obliquely to the right. This deployment position is mainly for the driver to control, which can mainly reduce the driver's body and Signal interference caused by the movement of the arm to control the steering wheel.

Among them, the radar beam of the radar system (such as the second radar system in the embodiment of the present application) deployed near the center console is irradiated toward the middle, which can be used by the main and co-drivers at the same time, and the passenger's body interference is small.

Among them, the radar system (for example, the third radar system in the embodiment of the present application) located at the position of the armrest box illuminates the radar beam upwards, which can be used by the main driver and the co-pilot at the same time, and the passenger's body interference is small.

The embodiment of the present application allows the user to complete gesture control under the conditions of no contact, no line of sight transfer, and short arm movement distance, which ensures driving safety and convenient operation.

An embodiment of the present application provides a function adjustment method, the method including: acquiring first radar data; based on the first radar data indicating a first gesture, and the duration of the first gesture exceeds a first threshold, turning on The adjustment function for the target function; acquiring second radar data; in response to the activation of the adjustment function for the target function, according to the second radar data, determine the second gesture indicated by the second radar data, and the motion characteristics of the second gesture; according to the motion characteristics, determine adjustment information, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and adjust the target based on the adjustment information function to adjust. In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be enough in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of the waking up gesture are coherent. Taking the duration of the gesture indicated by the first radar data as the basis for whether to enable the fine-tuning mode is more in line with the user's thinking and usage habits, and reduces the learning cost of the user.

Description of drawings

Figure 1a is a schematic diagram of the scene provided by the embodiment of the present application;

Figure 1b is a schematic diagram of the scene provided by the embodiment of the present application;

Figure 1c is a schematic diagram of the scene provided by the embodiment of the present application;

FIG. 2 is a schematic diagram of a scene provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a scene provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a scene provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a scene provided by an embodiment of the present application;

FIG. 6 is a schematic flowchart of a function adjustment method provided by the embodiment of the present application;

Figure 7a is a schematic diagram of the scene provided by the embodiment of the present application;

Figure 7b is a schematic diagram of a radar signal provided by the embodiment of the present application;

FIG. 8 is a schematic diagram of radar data processing provided by the embodiment of the present application;

FIG. 9 is a schematic diagram of radar data processing provided by the embodiment of the present application;

Figure 10 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 11a is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 11b is a schematic diagram of gesture data provided by the embodiment of the present application;

Fig. 11c is a schematic diagram of radar data processing provided by the embodiment of the present application;

Figure 12a is a schematic diagram of a gesture provided by the embodiment of the present application;

Fig. 12b is a schematic flowchart of a function adjustment method provided by the embodiment of the present application;

FIG. 13 is a schematic diagram of radar data processing provided by the embodiment of the present application;

Figure 14 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 15 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 16 is a schematic diagram of gesture data provided by the embodiment of the present application;

Fig. 17 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 18 is a schematic diagram of gesture data provided by the embodiment of the present application;

Fig. 19 is a schematic diagram of a radar antenna provided by the embodiment of the present application;

Fig. 20 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 21 is a schematic diagram of a radar angle provided by the embodiment of the present application;

Figure 22 is a schematic diagram of gesture data provided by the embodiment of the present application;

Figure 23 is a schematic diagram of gesture data provided by the embodiment of the present application;

Fig. 24a is a schematic flowchart of a function adjustment method provided by the embodiment of the present application;

Fig. 24b is a schematic flowchart of a function adjustment method provided by the embodiment of the present application;

Fig. 25 is a schematic structural diagram of a function adjustment device provided by an embodiment of the present application;

Fig. 26 is a schematic structural diagram of a function adjustment device provided by an embodiment of the present application;

Fig. 27 is a schematic structural diagram of a function adjustment device provided by an embodiment of the present application;

FIG. 28 is a schematic structural diagram of a chip provided by an embodiment of the present application.

Detailed ways

Embodiments of the present application are described below with reference to the drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only used to explain specific embodiments of the present application, and are not intended to limit the present application.

The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned accompanying drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used like this It can be interchanged under appropriate circumstances, and this is only to describe the distinguishing method adopted when describing the object of the same attribute in the embodiments of the application.In addition, the terms "comprising" and "having" and any deformation thereof are intended to be Covers a non-exclusive inclusion such that a process, method, system, product, or apparatus comprising a series of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to the process, method, product, or apparatus .

Embodiments of the present application are described below in conjunction with the accompanying drawings. Those of ordinary skill in the art know that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems. Firstly, the application scenario of the embodiment of this application is introduced:

The embodiments of the present application can be applied to scenarios requiring function adjustments such as smart homes and smart cockpits.

Next, combined with the product architecture included in the scenario, the architecture of the above application scenarios is described respectively.

Scenario 1. Smart home:

Referring to FIG. 1a, FIG. 1a shows a schematic structural diagram of a smart home system provided by an embodiment of the present application. As shown in Fig. 1a, the smart home system may include: an electronic device 100 (optional), one or more smart home devices 200, and a cloud server 300 (optional).

About Electronics 100:

Wherein, the electronic device 100 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (personal digital assistant, PDA), and a wearable device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, android, microsoft, or other operating systems. The aforementioned portable electronic device may also be other portable electronic devices, such as a laptop computer (laptop) with a touch-sensitive surface (such as a touch panel). It should also be understood that, in some other embodiments of the present application, the electronic device 100 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

The electronic device 100 may be installed with an application (application, APP) for managing smart home devices, or the electronic device 100 may access a world wide web (world wide web, web) page for managing smart home devices. Applications or web pages for managing smart home devices may be developed and provided by manufacturers of smart home devices (eg, manufacturers of smart routers (eg, Huawei)).

About the Smart Home Device 200:

Smart home devices refer to intelligent devices that can exchange information and even learn independently through wireless communication technology, which can provide users with convenient and effective services and reduce the workload of users. The smart home device 200 may include smart sockets, smart door locks, smart lamps, smart fans, smart air conditioners, smart curtains, smart TVs, smart rice cookers, smart routers, and so on. Exemplarily, as shown in FIG. 1 a , the smart home device 200 may include a smart lamp 201 , a smart TV 202 and a smart speaker 203 . Among them, the smart lamp 201 can control the change of light, such as the change of light color and brightness. The smart TV 202 can perform voice interaction with the user, for example, can receive the user's voice control instruction to play the user's favorite TV program. The smart speaker 203 can perform voice interaction with the user, for example, can receive the user's voice control instruction to play the user's favorite song. In some implementations, the smart speaker 203 can have an integrated voice assistant module, which can provide an interactive voice dialogue or query function through a "wake word" (for example, "Hello, Xiaoyi").

The smart home device 200 can be configured with a radar system (the architecture of the radar system can be shown in FIG. 2 ), and the radar system can transmit radar signals to the monitored area and receive the reflected signals of the radar signals (in the embodiment of this application, it can be referred to as Radar data), through the analysis and processing of reflected signals, the state determination of objects in the monitored area (such as moving state, sleeping state, static state, etc.), or the information recognition of gestures (such as the determination of gesture categories, Determination of the motion characteristics of gestures).

About the radar system:

According to different specific implementations of the radar system, the radar signal can have multiple carriers, for example: when the radar system is a microwave radar, the radar signal is a microwave signal; when the radar system is an ultrasonic radar, the radar signal is an ultrasonic signal ; When the radar system is a laser radar, the radar signal is a laser signal. It should be noted that when the radar system integrates multiple different radars, the radar signal may be a collection of multiple radar signals, which is not limited here.

A radar system may generate and transmit radar signals into an area that the radar system is monitoring. Referring to FIG. 2 , signal generation and transmission may be implemented by a radio frequency (radio frequency, RF) signal generator 12 , a radar transmitting circuit 14 and a transmitting antenna 32 . Radar transmit circuitry 14 generally includes any circuitry required to generate a signal for transmission via transmit antenna 32, such as pulse shaping circuitry, transmit trigger circuitry, RF switching circuitry, or other suitable transmit circuitry. The RF signal generator 12 and the radar transmit circuit 14 are controllable via the processor 20 which issues command and control signals via the control line 34 such that the desired RF signals are transmitted at the transmit antenna 32 with the desired configuration and signal parameters. Signal.

The radar system may also receive return radar signals at the analog processing circuit 16 via the receive antenna 30, which return radar signals may be referred to as "echoes," "radar data," "echo signals," "echo data," or "reflected signal". Analog processing circuitry 16 generally includes processing (e.g., signal separation, mixing, heterodyne and/or homodyne conversion, amplification, filtering, received signal triggering, signal switching and routing, and/or other suitable radar signal receiving function) any circuitry required. Accordingly, analog processing circuitry 16 generates one or more analog signals, such as an in-phase (I) analog signal and a quadrature (Q) analog signal. The resulting analog signal is transmitted to and digitized by an analog-to-digital converter circuit (analog-to-digital converter (ADC) 18 . The digitized signal is then forwarded to processor 20 for reflected signal processing.

It should be understood that the above radar system may also not be deployed in the smart home device 200 , but be deployed independently with the smart home device 200 .

Exemplarily, taking the smart home device 200 as a smart screen as an example, referring to FIG. 1b, the radar system can be deployed at but not limited to the corner position of the upper frame of the display screen shown in FIG. 1b. Referring to FIG. 1c, the radar system It can also be deployed independently with the smart home device 200, which is set in the smart home scene as an independent sensing unit.

About the processor:

Processor 20 may be one of various types of processors capable of processing digitized received signals and controlling RF signal generator 12 and radar transmit circuit 14 to provide radar operation of terminal device 100 and function. Accordingly, processor 20 may be a digital signal processor (DSP), microprocessor, microcontroller, or other such device.

In some implementations, the processor 20 may include a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general purpose processor, a digital signal processor (digital signal processor) processing, DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits, for example, the processor 20 can be a hardware system with the function of executing instructions, such as a CPU, DSP, etc., or a hardware system that does not have the ability to execute instructions Functional hardware systems, such as ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without the function of executing instructions and hardware systems with the function of executing instructions.

In order to perform the radar operations and functions of the radar system, the processor 20 communicates via the system bus 22 with one or more other required circuits, such as one or more memory devices 24 consisting of one or more types of memory, any required The peripheral circuitry 26 is identified as well as any desired input/output circuitry 28 interfaces.

As mentioned above, the processor 20 can interface with the RF signal generator 12 and the radar transmitting circuit 14 via the control line 34 . In an alternate embodiment, RF signal generator 12 and/or radar transmit circuitry 14 may be connected to bus 22 such that they may communicate with processor 20, memory device 24, peripheral circuitry 26, and input/output circuitry 28 via bus 22. One or more communicate.

Wherein, the target object (such as the user's gesture in the embodiment of the present application) may be located in the surveillance area of the radar system, so the radar system can receive the reflected signal of the radar signal reflected by the target object (such as the first signal in the embodiment of the present application). radar data, second radar data, third radar data).

In an optional implementation, after receiving the radar data, the processor 20 may process the radar data to determine the gesture indicated by the reflected signal and gesture-related information, and perform related function control based on the gesture-related information .

It should be understood that the smart home system may include multiple smart home devices with data processing capabilities, and there is a communication connection relationship between each smart home device, so distributed computing can be realized through multiple smart home devices in the smart home system, Further, the above-mentioned processing to determine the gesture indicated by the reflected signal and the information related to the gesture may be implemented by multiple smart home devices in the smart furniture system.

In the embodiment of the present application, the processor 20 may obtain the code stored in the memory device 24 (or a memory device deployed separately from the processor 20 ) to implement the function adjustment method in the embodiment of the present application.

Specifically, the processor 20 may be a hardware system capable of executing instructions, and the function adjustment method provided in the embodiment of the present application may be a software code stored in a memory, and the processor 20 may acquire the software code from the memory, and execute the acquired The obtained software code is used to implement the function adjustment method provided by the embodiment of the present application.

It should be understood that the processor 20 can also be a combination of a hardware system that does not have the function of executing instructions and a hardware system that has the function of executing instructions. It can be implemented by a hardware system that executes the function of the instruction, which is not limited here.

In some possible implementations, the above step of determining the identity of the target object may also be implemented based on the interaction between the smart home device 200 and the cloud server 300 .

The smart home device 200 can be configured with a wireless communication module, and the smart home device 200 can establish a communication connection with the cloud server 300 through the wireless communication module.

About the wireless communication module:

The wireless communication module can provide wireless local area networks (wireless local area networks, WLAN) (such as wireless fidelity (Wi-Fi) network), bluetooth (bluetooth, BT), short-distance One or more of wireless communication methods such as wireless communication technology (near field communication, NFC) and infrared technology (infrared, IR). In some embodiments, the smart home device 200 can also be configured with a mobile communication module, which can provide solutions including 2G/3G/4G/5G and other wireless communication technologies applied on the electronic device 100 .

