CN115830563A - Method, device, equipment and storage medium for determining vehicle wading state - Google Patents

Abstract

The invention provides a method, a device, equipment and a storage medium for determining a vehicle wading state, wherein the method comprises the following steps: acquiring a target environment image of a target vehicle; determining a target vehicle wading water line of the target vehicle based on the target environment image; determining the wading depth of the target vehicle based on the position relation between the wading water level line of the target vehicle and the vehicle mark bit of the target vehicle; and determining the wading state of the target vehicle based on the wading depth of the target vehicle. The method gives full play to the capability of the panoramic image system, does not need to add an additional peripheral system, avoids increasing the cost, solves the problem of passive monitoring only depending on an ultrasonic radar, realizes active monitoring on wading of the vehicle, improves the situation perception of wading of a driver, and avoids vehicle loss and safety accidents under the wading condition.

Description

Method, device, equipment and storage medium for determining vehicle wading state

technical field

The invention relates to the field of automobiles, in particular to a method, device, equipment and storage medium for determining a vehicle wading state.

Background technique

With the extreme climate and the deepening of the urban construction process, more and more drivers encounter vehicles wading. Because the drivers often underestimate the water depth, the tragedy of vehicle flooding and even casualties is becoming more and more serious. many. Therefore, realizing real-time monitoring of vehicle wading status and wading depth, providing drivers with information on wading status and wading depth, and assisting drivers in taking escape measures in advance is the key to facing extreme climate and deepening urban construction process. effective solution.

At present, the sensing of vehicle wading status and wading depth is mostly realized by ultrasonic radar. Specifically, the wading depth is calculated based on the time difference between the sending and receiving of radar waves combined with the radar transmission speed. The problem is that a downward ultrasonic radar needs to be installed separately on the body, which increases the hardware cost; the vehicle system cannot actively sense the wading state, and only the driver can actively trigger the wading depth sensing system.

Contents of the invention

In view of the above-mentioned shortcomings of the prior art, the present invention provides a vehicle wading state determination method, device, equipment and storage medium to solve the above technical problems.

A method for determining a vehicle wading state provided by the present invention, the method includes: acquiring a target environment image of a target vehicle, the target environment image including a body image of at least one body of the target vehicle; based on the target environment image , determine the target vehicle wading water level line of the target vehicle; determine the target vehicle wading depth of the target vehicle based on the positional relationship between the target vehicle wading water level line and the vehicle marker position of the target vehicle; The wading depth of the target vehicle is determined to determine the wading state of the target vehicle.

The vehicle wading water level line includes: acquiring a plurality of sample images of the target vehicle, the sample images including at least one body image of the target vehicle body; marking the vehicle wading water level line of the sample images to obtain a training sample data set ; The image recognition model is trained through the sample data set, and the trained image recognition model is used as the vehicle wading water level recognition model; the target environment image of the target vehicle is input to the vehicle wading water level recognition model to obtain the wading water level of the target vehicle.

In an embodiment of the present invention, after acquiring the target vehicle wading water level line of the target vehicle, determining the target vehicle wading depth of the target vehicle includes at least one of the following: acquiring multiple vehicles in the target environment image mark position, and determine the target mark position based on the wading water level line of the target vehicle and the vehicle mark position, and determine the wading position of the target vehicle according to the positional relationship between the wading water level line of the target vehicle and the target mark position Water depth: obtain the complete area of the tire of the target vehicle, and regard the area of the tire above the wading water level of the target vehicle as the exposed area of the tire, and determine the target vehicle based on the relationship between the exposed area of the tire and the complete area of the tire wading depth.

In one embodiment of the present invention, a plurality of vehicle marker positions in the target environment image are obtained, and the target marker positions are determined based on the target vehicle wading water level line and the vehicle marker positions, and according to the target vehicle wading The positional relationship between the water level line and the target marker position, determining the wading depth of the target vehicle includes: acquiring a plurality of vehicle marker positions in the target environment image; A plurality of vehicle flags of the target vehicle wading water level line is determined as a plurality of expected flags; a vehicle flag closest to the target vehicle in the plurality of expected flags is determined as a target flag; based on the target The flag position, the target flag position and the wading water level line of the target vehicle determine the wading depth of the target vehicle.

In an embodiment of the present invention, determining the wading depth of the target vehicle based on the target marker position and the positional relationship between the target marker position and the wading water level line of the target vehicle includes: obtaining the target marker position For the actual height value, the distance between the target mark position and the wading water level line of the target vehicle is determined as the separation distance; based on the separation distance and the preset image distance-preset actual distance library, the distance is determined The actual interval of the distance is obtained to obtain an actual interval value; based on the difference between the actual height value of the target marker and the actual interval value, the wading depth of the target vehicle is determined.

In one embodiment of the present invention, the complete area of the tire of the target vehicle is obtained, and the area of the tire above the wading water level of the target vehicle is regarded as the exposed area of the tire, based on the relationship between the exposed area of the tire and the complete area of the tire , determining the wading depth of the target vehicle includes: obtaining the tire exposed area of the target vehicle tire above the water surface, and determining the complete area of the tire based on the vehicle model of the target vehicle; based on the exposed area of the tire and the The complete tire area determines the tire exposed area ratio of the target vehicle; based on the tire exposed area ratio and the preset tire exposed area ratio-preset target vehicle wading depth library, the target vehicle wading depth of the target vehicle is determined.