The smart home device 200 can be connected to the network through the wireless communication module or the mobile communication module, and then communicate with the cloud server 300 to receive data and instructions from the cloud server 300, or the smart home device 200 can send data, its own working status and working parameters are reported to the cloud server 300.

In an optional implementation, after receiving the radar data, the processor 20 may transmit the radar data to the cloud server 300, and then the server may process the radar data to determine the gesture indicated by the reflected signal and gesture-related information. .

In an optional implementation, the processor 20 may receive the gesture indicated by the reflection signal sent by the cloud server and information related to the gesture.

About cloud server 300:

The cloud server 300 is a device that provides safe and reliable elastic computing services, and can serve as a media platform to realize communication between the home and external control devices to meet the needs of remote control, detection and information exchange. Understandably, the cloud server 300 may include one or more servers, for example, the cloud server 300 may be a server cluster, and different servers may be used to provide different services. The cloud server 300 is associated with the manufacturer or service provider of the smart home device 200 . For example, the cloud server 300 may automatically send software updates to the smart home device 200 or provide cloud services for the smart home device 200 . In the embodiment of the present application, the cloud server 300 provides an interface for managing applications or web pages of smart home devices. The cloud server 300 may receive an instruction for managing smart home devices sent by the electronic device 100 through the interface, and based on the instruction, send an instruction to the corresponding smart home device to manage the smart home device. For example, the cloud server 300 may instruct the smart lamp 201 to turn on/off, adjust brightness or color temperature, etc. according to the instruction sent by the electronic device 100 .

Scenario 2: Intelligent cockpit

FIG. 3 is a schematic structural diagram of an interior of a car provided by an embodiment of the present application. At present, in the field of automobiles, in-vehicle terminals such as car machines (also known as in-car audio-visual entertainment systems) can be fixed on the center console of the car, and their screens can also be called central control display screens or central control screens. In addition, in some high-end cars, the cockpit is gradually fully digitalized, and there are multiple or one display screens in the cockpit, which are used to display content such as digital dashboards and in-vehicle entertainment systems. As shown in Figure 3, multiple display screens are arranged in the cockpit, such as a digital instrument display screen 101, a central control screen 102, a display screen 103 in front of a passenger (also known as a front row passenger) on the co-pilot seat, and a left rear screen. The display screen 104 in front of the passenger in the row and the display screen 105 in front of the passenger in the right rear row.

In addition, a radar system (also referred to simply as radar in subsequent embodiments) can also be deployed inside the car. Although only one radar 106 is shown near the A-pillar (pillar) on the driver's side in FIG. and the position of the radar is more flexible. For example, some cockpit radars can be set above the vehicle central control screen, some cockpit radars can be set on the left side of the vehicle central control screen, and some cockpit radars can be set on the A Pillars or B-pillars, and some cockpit radars can be set at the front of the vehicle's cockpit roof. For a specific description about the radar, reference may be made to the description about the radar system in FIG. 2 in the foregoing embodiment.

In order to be able to recognize the gesture information of the main driver and the co-pilot, the radar can be set on the side of the steering wheel close to the co-pilot, on the main console, and on the armrest box between the main driver and the co-pilot.

For example, reference can be made to Fig. 4, wherein Fig. 4 shows a schematic layout of a radar in the cabin. The direction of the field can be towards the area close to the passenger seat in the main driver's seat, and the area between the main driver's seat and the passenger seat. In addition, it can also be set on the center console towards the side of the main driver's seat and the passenger seat Radar 2. The direction of the radar field provided by radar 2 can be towards the area near the main driver's seat, the area near the main driver's seat in the passenger seat, and the area between the main driver's seat and the passenger seat.

For example, reference can be made to Fig. 5, wherein Fig. 5 shows a schematic layout of a radar in the cabin. As shown in Fig. 4, a radar 1 can be set on the side of the steering wheel close to the co-pilot's seat, and the radar 1 provides a radar The direction of the field can be towards the area close to the passenger seat in the main driver's seat, and the area between the main driver's seat and the passenger seat. In addition, it can also be set on the center console towards the side of the main driver's seat and the passenger seat Radar 2. The direction of the radar field provided by radar 2 can be towards the area near the main driver's seat, the area near the main driver's seat in the passenger seat, and the area between the main driver's seat and the passenger seat. In addition, The radar 3 can be installed on the armrest box between the main driver's seat and the co-pilot's seat on the side facing the main console. The direction of the radar field provided by the radar 3 can be towards the area close to the passenger's The area close to the main driver's seat, and the area between the main driver's seat and the co-pilot's seat.

The embodiment of the present application proposes three deployment positions of the radar system from the perspectives of facilitating the use of passengers, ensuring safety, reducing signal interference, and enhancing gesture characteristics.

Among them, the radar system located on the right side of the steering wheel (such as the first radar system in the embodiment of the present application) emits the radar beam obliquely to the right. This deployment position is mainly for the driver to control, which can mainly reduce the driver's body and Signal interference caused by the movement of the arm to control the steering wheel.

Among them, the radar beam of the radar system (such as the second radar system in the embodiment of the present application) deployed near the center console is irradiated toward the middle, which can be used by the main and co-drivers at the same time, and the passenger's body interference is small.

Among them, the radar system (for example, the third radar system in the embodiment of the present application) located at the position of the armrest box illuminates the radar beam upwards, which can be used by the main driver and the co-pilot at the same time, and the passenger's body interference is small.

The embodiment of the present application allows the user to complete gesture control under the conditions of no contact, no line of sight transfer, and short arm movement distance, which ensures driving safety and convenient operation.

The above-mentioned vehicles 200 may be cars, trucks, motorcycles, buses, boats, airplanes, helicopters, lawn mowers, recreational vehicles, playground vehicles, construction equipment, trams, golf carts, trains, and trolleys, etc. The application examples are not particularly limited.

Embodiments of the present application are described below with reference to the drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only used to explain specific embodiments of the present application, and are not intended to limit the present application.

Referring to FIG. 6, FIG. 6 is a schematic diagram of an embodiment of a function adjustment method provided by the embodiment of the present application. The function adjustment method provided by the embodiment of the present application can be applied to an electronic device or a server, wherein the electronic device can be a vehicle-mounted device, a computer , smartphones or smart watches. As shown in Figure 6, the function adjustment method provided by the embodiment of the present application may include:

601. Acquire first radar data.

Taking the application scenario of smart home as an example, indoor users can perform radar gesture operations within the detection range of radar, and users can adjust specific functions in smart home through radar gesture operations.

Taking the application scenario of the smart cockpit as an example, passengers in the car (such as the main driver and co-pilot passengers) can perform radar gesture operations within the detection range of the radar, and the user can control specific functions in the vehicle system through radar gesture operations. Make adjustments.

Among them, the radar gestures (such as the first gesture, the second gesture, the third gesture, and the target gesture) in the embodiments of the present application are radar-based touch-independent gestures (radar-based touch-independent gestures), which can also be called Dubbed "3Dgesture", a radar gesture refers to the nature of a gesture that is spatially distant from the electronic device (eg, the gesture does not require the user to touch the device, although the gesture does not preclude touch). A radar gesture itself may typically only have a two-dimensional active information component, such as a radar gesture consisting of an upper-left to lower-right swipe, but since a radar gesture is some distance from the electronic device (the "third" dimension or depth), The radar gestures in the embodiments of the present application can generally be regarded as three-dimensional.

In a possible implementation, when the user performs a gesture operation, the user's gesture can be located in the monitoring area of the radar system, and the radar system can transmit radar signals to the monitored area and receive the reflection signal of the radar signal from the user's gesture . For example, the generation and transmission of signals can be realized by the RF signal generator 12, the radar transmitting circuit 14 and the transmitting antenna 32 in the above-mentioned embodiments.

Wherein, the radar system may generate a radar signal, and types of the radar signal may include but not limited to a continuous wave (continuous wave, CW) signal and a chirp signal (or called chirp).

Take the chirp signal as an example, the chirp signal is an electromagnetic signal whose frequency changes with time. Typically, the frequency of rising chirp signals increases over time, while the frequency of falling chirp signals decreases over time. Frequency changes in chirp signals can take on many different forms. For example, the frequency of a linear frequency modulated (LFM) signal varies linearly. Other forms of frequency variation in chirp signals include exponential variation. In addition to chirp signals of the type in which the frequency varies continuously according to some predetermined function (ie, linear or exponential), chirp signals can also be generated in the form of stepped chirp signals, in which the frequency is varied in steps. That is, a typical stepped chirp signal includes a number of frequency steps, where the frequency is constant at each step for some predetermined duration. The step chirp signal can also be pulsed on and off, where the pulse is on during some predetermined period of time during each step of the chirp scan.

In a possible implementation, the radar system can transmit a chirp signal, where the mathematical expression of the chirp signal can be exemplarily:

B为带宽，

为固定初始相位，t_c为chirp信号周期，A为幅值，f₀为起始频率。in,

B is the bandwidth,

For the fixed initial phase, t _c is the period of the chirp signal, A is the amplitude, and f ₀ is the starting frequency.

In one possible implementation, the radar system may transmit radar signals and receive reflected signals from the user's gesture reflection.

Wherein, the so-called "reflection signal reflected by the user's gesture" can be understood as: a signal that the radar signal hits the user's gesture and is reflected by the user's gesture. Among them, in the scene of smart home, the radar signal can be the signal that the radar signal hits the target object when walking and is reflected by the target object; The signal reflected by the target object.

Furthermore, the processor may acquire the first radar data, and perform recognition on the gesture of the user and analysis of the gesture information based on the first radar data.

It should be understood that the first radar data in this embodiment of the present application may refer to a reflected signal received by a receiving antenna in a radar system at an analog processing circuit, where the reflected signal is an analog signal. After obtaining the analog signal, the analog signal may be transmitted to an analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal.

It should be understood that the analog signal obtained by the analog processing circuit can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal. The first radar data in the embodiment of the present application can also refer to the above digitized The digital signal is not limited here.

Next, based on the situation of the processor and the deployment position of the radar system, the implementation of the processor to obtain the first radar data is described:

1. The radar system and processor are deployed in the same electronic device:

Wherein, the electronic device may be a terminal in a smart home or a vehicle-mounted device in a smart cockpit;

In a possible implementation, the radar system can be deployed in the electronic device, and after the radar system acquires the first radar data, it can transmit the first radar data to the processor in the electronic device (if the first radar data is an analog signal, the analog-to-digital conversion circuit can convert the analog signal into a digital signal, and then transmit the digital signal to the processor), and the processor can process the first radar data.

2. The radar system and the processor are deployed in different electronic devices (for convenience of description, different electronic devices are described as A electronic device and B electronic device below):

In a possible implementation, the radar system can be deployed in electronic device A, and after acquiring the first radar data, the radar system can transfer the first radar data to the processor in electronic device B (if the first radar data If it is an analog signal, then the analog-to-digital conversion circuit in A electronic equipment can convert the analog signal into a digital signal, and then transmit the digital signal to the processor in B electronic equipment, or can transmit the analog signal to B electronic equipment, and B After the analog-to-digital conversion circuit of the processor in the electronic device converts the analog signal into a digital signal, the digital signal is transmitted to the processor in the B electronic device), and then the processor in the B electronic device can process the first radar data.

3. The radar system is deployed in the electronic equipment, and the processor is deployed in the cloud server:

In a possible implementation, the radar system can be deployed in the electronic device, and after the radar system acquires the first radar data, it can transmit the first radar data to the processor in the cloud server (if the first radar data is an analog signal, the analog-to-digital conversion circuit in the electronic device can convert the analog signal into a digital signal, and then transmit the digital signal to the processor in the cloud server, or can transmit the analog signal to the cloud server, and the processor module of the cloud server The digital conversion circuit converts the analog signal into a digital signal), and then the processor in the cloud server can process the first radar data.

Referring to FIG. 7 a , an exemplary operation of the radar system 102 is shown in FIG. 7 a . Wherein the radar system 102 is implemented as a frequency modulated continuous wave radar. In the environment, the user 302 is located at a distance from the monitored environment of the radar system 102 . To detect user 302, radar system 102 transmits a radar transmission 306 (depicted as radar transmission 306 in FIG. 7a). At least a portion of radar transmission 306 is reflected by user 302 . This reflected portion represents the reflected signal 308 (depicted as radar received signal 308 in FIG. 7a). Radar system 102 receives reflected signal 308 and processes reflected signal 308 to extract data for radar-based application 206 . As depicted, the magnitude of the reflected signal 308 is less than the magnitude of the radar transmitted signal 306 due to losses incurred during propagation and reflection.

Radar transmission 306 includes a sequence of chirps a 310-1 through 310-N, where N represents a positive integer greater than one. Radar system 102 may transmit chirps 310-1 through 310-N in continuous bursts, or as time-separated pulses. For example, the duration of each chirp 310-1 through 310-N may be on the order of tens or thousands of microseconds (eg, between approximately 30 microseconds (μs) to 5 milliseconds (ms)).

The individual frequencies of chirps 310 1 through 310-N may increase or decrease over time. In the depicted example, radar system 102 employs dual-slope cycling (eg, triangular frequency modulation) to linearly increase and linearly decrease the frequency of chirps 310-1 through 310-N over time. The dual slope cycle enables the radar system 102 to measure the Doppler shift caused by the motion of the user 302 .

In general, the transmit characteristics (e.g., bandwidth, center frequency, duration, and transmit power) of chirps 310-1 through 310-N can be tailored to achieve a specific detection range, range resolution, or Doppler sensitivity to detect user One or more features of 302 or one or more gestures performed by user 302 .

At radar system 102 , reflected signal 308 represents a delayed version of radar transmitted signal 306 . The amount of delay is proportional to the tilt range (eg, distance) from antenna array 212 of radar system 102 to user 302 . Specifically, this delay represents the sum of the time taken for radar transmit signal 306 to travel from radar system 102 to user 302 and the time taken for reflected signal 308 to travel from user 302 to radar system 102 . If user 302 and/or radar system 102 are moving, reflected signal 308 is shifted in frequency relative to radar transmitted signal 306 due to the Doppler effect. In other words, the characteristics of the reflected signal 308 depend on the motion of the hand and/or the motion of the radar system 102 . Similar to radar transmit signal 306, reflected signal 308 is composed of one or more of chirps 310-1 through 310N.

In a possible implementation, motion information of objects in the radar field (such as motion information of a user's gesture) can be extracted based on the first radar data, and the motion information can include but not limited to distance information, velocity information, angle information, etc., Among them, the distance information is contained in the frequency of each echo pulse, and the distance information of the gesture in the current pulse time can be obtained by performing fast Fourier transform on a single pulse in a fast time, and the distance information of each pulse can be integrated to obtain a single gesture The overall distance change information of . After FFT is performed on the fast time of the original gesture echo, FFT is performed on the slow time dimension, and its peak value can reflect the Doppler frequency of the target, which contains the speed information of the target. The slow time domain FFT needs to be performed in the same range gate, and because of the distance migration of the overall movement of the target, it is not possible to directly perform FFT on a certain range gate of the overall gesture, but the number of accumulated pulses should be set reasonably so that each FFT operation Gesture truncation basically has no distance migration.

Specifically, after the first radar data is acquired, preliminary processing (such as fast Fourier transform (FFT)) may be performed on the first radar data, and specifically, the processor may perform processing on the first radar data One-dimensional (1D) fast Fourier transform (fast fourier transform, FFT) calculation to obtain the range Fourier spectrum Range-FFT, and two-dimensional (2D) FFT calculation to obtain the range Doppler spectrum Range-Doppler, and then for The process of the above 1D-FFT and 2D-FFT is described in detail:

In a possible implementation, the first radar data may include multiple chirp signals, and each chirp signal may be processed to obtain a corresponding range Fourier spectrum Range-FFT. For example, if r(n) is a digitized reflection signal, where n is the number of samples in a single chirp signal period, then N1-point FFT (or 1D-FFT) calculation can be performed on r(n), and R( k):

R(k)=FFT(r(n), N ₁ ), N ₁ ≥ n;

其中α_i为R(k)正频域复数值的模值，可以定义单个距离点Range-bin对应的单位距离为距离分辨率d_res，则距离值d_i＝α_i×d_res，最大探测距离为

距离傅里叶谱Range-FFT的横轴可以为上述距离值，距离傅里叶谱Range-FFT的纵轴可以为每个距离值对应的信号反射强度，信号反射强度可以定义为复数信号的模值(例如，若复数信号为a+bj，则信号反射强度可以表示为

)，距离傅里叶谱Range-FFT可以包括N₁/2个距离值，以及每个距离值对应的信号反射强度。That is, the 1D-FFT calculation can be performed on the reflected signal to obtain the corresponding range Fourier spectrum Range-FFT, wherein the range Fourier spectrum Range-FFT can be composed of multiple range points Range-bin, and the distance point Range-bin can be Expressed as

Where α _i is the modulus of the complex value of R(k) in the positive frequency domain, and the unit distance corresponding to a single range point Range-bin can be defined as the distance resolution d _res , then the distance value d _i =α _i ×d _res , the maximum detection distance is

The horizontal axis of the Range-FFT of the distance Fourier spectrum can be the above-mentioned distance value, and the vertical axis of the Range-FFT of the distance Fourier spectrum can be the signal reflection intensity corresponding to each distance value, and the signal reflection intensity can be defined as the modulus of the complex signal value (for example, if the complex signal is a+bj, the signal reflection intensity can be expressed as

), the range Fourier spectrum Range-FFT may include N ₁ /2 distance values, and the signal reflection intensity corresponding to each distance value.

)，纵轴表示信号反射强度。Exemplarily, can refer to Fig. 5, Fig. 5 is the schematic diagram of a kind of distance Fourier spectrum Range-FFT, as shown in Fig. 5, the abscissa of distance Fourier spectrum Range-FFT is the distance value d (including

), and the vertical axis represents the signal reflection intensity.

In a possible implementation, after calculating the range Fourier spectrum Range-FFT of a chirp signal, similarly, 1D-FFT processing can be performed on all K chirp signals in a frame to obtain K range Fourier spectrum Leaf spectrum Range-FFT.

In a possible implementation, an FFT calculation (also called 2D-FFT) can be performed on the sequence composed of K values on the same distance Range-bin on the Range-FFT of the distance Fourier spectrum, and it can be obtained Range-Doppler spectrum.

Taking the radar data as a chirp signal as an example, the first radar data may include multiple chirp signals, referring to FIG. 7b, each row in the matrix shown in FIG. 7b is a chirp signal, and multiple chirp signals are superimposed into gesture data ( e.g. first radar data).

In a possible implementation, the radar system can have a long-distance and large-angle detection range, and at the same time, the excellent radar performance makes it very sensitive to small movements, and the interference unrelated to gestures can be eliminated through distance-dimensional filtering and velocity-dimensional filtering. Information is filtered.

Among them, distance-dimension filtering refers to filtering out objects outside the gesture area (including moving objects and static objects, such as the driver's body movements and driver's breathing in the smart cockpit scene). As shown in Figure 8, the gesture action and the range of the human body are separated in distance, and the distance dimension filter can be used to filter out other targets beyond the gesture distance.

Among them, the speed-dimensional filtering refers to using a fourth-order feedback filter to filter out stationary targets and low-speed targets (such as in-vehicle displays, stationary or shaking ornaments, etc.) in the gesture area.

602. Based on the first radar data indicating a first gesture and the duration of the first gesture exceeds a first threshold, enable an adjustment function for a target function.

In the embodiment of the present application, after the first radar data is acquired, gesture-related data analysis may be performed on the first radar data.

In a possible implementation, some or all of the data in the first radar data may be radar data corresponding to the first gesture. After the first radar data is acquired, it is necessary to identify the The radar data, and further processing related to the first gesture (such as determination of the gesture category, determination of the duration of the gesture, etc.) can be performed on this part of the recognized radar data.

In a possible implementation, the start time and end time of the first gesture in the first radar data may be judged by a variance detection method. For example: the variance can be calculated for each chirp of the gesture echo. Since the variance of the echo when there is gesture action is significantly higher than the variance when there is no action, this feature can be used to judge the start and end moments of a gesture. When the gesture is performed, the echo variance increases. When the echo variance of a piece of radar signal data is greater than the set threshold θ, it is judged as the gesture start moment. For a segment of radar data as shown in Figure 9, if the echo variance at a certain point is greater than the threshold θ, then the radar wave data starting from this point is determined to be gesture data, as shown in "gesture starting point a" in Figure 9. In the process of judging the termination of the gesture, because there may be a short-term static situation during the gesture process, the variance of a certain period of time will be less than the threshold (as shown in Figure 9 from point b to point c data segment), if this A piece of data is included in the radar signal data used for gesture recognition, there will be redundant data, which increases the amount of calculation, so the end flag of the gesture is set to the echo variance of consecutive n frames (for example, about 1/30s). is less than the threshold θ (as shown in FIG. 9 , starting from point b, the echo variances of n consecutive frames are all smaller than the threshold θ, and point b is identified as the gesture termination point). After judging that the echo of a gesture is received, the end point after n frames (point c shown in Figure 9) is not used as the gesture end point, but the last echo smaller than the threshold is used as the end point of the gesture data (Figure 9 point b shown in).

In the embodiment of the present application, the timing can be started when the gesture data is detected, and the fine adjustment mode can be started if the duration of the gesture data exceeds the first threshold. Wherein, the first threshold may be greater than 0.7 seconds and less than 1.5 seconds, for example, the first threshold may be 0.7 seconds, 0.8 seconds, 0.9 seconds, 1 second, 1.1 seconds and so on.

Among them, the fine adjustment may include the opening of the function and the adjustment of the degree of the function. The adjustment of the degree may be the increase or decrease of the value, the direction adjustment of the display position, the zoom adjustment of the display area, the adjustment of the position or form of the hardware, For example, fine adjustments may include volume adjustments, display brightness adjustments or zoom adjustments of displayed images, display interface movement adjustments, window height adjustments, front and rear position adjustments of seats in the cabin, and the like. Since it involves level adjustment of functions, the gesture of fine adjustment needs to last for a certain period of time to select the level of adjustment, and the duration is relatively long.

In a possible implementation, the timing can be started when the gesture data is detected, and if the duration of the gesture data is terminated before exceeding the first threshold, the independent gesture adjustment mode can be started.

Wherein, the independent gesture adjustment mode may include turning on or off the function, and since it does not involve the degree adjustment of the function, the independent gesture may be a single gesture with a short duration, such as waving left or right.

With the gradual enrichment of interaction schemes, the number of gestures gradually increases, and the characteristics of each gesture are different. Therefore, independent gestures and fine-tuning gestures have a lot of overlap in action characteristics, and it is difficult to directly distinguish them. The biggest difference lies in the gesture time. Length, Independent gestures are all single gestures with a short duration. As shown in Table 1 below, Table 1 shows an example of statistics on the duration of continuous circle-drawing actions by taking circle-drawing as an example.

Table 1

Table 1 takes continuous circle-drawing actions as an example, considering individual gesture differences, and taking the judgment limit as 1s. Under the test radar parameter configuration in Table 1 above, 1s corresponds to 1440 chirps. Gestures less than 1s are judged as independent gestures, and gestures greater than 1s are regarded as The fine adjustment gesture can ensure that at the beginning of the second round of action, the system can know that the fine adjustment has been carried out.

In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be enough in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of the waking up gesture are coherent.

When the duration of the first gesture indicated based on the first radar data exceeds the first threshold, the radar data related to the first gesture in the first radar data can be identified for the gesture category (that is, the gesture category for the first gesture The recognition of the gesture category of the first gesture is performed because the gesture category of the first gesture needs to be used to determine the type of function for subsequent fine-tuning (that is, to determine the target function). It should be understood that the gesture category here may be understood as a hand shape category, and gestures of different gesture categories have different hand shape characteristics.

In a possible implementation, the processor may indicate the user's gesture based on the first radar data, and the duration of the user's gesture exceeds a first threshold, and determine the user's gesture according to the first radar data. The gesture is a first gesture, and the first gesture is used to indicate to start the adjustment function.

In a possible implementation, part of the radar data may be intercepted from the first radar data, and according to the part of the radar data, it is determined that the user's gesture is the first gesture. Optionally, the part of radar data is the first N radar data in the first radar data. Different from gesture detection, gesture interception is to intercept some gestures of appropriate length during the process of gesture action for gesture recognition. Therefore, the interception length is the key to gesture interception, if the interception is too short or too long, this part of the gesture recognition will fail. Optionally, the gesture interception may be performed through a time interception method and a gesture feature interception method.

The time interception method is consistent with the idea of independent gesture judgment. From the perspective of time, N radar data (for example, N chirp signals are intercepted) are intercepted after the gesture starts, and gesture recognition is performed on the intercepted signals. The time interception method is simple, direct but effective, and its effectiveness comes from the following aspects: First, the gesture recognition algorithm based on the multi-dimensional feature fusion network based on the self-attention mechanism can be used in the subsequent determination of the gesture category. The length of the signal is not sensitive to the change of the signal length, similar to the characteristics of gestures, and the length of time (that is, the speed of gestures) is slightly different, which has little impact on the recognition results, and the length of the same gesture itself of different users is also different; A threshold, the judgment based on the duration can ensure that independent gestures will not be intercepted, and thus will not affect the recognition of independent gestures.

Taking the fine adjustment of continuous circle drawing as an example, according to Table 1, the length of the first clockwise and counterclockwise wake-up gesture generally does not exceed 1000 chirps, so the interception length N can be selected as 1000 chirps. Referring to FIG. 10 , FIG. 10 is a schematic diagram before gesture interception by drawing 2 circles counterclockwise. Referring to FIG. 11 a , FIG. 11 a is a schematic diagram after gesture interception by drawing 2 circles counterclockwise.

In the above fine adjustment example of continuous circle drawing, the system determines that the fine adjustment operation is being performed when the gesture action lasts for 1 second, and intercepts the data of the first 1000 chirps in 1 second (1 second is 1440 chirps under the current radar parameter configuration, which is greater than 1000 chirps) for recognition, and the recognition result is The category of the wake gesture.

The gesture feature interception method refers to analyzing the characteristic changes of a specific gesture and completing the gesture interception. The interception length is not fixed and changes with the gesture situation. For example: Hover gesture interception can be completed from distance or speed changes, and the first circle of continuous circle drawing can be intercepted from distance, angle, and speed changes. Gesture feature interception can solve the difference in gesture length caused by different users and different gestures The influence of sex on interception, the interception of a single gesture is more accurate.

Based on the above description, the time interception method is applicable to situations where the time lengths of different wake-up gestures are similar; and the gesture feature interception method is suitable for different wake-up gestures having the same feature with similar features, and a single feature can be used to realize the interception of different wake-up gestures. In practical applications, which interception method to choose can be comprehensively considered according to the type and characteristics of the wake-up gesture.

After obtaining the above-mentioned intercepted radar data, the motion characteristics of the user's gesture may be obtained according to the first radar data, and the user's gesture may be determined as the first gesture according to the motion characteristics of the user's gesture; Or, according to the first radar data, determine that the user's gesture is the first gesture through a pre-trained gesture classification network.

The following describes how to obtain the motion feature of the user's gesture according to the first radar data, and determine that the user's gesture is the first gesture according to the motion feature of the user's gesture:

In a possible implementation, the motion feature is a single salient feature of the gesture (such as distance, speed, angle feature, etc.), and the recognition of a certain type of gesture can be realized by analyzing the feature. Gesture type recognition based on the motion characteristics of gestures only needs to perform some feature analysis, without feature fusion and neural network, so it can simplify part of the gesture recognition work, reduce the amount of calculation, and improve real-time performance.

In the wake-up gesture, take the hovering action as an example. The hovering action is a static action, and the distance, speed, and angle characteristics remain unchanged. It is very suitable for judging from the signal layer, and considering the conventional hardware performance, the distance resolution is much higher. Due to the angular resolution, the distance feature is used to judge the hovering action. Specifically, it is possible to obtain the distance characteristics of the current received signal, extract the position of the maximum value of signal energy at each time, and take the position of the end of the signal as the reference, and continue to extend toward the starting point of the signal until the distance difference between the gesture position of several times and the reference position exceeds When the threshold is set, it is considered to be non-hovering at this time, and there is a large displacement. Through this method, the hover time can be obtained quantitatively. In addition, it can also be quantified similarly to the distance feature. When the slope value of the first-order distance change fitting line continues to be low within a certain period of time, it can be considered as a hovering action.

Referring to Figure 11b, Figure 11b is an example of the hover gesture signal layer judgment using the above method, and the slope values at each stage are -7.2967, -1.5059e-14, -2.8360, -1.5059e-14, 1.2219, -1.5059e -14, 0.1450, 0.5360, 0.5165, -0.0956, -0.7544, 2.3507, -0.8567, -0.6055, 0.4787. If the slope judgment limit is set to 3, it can be known that the hover gesture lasts for about 2 seconds.

Next, describe how to determine the user's gesture as the first gesture through the pre-trained gesture classification network according to the first radar data:

In a possible implementation, the above-mentioned pre-trained gesture classification network can be a network based on a convolutional layer multi-dimensional feature fusion recognition algorithm combined with a self-attention mechanism, which can be obtained by fusing the distance, angle, and speed features of gesture actions. recognition result. It should be understood that the above-mentioned pre-trained gesture classification network can also be applied to the independent gesture category recognition in the independent gesture mode.

Among them, the realization of gesture recognition mainly includes two ways of network recognition and signal layer recognition. Network layer recognition uses the multi-dimensional feature fusion recognition algorithm combined with the attention mechanism based on this application. The overall structure of the algorithm is shown in Figure 11c. First, the three types of information of a single gesture are stacked to obtain information in a three-channel format, which is similar to the RGB image commonly input by deep learning algorithms in computer vision, as the data input of a single gesture. Finally, feature extraction is performed on the input data. This part is completed through a multi-layer convolutional layer, and the convolution kernel size of the convolutional layer is 3. The feature extraction part reduces the data size and increases the number of channels. The data output passes through the inter-channel feature fusion step based on the self-attention mechanism, and the attention value information is superimposed on each channel. Afterwards, through the fully connected layer and the Softmax layer, the feature data is one-dimensionalized, and the length is shortened to the number of gesture categories, and the predicted probability of each category of gestures is output. Furthermore, the gesture category with the highest prediction probability may be used as the gesture type of the first gesture.

Through the above method, the gesture type of the first gesture can be obtained, and then it can be determined that the gesture type of the first gesture corresponds to the target function based on the preset correspondence, wherein the preset correspondence includes gesture type and Mapping between functions.

That is to say, it may be determined based on the gesture type of the first gesture to determine what the adjustment object (ie, the target function) is for subsequent fine adjustments.

In a possible implementation, the gesture type of the first gesture is finger pinching (such as shown in FIG. 12a ), and the target function is to adjust the progress of the video or audio played by the application; or, the The gesture type is circle drawing, and the target function is volume adjustment; or, the gesture type of the first gesture is palm hovering, and the target function is display brightness adjustment or display image zoom adjustment; or, the second gesture The gesture type of a gesture is a fist, and the target function is movement adjustment of the display interface; or, the gesture type of the first gesture is palm flicking, and the target function is window height adjustment; or, the first gesture The gesture type of the gesture is to make a fist and extend a thumb, and the target function is to adjust the front and rear positions of the seats in the vehicle cabin.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold, and then recognize that the gesture category of the user's gesture is finger pinching , and then you can turn on the function adjustment mode for adjusting the progress of the video or audio played by the application.

Specifically, the processor may recognize that there is a gesture of the user in the monitoring area of the radar system at a certain moment, and determine that the duration of the gesture of the user exceeds the first threshold, and then may recognize that the gesture category of the gesture of the user is circle drawing , and then you can turn on the function adjustment mode for volume adjustment.

Specifically, the processor can recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds the first threshold, and then can recognize that the gesture category of the user's gesture is palm hanging Stop, and then you can start the function adjustment mode for display brightness adjustment or display image zoom adjustment.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold, and then recognize that the gesture category of the user's gesture is a fist, Furthermore, a function adjustment mode for mobile adjustment of the display interface can be enabled.

Specifically, the processor may recognize that there is a user's gesture in the monitoring area of the radar system at a certain moment, and determine that the duration of the user's gesture exceeds the first threshold, and then may recognize that the gesture type of the user's gesture is a light palm Shake, and then you can turn on the function adjustment mode of window height adjustment.

Specifically, the processor may recognize that there is a gesture of the user in the monitoring area of the radar system at a certain moment, and determine that the duration of the gesture of the user exceeds the first threshold, and then may recognize that the gesture category of the gesture of the user is fist and Stretch out your thumb, and then you can turn on the function adjustment mode for adjusting the front and rear positions of the seats in the cabin.

In the embodiment of the present application, when it is determined based on the first radar data that there is a first gesture and the duration of the first gesture exceeds a first threshold, the adjustment function for the target function may be enabled.

Specifically, referring to FIG. 12b, when the adjustment function for the target function is turned on, certain feedback information may be presented, and the feedback information may indicate that the adjustment function for the target function has been turned on. Specifically, when the adjustment function for the target function is turned on, When adjusting a function, a target presentation corresponding to the target function may be performed, and the target presentation is used to indicate that the adjustment function for the target function has been enabled.

In a possible implementation, the target presentation may include: displaying controls for adjusting the target function. In the application scenario of a smart home, the target presentation can be performed on an electronic device with a display; in the scenario of a smart cockpit, the target presentation can be performed on the central control screen in the car cabin.

Taking the target function as the progress adjustment of the video or audio played by the application as an example, the target presentation may be the display of a progress bar.

Taking the target function as volume adjustment as an example, the target presentation may be the display of a volume adjustment control.

Taking the target function as display brightness adjustment as an example, the target presentation may be the display of a display brightness adjustment control.

Taking the target function as an example of displaying zoom adjustment of an image, the target presentation may be the display of a zoom control of an image.

Taking the target function as the mobile adjustment of the display interface as an example, the target presentation may be the display of the mobile controls of the display interface.

In a possible implementation, the target presentation may include: a vibration prompt of hardware related to the target function, for example, in the scenario of a smart car cabin, the target presentation may be a seat vibration prompt.

Taking the target function as an example of adjusting the front and rear positions of the seats in the vehicle cabin, the target presentation may be a vibration reminder of the seat to be adjusted.

In a possible implementation, the target presentation may include: a sound prompt, which may include a voice that the adjustment function for the target function has been turned on, for example, the progress of the video or audio played by the application with the target function is adjusted as For example, the target presentation can be to play the voice "The progress adjustment function of the video or audio played by the application has been turned on"; if the target function is volume adjustment as an example, the target presentation can be to play the voice "The volume adjustment function has been turned on"; If the target function is display brightness adjustment as an example, the target presentation can be to play the voice "The display brightness adjustment function has been turned on"; if the target function is the zoom adjustment of the displayed image, the target presentation can be to play the voice "The zoom function of the image is turned on". If the target function is the height adjustment of the car window as an example, the target presentation can be to play the voice "The window height adjustment function has been turned on"; if the target function is the front and rear position adjustment of the seat in the cabin, the target presentation The voice "The front and rear position adjustment function of the seat in the cabin has been turned on" can be played.

603. Acquire second radar data.

After turning on the adjustment function (fine adjustment) for the target function, the user can adjust the target function through gestures in the monitoring area of the radar system.

Specifically, the processor may obtain the second radar data, wherein the second radar data may be obtained from a reflected signal of the user's gesture (second gesture). For how the processor obtains the second radar data, please refer to the above-mentioned The description about the manner of acquiring the first radar data in the embodiment will not be repeated here.

In a possible implementation, the first radar data is acquired before the second radar data.

In a possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or, the first radar data and the second radar data are The radar data acquired at intervals of the target time period on the domain, and the duration of the target time period is less than the second threshold; wherein, the second threshold may be the time when the processor is performing related processing on the first radar data, and within this time, for The adjustment function for the target function has not been turned on.

604. In response to enabling the adjustment function for the target function, according to the second radar data, determine a second gesture indicated by the second radar data and a motion feature of the second gesture.

In the embodiment of the present application, based on the adjustment function for the target function being turned on, the second gesture indicated by the second radar data and the movement of the second gesture can be determined according to the second radar data feature.

It should be understood that there is also a preset mapping relationship between the first gesture and the second gesture. Specifically, the first gesture can be used to enable the adjustment mode of the target function corresponding to the gesture type of the first gesture. In the case of the adjustment mode of the target function, the user can only adjust the target function based on the gesture type (the gesture type of the second gesture) corresponding to the adjustment mode of the target function.

Among them, the second radar gesture is a gesture when the user performs fine adjustment, and the first gesture, as a wake-up gesture for the fine adjustment function, can be quite different from the second gesture, that is, it can be considered that the first gesture and the second gesture Gestures are independent gestures.

In a possible implementation, the first gesture and the second gesture can also be continuous gesture actions of the user. The so-called continuous gesture actions can be understood as the hand shapes of the first gesture and the second gesture are the same (or The difference is very small), optionally, the first gesture may be a static gesture or a gesture whose movement range is smaller than a threshold, and since the second gesture needs to adjust the target function to a certain extent, the second gesture may be It is a gesture whose movement range is greater than the threshold.

In the embodiment of the present application, the hand shapes of the first gesture and the second gesture are the same, so that the gesture when the user wakes up the fine-tuning function and the gesture used when fine-tuning are the same hand-shaped gestures, which can make The user can accurately adjust the function with a small learning cost.

In a possible implementation, the first gesture is a finger pinching gesture, and the second gesture is a gesture of holding the fingers pinching and dragging; or, the first gesture is a palm hovering gesture, The second gesture is an upward gesture or a downward gesture; or, the first gesture is a palm hovering gesture, and the second gesture is a left and right waving gesture; or, the first gesture is a palm hovering gesture Gesture, the second gesture is a gesture of pushing back and forth; or, the first gesture is a gesture of making a fist, and the second gesture is a gesture of keeping the fist and moving; or, the first gesture is a palm For a jiggling gesture, the second gesture is a lifting gesture or a pressing gesture; or, the first gesture is a gesture of making a fist and extending a thumb, and the second gesture is maintaining the fist and extending a thumb. Thumbs up and push back and forth gesture. The gesture-semantic fit adjustment function of the above-mentioned second gesture conforms to user habits and can help reduce learning costs.

In a possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture have a movement range greater than a threshold gesture. For example, the first gesture and the second gesture may both be circle-drawing gestures.

In the embodiment of the present application, the second radar data may be analyzed to determine the motion feature of the second gesture, and the motion feature may be used to determine adjustment information when fine adjustment is performed. In the fine adjustment scheme, it is not necessary to finely quantify all the features of each adjustment action. According to the characteristics of the gesture, one or part of the motion features of the gesture can be selected to realize the fine adjustment function. Wherein, different gestures may adopt different motion characteristics.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture may include: the second gesture The distance information includes at least one of a change over time of a distance between the second gesture and the radar system, a change rate of the distance, and a change direction of the distance.

Among them, the application of fine adjustment based on distance features can be the situation where the relative distance between the gesture action and the radar is constantly changing, and the hand reflection point area is relatively concentrated, which is conducive to distance detection.

For example, gestures suitable for fine quantification of distance features may include, but are not limited to: lifting/pressing the palm, swaying left and right, moving back and forth, and the like.

Among them, the distance information is contained in the frequency of each echo pulse, and the distance information of the gesture in the current pulse time can be obtained by performing fast Fourier transform on a single pulse in a fast time, and the distance information of each pulse can be integrated to obtain a single gesture The overall distance change information of .

The intermediate frequency signal can be simplified as:

The signal spectrum can be obtained by FFT, and the peak position can be found:

It is proportional to the target distance, and the target distance can be obtained as:

The schematic diagram of distance information extraction is shown in Figure 13. Range resolution refers to the ability to distinguish two adjacent targets, that is, the minimum distance between targets that can ensure that echo signals do not alias, which satisfies:

Among them, c is the speed of light, and B is the frequency modulation bandwidth of the chirp signal. The corresponding relationship between commonly used bandwidth and distance resolution in the 60GHz frequency band can be shown in Table 2 below:

Table 2

Therefore, increasing the sweep bandwidth improves the range resolution. At this time, the minimum scale for fine adjustment of the distance dimension is the distance resolution. In the embodiment of the present application, the distance resolution capability can also be improved by adjusting the Range-FFT when extracting distance features. Specifically, after Range_FFT processing, a spectrum interval corresponds to a range gate unit, which satisfies the following relationship:

若增大N_FFT，即可减小a。Among them, N _s represents the number of sampling points of the Chirp signal of the I/Q channel, and N _FFT represents the number of sampling points of the FFT. In general, N _s is equal to N _FFT , at this time

If increase _NFFT , can reduce a.

For example: If N _s is set to 128, and _NFFT is set to 512, the 128 sampling points of the signal are used as the first 1/4 input of the FFT, and the remaining 3/4 is filled with 0. At this time, the range gate interval is reduced to 1/4 of the previous value. 4. At this time, the minimum scale of the fine adjustment of the super-resolution can be 1/4 of the distance resolution.

In a possible implementation, the distance feature map can be obtained through range-FFT, and the horizontal axis of the feature map corresponds to the number of chirp signals, which can represent time. The vertical axis represents the distance, and each unit corresponds to the length corresponding to the distance resolution R _res . Due to the sensitivity of millimeter-wave radar to submillimeter displacement, there are echo signals with different strengths on different range gates on the same chirp signal. Afterwards, the position of the energy maximum value in each chirp echo signal can be extracted, and the value corresponding to the position on the vertical axis is the position of the current gesture action. There are generally very few positional mutation points in the results, and the reason for the analysis is mainly due to noise. In order to weaken the influence of abrupt points, the sliding window average method is used for smoothing, and the jumps between distance points can be smoothed, which is convenient for subsequent processing. The length of the sliding window can be determined according to the length of the time window (n frames) for extracting fine features. Afterwards, first-order fitting can be performed on each segment of distance feature data, and the slope k of the first-order fitting function can be extracted to obtain the distance adjustment basis information shown in Table 3 below:

table 3

Take the up gesture and the down gesture as examples. For the up gesture, referring to FIG. 14 , the up gesture can last for about 5/6 seconds, and 5 slope values are generated. They are -4.4657, 2.4895, 5.7985, 8.8039, and 12.5691, respectively. The first slope is a negative number. The reason is that the process of reaching into the radar detection is a process of relative distance reduction, and the subsequent actions keep moving away from the radar. The numerical size reflects the movement rate.

For the pressing action, referring to FIG. 15 , contrary to the lifting action, the pressing action is a process of decreasing relative distance. The above actions also lasted about 5/6 seconds, and all slope values were negative, respectively -9.4675, -8.8054, -4.7695, -8.7964, -6.6660. Similarly, the absolute value of the slope reflects the movement speed.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture may include: Velocity information, where the velocity information includes the variation of the moving velocity of the second gesture in the radar field with time.

The fine adjustment based on the velocity feature can be applied to the fine adjustment process with obvious velocity changes, especially for periodic motion. At this time, the speed shows a clear sinusoidal relationship with time. Based on this analysis, gestures that are suitable for fine quantification of speed characteristics, such as clockwise and counterclockwise circles, continuous clicking, and sliders, etc.

In a possible implementation, after FFT is performed on the fast time of the original gesture echo, FFT is performed on the slow time dimension, and its peak value can reflect the Doppler frequency of the target, that is, it contains the speed information of the target. The slow time domain FFT needs to be performed in the same range gate, and because of the distance migration of the overall movement of the target, it is not possible to directly perform FFT on a certain range gate of the overall gesture, but the number of accumulated pulses should be set reasonably so that each FFT operation Gesture truncation basically has no distance migration. In this paper, the time-frequency analysis of the gesture signal is completed through the short-time Fourier transform, so as to extract the gesture Doppler information, and reasonably design the number of accumulated pulses, that is, to reasonably set the window length of the short-time Fourier transform.

For the data processing in this paper, the original signal is firstly subjected to fast-time FFT to obtain the distance information, and then the peak position data of each pulse is extracted and recombined into a column, and STFT is used for time-frequency analysis of this column of data to obtain the Doppler variation law of a single gesture .

If the target is in motion, then:

The signal frequency contains distance and speed information at the same time, that is, the coupling of distance and speed occurs, which cannot be obtained directly through one-dimensional FFT. Suppose the signal sampling period is T _s , the pulse repetition interval is T, the number of single pulse sampling points is N, and L pulses are received, rewritten as:

Where n=0,1,2,...,N-1, represents a single pulse sampling point sequence, and l=0,1,2,...,L-1, represents a pulse sequence.

It can be seen from the observation that the phase part of the signal carries velocity information, and the phase part presents the form of the complex envelope of the signal after one-dimensional FFT. Therefore, FFT is performed on the signal after the one-dimensional FFT in the second dimension (that is, the slow time lT is used as a variable), and the center frequency of the signal that reflects the target speed (that is, the target Doppler frequency) can be obtained:

Available:

The time-frequency analysis of the signal refers to the description of the composition of the frequency components in each time range of the signal. Since the stationary signal is often ideal or man-made, and the signal is generally non-stationary, the Fourier transform is not enough to analyze it, and it needs to be analyzed by means of time-frequency analysis. The short-time Fourier transform is a means of time-frequency analysis.

The short-time Fourier transform (STFT) represents the signal characteristics at a certain moment through a section of the signal within the time window. In the short-time Fourier transform process, the time resolution and frequency resolution of the time-frequency map are determined by the window length. The increase of the window length leads to an increase in the length of the intercepted signal, so that the higher the frequency resolution obtained by STFT, the better the time resolution. Poor and vice versa. In terms of specific operations, the short-time Fourier transform first multiplies a function and the window function, and then performs a one-dimensional Fourier transform. And through the sliding of the window function, a series of Fourier transform results are obtained, and these results are arranged to obtain a two-dimensional representation with the time domain on the horizontal axis and the frequency domain on the vertical axis. Let s(t) be the signal to be analyzed, and STFT(t,ω) be the time-frequency analysis result of the signal, then the short-time Fourier transform formula is as follows:

STFT(t,ω)=∫s(t′)ω(t′-t)e ^-jωt′ dt′;

As mentioned above, the window length needs to be set when using STFT, and the window length will affect the time resolution and frequency resolution. High-frequency signals are suitable for using small window lengths to obtain high resolution in the time domain. Low-frequency signals are suitable for using large window lengths. In order to obtain high resolution in the frequency domain, but the STFT window length is fixed, so the time-frequency analysis ability of the signal still has certain defects. The STFT basis functions at different frequencies can be shown in FIG. 16 . A schematic diagram of Doppler information extraction may be shown in FIG. 17 .

Exemplarily, when performing fine adjustment based on speed information, a speed characteristic map may be obtained, and the energy maximum position in each chirp echo signal may be extracted, and the vertical axis value corresponding to the position is the current gesture speed value. There can be fluctuations in the local velocity value, which is due to the inability of gestures to maintain an absolutely constant velocity. In order to eliminate the local fluctuation of the speed change curve, the sliding window average method is used for smoothing. The obtained speed curve can reflect the relatively uniform motion of the gesture. According to the shape characteristics of the velocity curve obtained above, variables reflecting the fine features of gestures can be extracted. Taking the sinusoidal speed change curve as an example, the number of zero points of the sinusoidal speed curve can be determined by the intermediate value theorem: the function is monotonic in [a,b], and f(a)*f(b)<0, then the function f (x) has one and only one zero at [a,b]. A zero corresponds to 1/2 period. Through the first-order derivation, the number of peaks and troughs satisfying that the derivative value is 0 can be determined. One peak to trough corresponds to 1/2 cycle. Perform sine function fitting to obtain the frequency of the velocity transformation sine function. Wherein, total gesture duration/sine function period T=period number.

Similar to the distance feature, the control of the adjustment range and the adjustment speed can also be realized based on the change of the speed feature in the transform domain alone. The adjustment direction can be realized based on the recognition result of the wake-up gesture, such as drawing a circle clockwise or counterclockwise, or at the same time using the angle feature to realize the judgment, for example, the direction of the angle change of clockwise and counterclockwise is opposite.

Taking the circle gesture as an example, according to the above analysis, the clockwise and counterclockwise circle is a typical action that uses velocity features for fine adjustment, and the periodic change of velocity information after STFT is more obvious than the periodic fluctuation of distance.

The speed characteristic diagram shown in Figure 18 is the speed characteristic diagram of 5 circles drawn counterclockwise. After the above steps, the number of zero points can be 11, and the number of peaks and valleys can be 11. According to the gesture classification result, it is judged to be counterclockwise. According to the number of peaks and valleys and zero points, the user can be fed back every 1/4 cycle. The adjustment speed can be judged by the number of peaks and valleys within a fixed processing time interval.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture may include the angle of the second gesture Information, the angle information includes a change over time of an angle between the second gesture and the radar system, and the angle includes an azimuth angle and/or an elevation angle.

Among them, the fine adjustment based on the angle feature can be applied to the situation where the gesture action does not have a large distance and the speed fluctuates, especially for gestures whose trajectories exist in the XOY plane at different heights of the schematic diagram. For example, it can be applied to actions moving in different directions (currently limited by hardware performance, the angle resolution is low, and the 360° plane can be divided into 4 areas, as shown in Figure 21), and the acquisition of the target angle is based on the radar Multiple receiving antennas are realized by measuring the phase difference of each received echo. The schematic diagram of multi-antenna receiving target echo is shown in Figure 19.

Exemplarily, a multi-signal classification algorithm (multiple signal classification, MUSIC) can be used to measure the angle change of the gesture by using the radar four-receiving antenna array, which is different from the covariance matrix of the array received signals used by the preamble-related algorithm The idea of direct processing, the MUSIC algorithm decomposes the covariance matrix of any array output data into eigenvalues, so as to obtain the signal subspace corresponding to the signal component and the noise subspace orthogonal to the signal component, and then use these two subspaces Orthogonality can be used to estimate signal parameters such as incident direction, polarization information and signal strength. The MUSIC algorithm has universal applicability and has the advantages of high precision and simultaneous measurement of multiple signals. The use of the MUSIC algorithm requires the radar to satisfy that the inter-array spacing is not greater than half the wavelength of the carrier.

Exemplarily, the number of radar line array elements is K, and the spacing is d, then the time delay of receiving signals between two array elements is dsinθ/c, assuming that there are M targets, and their angles are respectively θ _m , m=1,..., M, then the received signals of M targets are:

S(t)=[S ₁ (t), S ₂ (t),..., S _M (t)] ^T ;

The direction vector of the signal is:

in,

Let the array element noise vector be:

N(t)=[n ₁ (t),n ₂ (t),...,n _K (t)] ^T ;

Then the received signal can be obtained as:

X(t)=AS(t)+N(t);

Assuming that the signals of each array element are not correlated, the covariance matrix of the received signal is:

R=E[XX ^H ]=APA ^H +σ ² I;

Among them, P=E[SS ^H ] is the signal correlation matrix, σ ² is the noise power, and I is the K×K order identity matrix. Since R is a full-rank matrix and the eigenvalues are positive, the eigenvectors v _i (i=1,2,...,K) are obtained by decomposing R eigenvalues. Since the noise subspace is orthogonal to the signal subspace, the noise eigenvectors are used as columns , to construct the noise matrix:

E _n =[v _M+1 ,...,v _K ];

Define the spatial spectral function:

When the columns of a(θ) and E _n are orthogonal, the denominator reaches the minimum value, so the spectral peak search can be performed on P _mu (θ), and the angle of arrival can be estimated by finding the peak.

Based on the multi-receiving antenna of the radar, the angle change of the gesture process can be obtained through the MUSIC algorithm. For this paper, the number of pulses used for each angle calculation is 8, that is, the 8 original echo pulses of the single-channel received echo are spliced first.

X _i = [x _i1 , x _i2 ,..., x _iN ];

Among them, N=4096, that is, the total length of 8 pulses, and i is the channel number. After splicing the four-channel data, the input matrix of the MUSIC algorithm is obtained:

The gesture angle distribution corresponding to the segment echo signal is obtained through the MUSIC algorithm. By performing the above operation on every 8 pulses in all echoes, the angle information of the whole stage of a single gesture can be obtained. The schematic diagram of angle information extraction is shown in Figure 20.

Angular resolution characterizes the ability to distinguish two targets at the same distance, expressed by the angle at this time. Generally speaking, the angular resolution of FMCW millimeter wave angle measurement is related to the number of receiving antennas, the more receiving antennas, the higher the accuracy. which satisfies:

The angular resolution can be further improved by using multiple transmitters. A series of transmitting and receiving antennas of the MIMO array can form a virtual array. At this time, the angular resolution satisfies:

According to the above formula, the results of calculating the angular resolution under the two commonly used transceiver mechanisms are shown in Table 3 below:

In summary, it can be seen that the angular resolution can be greatly improved by improving the radar hardware configuration.

When fine-tuning the target function based on the angle feature, the angle feature extraction method can be used to obtain the angle feature map, and the distribution of the scattering points of the angle feature map is divided into regions according to the angle, and the palm movement can be determined according to the change of the angle over time Direction, and then you can determine the change direction, change size, and change speed of the angle feature. The adjustment direction of the angle feature can be reflected through the change of the area, the adjustment range can be reflected through the angle difference, and the angle difference per unit time can be reflected. The speed of adjustment.

Exemplarily, due to the limitation of the current angular resolution, the radar detection area can be roughly divided into four parts (as shown in FIG. 21 ). With the improvement of radar performance, areas can be divided more finely, so as to achieve more accurate direction judgment. In the case of dividing into 4 areas, each area corresponds to 90°. Figure 22 shows the feature map obtained when the palm moves horizontally from Area 4 to Area 2 above the radar.

In addition, referring to FIG. 23 , the fine adjustment of the target function can also be performed based on the above-mentioned multiple motion features. Specifically, when fine adjustments are required for various high-degree-of-freedom gestures, the distance, speed, angle (azimuth, angle, etc.) Pitch angle) is not easy to achieve in a single dimension, and the fusion features are used for fine adjustment. By increasing the number of transmitting and receiving antennas, or using virtual aperture technology, the resolution and accuracy of radar angle measurement can be further improved, and the angle feature, distance feature, and speed feature can be fused to realize real-time spatial positioning and tracking of gestures, so as to achieve similar Air mouse movement function.

Optionally, in order to ensure real-time performance, a short-interval feature fine quantification method can be used to extract fine features every time window (nframes), and the gesture data processed in each segment will not be saved and updated quickly, such small-scale data processing mode, which improves feature feedback speed.

In the embodiment of the present application, on the basis of gesture feature extraction, gesture features are finely quantified, including distance, speed, horizontal angle, pitch angle, and the like. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

605. Determine adjustment information according to the motion feature, where the adjustment information includes at least one of an adjustment range, an adjustment direction, and an adjustment speed, and adjust the target function based on the adjustment information.

Wherein, taking the target function as the progress adjustment of the video or audio played by the application as an example, the adjustment range can indicate the adjustment size of the progress, the adjustment direction can indicate the adjustment direction of the progress (for example, adjust the progress forward or backward), and adjust the speed The speed at which the progress can be indicated.

Wherein, taking the target function as volume adjustment as an example, the adjustment range may indicate the adjustment size of the progress, the adjustment direction may indicate the adjustment direction of the progress (for example, adjust the progress forward or backward), and the adjustment speed may indicate the adjustment speed of the progress .

Wherein, taking the target function as display brightness adjustment as an example, the adjustment range can indicate the adjustment size of the progress, the adjustment direction can indicate the adjustment direction of the progress (for example, adjust the progress forward or backward), and the adjustment speed can indicate the adjustment speed of the progress .

Wherein, taking the zooming adjustment of the displayed image as the target function as an example, the adjustment range may indicate the zoom ratio of the displayed image, the adjustment direction may indicate whether it is zooming in or zooming out, and the adjustment speed may indicate the zooming adjustment speed.

Wherein, taking the target function as the movement adjustment of the display interface as an example, the adjustment range can indicate the displacement of the adjustment, the adjustment direction can indicate the direction of the movement during the adjustment, and the adjustment speed can indicate the speed of the movement during the adjustment.

Wherein, taking the target function as the window height adjustment as an example, the adjustment range can indicate the adjustment size of the window height, the adjustment direction can indicate whether the window height is adjusted upward or downward, and the adjustment speed can indicate the adjustment speed of the window height .

Wherein, taking the target function as the adjustment of the front and rear positions of the seats in the cabin as an example, the adjustment range can indicate the adjustment size of the front and rear positions of the seats in the cabin, and the adjustment direction can indicate whether the seats in the cabin are adjusted forward or toward Rear adjustment, the adjustment speed can indicate the front and rear position adjustment speed of the seat in the cabin.

In a possible implementation, the user may close the fine adjustment function by terminating the gesture (the third gesture). Specifically, the processor may acquire the third radar data, and then may indicate the third gesture based on the third radar data, Turning off the adjustment function for the target function, wherein the third gesture is a hand-off gesture or a hovering gesture. Among them, the function of the stop action is to serve as a sign of fine adjustment to avoid misadjustment caused by redundant actions. Most of the fine adjustment functions can be stopped directly by withdrawing the hand, and some of the functions that are sensitive to distance changes use hovering to stop. Optionally, there may be strong continuity between the third gesture and the second gesture.

For example, refer to FIG. 24a , which is a schematic flowchart of a function adjustment method provided by an embodiment of the present application. As shown in Figure 24a, the embodiment of the present application can organically combine fine adjustment with gesture classification and recognition, which not only ensures that the gesture classification and recognition outputs the recognition result to complete a single command operation, but is also compatible with using combined gestures or continuous repeated gestures to enter the fine adjustment function.

An embodiment of the present application provides a function adjustment method, the method including: acquiring first radar data; based on the first radar data indicating a first gesture, and the duration of the first gesture exceeds a first threshold, turning on The adjustment function for the target function; acquiring second radar data; in response to the activation of the adjustment function for the target function, according to the second radar data, determine the second gesture indicated by the second radar data, and the motion characteristics of the second gesture; according to the motion characteristics, determine adjustment information, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and adjust the target based on the adjustment information function to adjust. In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be sufficient in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of waking up gestures are coherent. Taking the duration of the gesture indicated by the first radar data as the basis for whether to enable the fine adjustment mode is more in line with the user's thinking and usage habits, and reduces the user's learning cost.

Referring to Figure 24b, Figure 24b is a schematic flowchart of a function adjustment method provided in the embodiment of the present application, the method may include:

2401. Acquire target radar data, where the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system;

Wherein, in the design where there is a wake-up gesture, the target radar data can be the second radar data described in the first aspect, and the similarities will not be repeated here.

2402. Determine the motion feature of the target gesture according to the target radar data; the feature type of the motion feature of the target gesture includes at least two of distance information, velocity information, or angle information, and the distance information includes the The distance between the target gesture and the radar system varies with time, the velocity information includes the relative velocity of the target gesture and the radar system varies with time, and the angle information includes the target gesture at the The change over time of angles in a radar field, including azimuth and/or elevation.

In a possible implementation, the change of the distance over time includes:

At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time;

The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time.

In a possible implementation, the target gesture is a periodic gesture, and the change of the relative speed over time is used to determine the number of gesture cycles of the target gesture;

The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

In a possible implementation, the change of the angle over time includes:

At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time;

The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time.

In a possible implementation, based on the fact that the target gesture is a periodic gesture or a gesture whose relative rate to the radar system is constantly changing, the feature type for determining the motion feature of the target gesture includes the speed information;

When the target gesture is a gesture whose distance from the radar system is constantly changing, determining that the feature type of the motion feature of the target gesture includes the distance information;

Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information.

According to the embodiment of the present application, for different gesture categories, corresponding motion feature types can be acquired, and the amount of data processing is reduced on the premise of ensuring accurate recognition.

For more descriptions about step 2402, reference may be made to the description of step 604 in the foregoing embodiment, and details are not repeated here.

2403. Determine adjustment information according to the motion feature, where the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and adjust the target function based on the adjustment information.

When fine-tuning the function, the adjustment action has at least one significant change feature, such as distance or angle or speed. The embodiment of the present application finely quantifies the gesture features on the basis of the motion feature extraction of gestures, including distance , speed, horizontal angle, pitch angle, etc. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

Referring to Fig. 25, Fig. 25 is a schematic structural diagram of a function adjustment device provided by an embodiment of the present application, wherein the device 2500 includes:

An acquisition module 2501, configured to acquire first radar data;

Wherein, for the specific description of the obtaining module 2501, reference may be made to step 601 and step 603, and the similarities are not repeated here.

A function enabling module 2502, configured to enable an adjustment function for a target function based on the first radar data indicating a first gesture and the duration of the first gesture exceeds a first threshold;

Wherein, for the specific description of the function enabling module 2502, reference may be made to step 602, and the similarities will not be repeated here.

The obtaining module 2501 is also used to obtain the second radar data;

A function adjustment module 2503, configured to determine a second gesture indicated by the second radar data and the second gesture according to the second radar data in response to the activation of the adjustment function for the target function the movement characteristics of the ; and,

According to the motion characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

Wherein, for the specific description of the function adjustment module 2503, reference may be made to step 604 and step 605, and the similarities will not be repeated here.

In a possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

In a possible implementation, the first radar data is acquired before the second radar data.

In a possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or,

The first radar data and the second radar data are radar data acquired at intervals of a target time period in the time domain, and the duration of the target time period is less than a threshold.

In a possible implementation, the first gesture and the second gesture are continuous gesture actions of the user.

In a possible implementation, the gesture types of the first gesture and the second gesture are the same, the first gesture is a static gesture or a gesture with a movement range smaller than a threshold, and the second gesture is a movement range Gestures greater than the threshold.

In a possible implementation, the first gesture is a gesture of pinching fingers, and the second gesture is a gesture of keeping the fingers pinched and dragging; or,

The first gesture is a palm-hovering gesture, and the second gesture is an upward gesture or a downward gesture; or,

The first gesture is a palm hovering gesture, and the second gesture is a left and right waving gesture; or,

The first gesture is a palm hovering gesture, and the second gesture is a forward and backward push gesture; or,

The first gesture is a gesture of making a fist, and the second gesture is a gesture of keeping the fist and moving; or,

The first gesture is a flicking gesture of the palm, and the second gesture is an upward gesture or a downward gesture; or,

The first gesture is a gesture of making a fist and extending a thumb, and the second gesture is a gesture of maintaining the fist and extending a thumb and pushing back and forth.

In a possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture have a movement range greater than a threshold gesture.

In a possible implementation, both the first gesture and the second gesture are circle-drawing gestures.

In a possible implementation, the function enabling module 2502 is also configured to:

Before enabling the adjustment function for the target function, based on a preset correspondence, it is determined that the gesture type of the first gesture corresponds to the target function, wherein the preset correspondence includes gesture type and Mapping between functions.

In a possible implementation, the gesture type of the first gesture is finger pinching, and the target function is to adjust the progress of the video or audio played by the application; or,

The gesture type of the first gesture is circle drawing, and the target function is volume adjustment; or,

The gesture type of the first gesture is palm hovering, and the target function is display brightness adjustment or zoom adjustment of a display image; or,

The gesture type of the first gesture is making a fist, and the target function is movement adjustment of the display interface; or,

The gesture type of the first gesture is palm flickering, and the target function is window height adjustment; or,

The gesture type of the first gesture is to make a fist and extend a thumb, and the target function is to adjust the front and rear positions of the seats in the vehicle cabin.

In a possible implementation, the device also includes:

A presenting module, configured to present a target corresponding to the target function before the adjustment of the target function based on the adjustment information, where the target presentation is used to indicate that the adjustment function for the target function has been enabled.

In a possible implementation, the target presentation includes at least one of the following:

a display of controls for making adjustments to said target function;

Vibration alerts for hardware associated with said target function; and,

Sound prompt.

In a possible implementation, the indicating the first gesture based on the first radar data and the duration of the first gesture exceeds a first threshold includes:

Based on the first radar data indicating the user's gesture, and the duration of the user's gesture exceeds a first threshold, according to the first radar data, determine that the user's gesture is a first gesture, and the first gesture It is used to indicate that the adjustment function is turned on.

In a possible implementation, the determining that the user's gesture is the first gesture according to the first radar data includes:

intercepting part of the radar data from the first radar data;

According to the part of the radar data, it is determined that the user's gesture is a first gesture.

In a possible implementation, the part of radar data is the first N radar data in the first radar data.

In a possible implementation, the determining that the user's gesture is the first gesture according to the first radar data includes:

According to the first radar data, acquiring a motion feature of the user's gesture, and determining that the user's gesture is a first gesture according to the motion feature of the user's gesture; or,

According to the first radar data, the user's gesture is determined to be the first gesture through a pre-trained gesture classification network.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

The distance information of the second gesture, the distance information including the change over time of the distance between the second gesture and the radar system, the change rate of the distance, and the change direction of the distance at least one of .

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

Velocity information of the second gesture, where the velocity information includes a change over time of a moving velocity of the second gesture in the radar field.

In a possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

Angle information of the second gesture, where the angle information includes a change over time of an angle between the second gesture and the radar system, and the angle includes an azimuth and/or an elevation angle.

In a possible implementation, the acquiring module 2501 is further configured to:

acquiring third radar data after said adjusting said target function based on said adjustment information;

The device also includes:

A function closing module, configured to indicate a third gesture based on the third radar data, and close the adjustment function for the target function; the third gesture is a hand-off gesture or a hovering gesture.

In the embodiment of the present application, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment in the subsequent fine adjustment, but only as whether to enable the fine adjustment mode. The trigger condition of the adjustment (which can also be referred to as a wake-up gesture in the embodiment of this application), enabling fine adjustment based on the duration of the gesture has the following benefits: Since the types of gestures are limited, in the case of continuous enrichment of future function types , the gesture type may not be enough in the scheme of enabling the fine-tuning function (the independent gesture function occupies a part of the gesture type, and the wake-up gesture occupies another part of the gesture type. The two cannot overlap, otherwise an error will occur), and based on The duration of the gesture is used as the basis for whether to enable the fine adjustment mode, so that the gesture categories used by the independent gesture function and the wake-up gesture can overlap, thereby reducing the gesture categories required for the function adjustment of the gesture implementation. In addition, in the gesture-related function adjustment scenario, especially the fine adjustment scenario, it is necessary to ensure that the overall gesture design is as continuous as possible. When the user wants to perform fine adjustment based on gestures, he will subconsciously know that the adjustment process requires Gestures for a continuous period of time, when waking up the fine-tuning function, if the rules for waking up gestures are also defined based on whether the duration is long enough, then as a user, they will think that the operation process and follow-up of this part of the waking up gesture are coherent. Taking the duration of the gesture indicated by the first radar data as the basis for whether to enable the fine-tuning mode is more in line with the user's thinking and usage habits, and reduces the learning cost of the user.

Referring to Fig. 26, Fig. 26 is a schematic structural diagram of a function adjustment device provided by an embodiment of the present application, wherein the device 2600 includes:

The acquisition module 2601 is configured to acquire target radar data, the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system.

For a specific description of the obtaining module 2601, reference may be made to the description of step 2401 in the above-mentioned embodiment, and details are not repeated here.

The motion feature determining module 2602 is configured to determine the motion feature of the target gesture according to the target radar data; the feature type of the motion feature of the target gesture includes at least two of distance information, velocity information, or angle information, so The distance information includes the change over time of the distance between the target gesture and the radar system, the velocity information includes the change over time of the relative speed between the target gesture and the radar system, and the angle information includes the The angle of the target gesture in the radar field changes over time, the angle includes an azimuth and/or an elevation angle;

For a specific description of the motion feature determination module 2602, reference may be made to the description of step 2402 in the above-mentioned embodiment, and details are not repeated here.

The function adjustment module 2603 is configured to determine adjustment information according to the movement characteristics, the adjustment information includes at least one of adjustment range, adjustment direction and adjustment speed, and adjust the target function based on the adjustment information.

For a specific description of the function adjustment module 2603, reference may be made to the description of step 2403 in the above embodiment, and details are not repeated here.

In a possible implementation, the change of the distance over time includes:

At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time;

The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time.

In a possible implementation, the target gesture is a periodic gesture, and the change of the relative speed over time is used to determine the number of gesture cycles of the target gesture;

The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

In a possible implementation, the change of the angle over time includes:

At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time;

The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time.

In a possible implementation, the motion feature determining module 2602 is further configured to: before determining the motion feature of the target gesture according to the target radar data, based on whether the target gesture is a periodic gesture or for a gesture whose relative velocity to the radar system is constantly changing, the feature type determining the motion signature of the target gesture includes the velocity information;

When the target gesture is a gesture whose distance from the radar system is constantly changing, determining that the feature type of the motion feature of the target gesture includes the distance information;

Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information.

When fine-tuning the function, the adjustment action has at least one significant change feature, such as distance or angle or speed. The embodiment of the present application finely quantifies the gesture features on the basis of the motion feature extraction of gestures, including distance , speed, horizontal angle, pitch angle, etc. Obtain variables that reflect the direction of feature change, the amount of feature change, and the speed of feature change, and then fine-tuning can be achieved in two directions, with different amplitudes, different speeds, high stability, and strong generalization.

Next, a function adjusting device provided by the embodiment of the present application is introduced, please refer to FIG. 27 , which is a schematic structural diagram of the function adjusting device provided by the embodiment of the present application. Specifically, the function adjustment device 2700 includes: a receiver 2701, a transmitter 2702, a processor 2703, and a memory 2704 (the number of processors 2703 in the function adjustment device 2700 may be one or more, and one processor is used in FIG. 27 For example), the processor 2703 may include an application processor 27031 and a communication processor 27032. In some embodiments of the present application, the receiver 2701 , the transmitter 2702 , the processor 2703 and the memory 2704 may be connected through a bus or in other ways.

The memory 2704 may include read-only memory and random-access memory, and provides instructions and data to the processor 2703 . A part of the memory 2704 may also include a non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 2704 stores processors and operating instructions, executable modules or data structures, or their subsets, or their extended sets, wherein the operating instructions may include various operating instructions for implementing various operations.

The processor 2703 controls the operation of the radar system (including the antenna, receiver 2701 and transmitter 2702). In a specific application, various components of the radar system are coupled together through a bus system, where the bus system may include not only a data bus, but also a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the various buses are referred to as bus systems in the figures.

The function adjustment method (shown in FIG. 6 and FIG. 24 b ) disclosed in the above embodiments of the present application may be applied to the processor 2703 or implemented by the processor 2703 . The processor 2703 may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 2703 or instructions in the form of software. The above-mentioned processor 2703 may be a general-purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and may further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate Field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The processor 2703 may implement or execute various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory 2704, and the processor 2703 reads the information in the memory 2704, and completes the steps of the function adjustment method provided by the above-mentioned embodiments in combination with its hardware.

The receiver 2701 can be used to receive input digital or character information, and generate signal input related to the settings and function control of the radar system. The transmitter 2702 can be used to output digital or character information through the first interface; the transmitter 2702 can also be used to send instructions to the disk group through the first interface, so as to modify the data in the disk group.

In a possible implementation, the device further includes a radar system for:

provide a radar field;

sensing reflections from users in the radar field;

analyzing reflections from the user in the radar field; and

Based on the analysis of the reflections, radar data is provided.

Wherein, the function adjusting device 2700 may be a vehicle-mounted device in a smart cockpit scene, a terminal device in a smart home scene, and the like.

Embodiments of the present application also provide a computer program product, which, when run on a computer, enables the computer to execute the function adjustment method described in the foregoing embodiments.

An embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a program for signal processing, and when it is run on a computer, the computer executes the functions described in the above-mentioned embodiments Adjustment method.

The function adjustment device provided in the embodiment of the present application may specifically be a chip. The chip includes: a processing unit and a communication unit. The processing unit may be, for example, a processor, and the communication unit may be, for example, an input/output interface, a pin, or a circuit. The processing unit can execute the computer-executed instructions stored in the storage unit, so that the chip in the execution device executes the image enhancement method described in the above embodiment, or the chip in the training device executes the image enhancement method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit located outside the chip in the wireless access device, such as a read-only memory (read- only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM), etc.

Specifically, please refer to FIG. 28. FIG. 28 is a schematic structural diagram of a chip provided by the embodiment of the present application. The chip can be represented as a neural network processor NPU280, and the NPU 280 is mounted to the main CPU (Host CPU) as a coprocessor. Above, the tasks are assigned by the Host CPU. The core part of the NPU is the operation circuit 2803, and the operation circuit 2803 is controlled by the controller 2804 to extract matrix data in the memory and perform multiplication operations.

In some implementations, the operation circuit 2803 includes multiple processing units (Process Engine, PE). In some implementations, arithmetic circuit 2803 is a two-dimensional systolic array. The arithmetic circuit 2803 may also be a one-dimensional systolic array or other electronic circuits capable of performing mathematical operations such as multiplication and addition. In some implementations, arithmetic circuit 2803 is a general-purpose matrix processor.

For example, suppose there is an input matrix A, a weight matrix B, and an output matrix C. The operation circuit fetches the data corresponding to the matrix B from the weight memory 2802, and caches it in each PE in the operation circuit. The operation circuit takes the data of matrix A from the input memory 2801 and performs matrix operation with matrix B, and the obtained partial or final results of the matrix are stored in the accumulator (accumulator) 2808 .

The unified memory 2806 is used to store input data and output data. The weight data directly accesses the controller (direct memory access controller, DMAC) 2805 through the storage unit, and the DMAC is transferred to the weight storage 2802 . Input data is also transferred to unified memory 2806 by DMAC.

The BIU is a Bus Interface Unit, that is, the bus interface unit 2810 , which is used for the interaction between the AXI bus, the DMAC and the instruction fetch buffer (Instruction Fetch Buffer, IFB) 2809 .

The bus interface unit 2810 (Bus Interface Unit, BIU for short) is used for the instruction fetch memory 2809 to obtain instructions from the external memory, and for the storage unit access controller 2805 to obtain the original data of the input matrix A or the weight matrix B from the external memory.

The DMAC is mainly used to move the input data in the external memory DDR to the unified memory 2806 , to move the weight data to the weight memory 2802 , or to move the input data to the input memory 2801 .

The vector calculation unit 2807 includes a plurality of calculation processing units, and if necessary, further processes the output of the calculation circuit, such as vector multiplication, vector addition, exponent operation, logarithmic operation, size comparison and so on. It is mainly used for non-convolutional/fully connected layer network calculations in neural networks, such as Batch Normalization (batch normalization), pixel-level summation, and upsampling of feature planes.

In some implementations, vector computation unit 2807 can store the vector of the processed output to unified memory 2806 . For example, the vector calculation unit 2807 may apply a linear function and/or a nonlinear function to the output of the operation circuit 2803, such as performing linear interpolation on the feature plane extracted by the convolutional layer, and for example, a vector of accumulated values to generate an activation value. In some implementations, the vector computation unit 2807 generates normalized values, pixel-level summed values, or both. In some implementations, the vector of processed outputs can be used as an activation input to arithmetic circuitry 2803, eg, for use in subsequent layers in a neural network.

An instruction fetch buffer (instruction fetch buffer) 2809 connected to the controller 2804 is used to store instructions used by the controller 2804;

The unified memory 2806, the input memory 2801, the weight memory 2802 and the fetch memory 2809 are all On-Chip memories. External memory is private to the NPU hardware architecture.

Wherein, the processor mentioned in any of the above-mentioned places may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrations used to control the execution of programs related to the steps of the function adjustment method described in the above-mentioned embodiments. circuit.

In addition, it should be noted that the device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physically separated. A unit can be located in one place, or it can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the device embodiments provided in the present application, the connection relationship between the modules indicates that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines.

Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general-purpose hardware, and of course it can also be realized by special hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, Special components, etc. to achieve. In general, all functions completed by computer programs can be easily realized by corresponding hardware, and the specific hardware structure used to realize the same function can also be varied, such as analog circuits, digital circuits or special-purpose circuit etc. However, for this application, software program implementation is a better implementation mode in most cases. Based on this understanding, the essence of the technical solution of this application or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, such as a floppy disk of a computer , U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including several instructions to make a computer device (which can be a personal computer, training device, or network device, etc.) execute the method of each embodiment of the present application .

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be passed from a website site, computer, training device, or data center Wired (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.) transmission to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that can be stored by a computer, or a data storage device such as a training device or a data center integrated with one or more available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (Solid State Disk, SSD)) and the like.

Claims (35)

1. A function adjustment method, characterized in that the method comprises: Obtain the first radar data; based on the first radar data indicating a first gesture, and the duration of the first gesture exceeds a first threshold, enabling an adjustment function for a target function; Obtain the second radar data; In response to the activation of the adjustment function for the target function, according to the second radar data, determine a second gesture indicated by the second radar data and a motion characteristic of the second gesture; According to the motion characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information. 2. The method according to claim 1, wherein the first threshold is greater than 0.7 seconds and less than 1.5 seconds. 3. The method according to claim 1 or 2, wherein the first radar data and the second radar data are radar data acquired continuously in the time domain; or, The first radar data and the second radar data are radar data acquired at intervals of a target time period in the time domain, and the duration of the target time period is less than a second threshold. 4. The method according to any one of claims 1 to 3, wherein the hand shapes of the first gesture and the second gesture are the same, and the first gesture is a static gesture or a movement range smaller than a threshold Gesture, the second gesture is a gesture whose movement amplitude is greater than a threshold. 5. The method according to claim 4, wherein the first gesture is a gesture of pinching fingers, and the second gesture is a gesture of keeping the fingers pinched and dragging; or, The first gesture is a palm-hovering gesture, and the second gesture is an upward gesture or a downward gesture; or, The first gesture is a palm hovering gesture, and the second gesture is a left and right waving gesture; or, The first gesture is a palm hovering gesture, and the second gesture is a forward and backward push gesture; or, The first gesture is a gesture of making a fist, and the second gesture is a gesture of keeping the fist and moving; or, The first gesture is a flicking gesture of the palm, and the second gesture is an upward gesture or a downward gesture; or, The first gesture is a gesture of making a fist and extending a thumb, and the second gesture is a gesture of maintaining the fist and extending a thumb and pushing back and forth. 6. The method according to any one of claims 1 to 5, wherein the first gesture is determined according to part of the radar data intercepted from the first radar data. 7. The method according to claim 6, wherein the partial radar data is the first N radar data in the first radar data. 8. The method according to any one of claims 1 to 7, wherein the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the movement of the second gesture features, including: The distance information of the second gesture, the distance information including the change over time of the distance between the second gesture and the radar system, the change rate of the distance, and the change direction of the distance at least one of; or, The velocity information of the second gesture, the velocity information including the variation of the moving velocity of the second gesture in the radar field over time; or, Angle information of the second gesture, where the angle information includes a change over time of an angle between the second gesture and the radar system, and the angle includes an azimuth and/or an elevation angle. 9. The method according to any one of claims 1 to 8, characterized in that, after the adjustment of the target function based on the adjustment information, the method further comprises: Obtain the third radar data; Based on the third radar data indicating a third gesture, the adjustment function for the target function is turned off; the third gesture is a hand-off gesture or a hovering gesture. 10. The method according to any one of claims 1 to 9, characterized in that, before the enabling of the adjustment function for the target function, the method further comprises: Based on a preset correspondence, determine that the gesture type of the first gesture corresponds to the target function, wherein the preset correspondence includes a mapping between gesture types and functions, wherein the preset correspondence Including at least one of the following: The gesture type of the first gesture is finger pinching, and the target function is to adjust the progress of the video or audio played by the application; or, The gesture type of the first gesture is circle drawing, and the target function is volume adjustment; or, The gesture type of the first gesture is palm hovering, and the target function is display brightness adjustment or zoom adjustment of a display image; or, The gesture type of the first gesture is making a fist, and the target function is movement adjustment of the display interface; or, The gesture type of the first gesture is palm flickering, and the target function is window height adjustment; or, The gesture type of the first gesture is to make a fist and extend a thumb, and the target function is to adjust the front and rear positions of the seats in the vehicle cabin. 11. A function adjustment method, characterized in that the method comprises: Acquiring target radar data, the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system; According to the target radar data, determine the motion feature of the target gesture; the feature type of the motion feature of the target gesture includes at least one of distance information, velocity information or angle information, and the distance information includes the target gesture. The distance between the radar system and the radar system changes over time, the speed information includes the relative speed of the target gesture and the radar system changes over time, and the angle information includes the target gesture in the radar field The change in angle over time, said angle including azimuth and/or elevation angle; According to the movement characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction and adjustment speed, and the target function is adjusted based on the adjustment information. 12. The method according to claim 11, wherein the change of the distance over time comprises: At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time; The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time. 13. The method according to claim 11 or 12, wherein the target gesture is a periodic gesture, and the change of the relative speed over time is used to determine the number of gesture cycles of the target gesture; The adjustment range is related to the number of gesture cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time. 14. The method according to any one of claims 11 to 13, wherein the change of the angle over time comprises: At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time; The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time. 15. The method according to any one of claims 11 to 14, wherein, before determining the motion characteristics of the target gesture according to the target radar data, the method further comprises: When the target gesture is a periodic gesture or a gesture with a constantly changing relative velocity to the radar system, determining that the feature type of the motion feature of the target gesture includes the velocity information; or, When the target gesture is a gesture with a constantly changing distance from the radar system, determining that the feature type of the motion feature of the target gesture includes the distance information; or, Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information. 16. A function adjustment device, characterized in that the device comprises: an acquisition module, configured to acquire the first radar data; A function enabling module, configured to enable an adjustment function for a target function based on the first radar data indicating a first gesture and the duration of the first gesture exceeds a first threshold; The acquisition module is also used to acquire the second radar data; A function adjustment module, configured to determine, according to the second radar data, the second gesture indicated by the second radar data and the motor characteristics; and, According to the motion characteristics, adjustment information is determined, the adjustment information includes at least one of adjustment range, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information. 17. The device according to claim 16, wherein the first gesture and the second gesture have the same hand shape, the first gesture is a static gesture or a gesture with a movement range smaller than a threshold, the The second gesture is a gesture whose movement amplitude is greater than a threshold. 18. The device according to claim 16 or 17, wherein the first gesture is determined according to part of the radar data intercepted from the first radar data. 19. The device according to any one of claims 16 to 18, wherein the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the movement of the second gesture features, including: The distance information of the second gesture, the distance information including the change over time of the distance between the second gesture and the radar system, the change rate of the distance, and the change direction of the distance at least one of; or, The velocity information of the second gesture, the velocity information including the variation of the moving velocity of the second gesture in the radar field over time; or, Angle information of the second gesture, where the angle information includes a change over time of an angle between the second gesture and the radar system, and the angle includes an azimuth and/or an elevation angle. 20. A function adjustment device, characterized in that the device comprises: An acquisition module, configured to acquire target radar data, which is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system; The motion feature determination module is configured to determine the motion feature of the target gesture according to the target radar data; the feature type of the motion feature of the target gesture includes at least two of distance information, velocity information or angle information, the The distance information includes the change over time of the distance between the target gesture and the radar system, the speed information includes the change over time of the relative speed between the target gesture and the radar system, and the angle information includes the The angle of the target gesture in the radar field changes over time, the angle includes an azimuth and/or an elevation angle; A function adjustment module, configured to determine adjustment information according to the movement characteristics, the adjustment information includes at least one of adjustment range, adjustment direction and adjustment speed, and adjust the target function based on the adjustment information. 21. The device according to claim 20, wherein the variation of the distance over time comprises: At least one of the change value of the distance over time, the rate of change of the distance over time, or the direction of change of the distance over time; The adjustment range is related to the change value of the distance with time, the adjustment speed is related to the change rate of the distance with time, and the adjustment direction is related to the change direction of the distance with time. 22. The device according to claim 20 or 21, wherein the variation of the angle over time comprises: At least one of the change value of the angle over time, the rate of change of the angle over time, or the direction of change of the angle over time; The adjustment range is related to the change value of the angle with time, the adjustment speed is related to the change rate of the angle with time, and the adjustment direction is related to the change direction of the angle with time. 23. The device according to any one of claims 20 to 22, wherein the motion feature determining module is further configured to: before determining the motion feature of the target gesture according to the target radar data, When the target gesture is a periodic gesture or a gesture with a constantly changing relative velocity to the radar system, determining that the feature type of the motion feature of the target gesture includes the velocity information; or, When the target gesture is a gesture with a constantly changing distance from the radar system, determining that the feature type of the motion feature of the target gesture includes the distance information; or, Based on the fact that the target gesture is a gesture whose angle is constantly changing in the radar field, the feature type for determining the motion feature of the target gesture includes the angle information. 24. A function adjustment device, characterized in that it comprises: one or more processors and memory; wherein, computer-readable instructions are stored in the memory; The one or more processors read the computer readable instructions to cause the computer device to implement the method according to any one of claims 1 to 15. 25. The apparatus of claim 24, further comprising a radar system for: provide a radar field; sensing reflections from users in the radar field; analyzing reflections from the user in the radar field; and Based on the analysis of the reflections, radar data is provided. 26. A vehicle, comprising: one or more processors and memory; wherein computer readable instructions are stored in the memory; The one or more processors read the computer-readable instructions, so that the computer device implements the method according to any one of claims 1 to 15; The vehicle also includes a radar system in the cabin for: provide a radar field; sensing reflections from users in the radar field; analyzing reflections from the user in the radar field; and Based on the analysis of the reflections, radar data is provided. 27. The vehicle according to claim 26, wherein the cabin further comprises a main driver's seat, a co-driver's seat and a steering wheel fixed in front of the main driver's seat; wherein, The radar system includes: A first radar system comprising a first radar integrated circuit comprising: at least one first transmit antenna; at least one first receive antenna; The first radar integrated circuit is located on the side of the steering wheel close to the passenger seat, wherein the steering wheel is not rotated by the user. 28. The vehicle of claim 27, wherein said at least one first transmit antenna is adapted to provide a radar field to at least one of the following areas: an area of the primary driver's seat that is close to the passenger seat; and, The area between the main driver's seat and the passenger driver's seat. 29. The vehicle according to any one of claims 26 to 28, wherein the cabin further includes a main driver's seat, a co-pilot's seat and a center console; The radar system includes: A second radar system comprising a second radar integrated circuit comprising: at least one second transmit antenna; at least one second receive antenna; The second radar integrated circuit is located on the side of the center console away from the direction of the front of the vehicle. 30. The vehicle of claim 29, wherein the at least one second transmit antenna is configured to provide a radar field to at least one of the following areas: The area near the co-pilot's seat in the main driver's seat; an area of the passenger seat close to the main driver's seat; and The area between the main driver's seat and the passenger driver's seat. 31. The vehicle according to any one of claims 26 to 30, wherein the cabin further comprises a main driver's seat, a co-driver's seat and an armrest box, and the armrest box is fixed between the main driver's seat and the the area between the passenger seats; The radar system includes: A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including: at least one third transmit antenna; at least one third receive antenna; The third radar integrated circuit is located on the side of the armrest box facing the main console. 32. The vehicle of claim 31, wherein the at least one third transmit antenna is adapted to provide a radar field to at least one of the following areas: The area near the co-pilot's seat in the main driver's seat; an area of the passenger seat close to the main driver's seat; and The area between the main driver's seat and the passenger driver's seat. 33. The vehicle according to any one of claims 26 to 32, further comprising: a seat; The one or more processors are further configured to read the computer-readable instructions, so as to control the seat to vibrate when the adjustment function for the target function is turned on. 34. A computer-readable storage medium, characterized by comprising computer-readable instructions, when the computer-readable instructions are run on a computer device, the computer device is made to execute any one of claims 1 to 15. Methods. 35. A computer program product, characterized in that it includes computer-readable instructions, and when the computer-readable instructions are run on a computer device, the computer device is made to perform the method according to any one of claims 1 to 15 .

Images