In one embodiment of the present invention, determining the wading depth of the target vehicle further includes: obtaining the water depth, clarity of the water and the blurred area of the vehicle tires in the environment where the target vehicle is located, and determining the water depth of the target vehicle. The environmental index of the environment; the first wading depth calculated based on the relative positional relationship between the vehicle wading water level line and the target mark position, and the second wading depth calculated based on the proportional relationship between the exposed area of the tire and the complete area of the tire; based on The wading environment index is assigned a first calculation weight to the first wading depth, and a second calculation weight is assigned to the second wading depth. When the wading environment index is greater than or equal to the standard environment index, the first wading depth A calculation weight greater than the second calculation weight, when the wading environment index is less than the standard environment index, the first calculation weight is less than the second calculation weight; based on the first wading depth, the first calculation weight , the second wading depth, and the second calculation weight determine the wading depth of the target vehicle.

In an embodiment of the present invention, determining the target vehicle wading depth of the target vehicle further includes: acquiring a plurality of wading water levels of the target vehicle, and determining the plurality of wading water levels as expected wading depths. water level line; determine the expected wading depth of the target vehicle based on the expected wading water level line, and obtain the maximum value of the expected wading depth; determine the maximum value of the expected wading depth as the wading depth of the target vehicle depth.

In one embodiment of the present invention, obtaining the wading water level of the target vehicle includes: acquiring multiple frames of target environment images of the target vehicle, and inputting multiple frames of the target environment images into the vehicle wading water level Identifying the model to obtain a plurality of vehicle wading water levels; assigning calculation weights to the plurality of vehicle wading water levels, and obtaining theoretical wading water levels of the plurality of vehicle wading water levels based on the calculation weights, and The theoretical wading water level is regarded as the vehicle wading water level of the target vehicle.

In one embodiment of the present invention, acquiring a plurality of sample images of the target vehicle includes: acquiring an initial environment image of the target vehicle, and identifying the height of splashes and waves in the initial environment image; The maximum value of the splash height and water wave height in the image is used as the water surface fluctuation value of the initial environment image; when the water surface fluctuation value is less than the standard water surface fluctuation value, the initial environment image is retained, and the retained initial environment image is used as The target environment image.

In one embodiment of the present invention, obtaining multiple sample images of the target vehicle further includes: obtaining the ambient light intensity of the environment where the target vehicle is located; when the ambient light intensity is lower than the standard light intensity, starting the vehicle backup light source to supplement light , the vehicle backup light source includes a welcome light facing downwards at the position of the reversing mirror.

In an embodiment of the present invention, before obtaining the target vehicle wading water level line of the target vehicle, it further includes: based on the target environment image, determining the water accumulation position information of the water accumulation area in the target environment image and the The tire position information of the target vehicle tire in the target environment image; determine the water accumulation position of the water accumulation area and the tire position of the target vehicle tire based on the water accumulation position information and the tire position information; if the accumulation of water If the area overlaps with the tire area, it is determined that the target vehicle has waded.

In an embodiment of the present invention, determining the wading state of the target vehicle based on the wading depth of the target vehicle includes: determining a wading depth value of the target vehicle based on the wading depth of the target vehicle, when the target vehicle If the wading depth of the vehicle is greater than or equal to the preset first threshold, it is determined that the wading state of the target vehicle is a first-level wading; when the wading depth of the target vehicle is greater than or equal to the preset second threshold, it is determined that the target vehicle The wading state is a secondary wading state; the preset first threshold is smaller than the preset second threshold.

In an embodiment of the present invention, after determining the wading state of the target vehicle based on the wading depth of the target vehicle, it further includes: when the wading state of the target vehicle is a first-level wading, issuing a first-level alarm, To remind the driver that the current vehicle is wading; when the target vehicle is in the second-level wading state, a second-level alarm is issued to remind the driver that the current vehicle parts have been wading.

The present invention provides a device for determining a vehicle wading state, the device comprising: an image acquisition module, configured to acquire a target environment image of a target vehicle, the target environment image including a body image of at least one body of the target vehicle; The water determination module is used to obtain the target vehicle wading water level of the target vehicle based on the target environment image; the wading depth determination module is used to obtain the target vehicle wading water level based on the target vehicle wading water level and the target vehicle The positional relationship of the flags determines the target vehicle wading depth of the target vehicle; the wading state determination module is used to determine the wading state of the target vehicle based on the target vehicle wading depth.

In an embodiment of the present invention, the vehicle wading state determination device further includes an alarm module, the alarm module includes: a display module, the display module includes at least one display screen, and is used to issue a message based on the target vehicle wading state. Text alarm information; indicator light module, the indicator light module includes at least two color indicator lights, which are used to start the indicator lights of different colors in the wading state of the target vehicle, and send out light alarm information; speaker module, the speaker module includes at least one The buzzer is used to send out voice alarm information based on the wading state of the target vehicle.

An electronic device provided by the present invention, the electronic device includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are processed by the one or more When the controller is executed, the electronic device is made to implement the method for determining the vehicle wading state as described above.

The present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is made to execute the method for determining the vehicle wading state as described above.

Beneficial effects: the present invention utilizes the panoramic image system installed around the vehicle for wading sensing detection, collects the environmental image around the vehicle, and processes the graphics to obtain the relationship between the distance in the image and the actual distance. Position or the relationship between the vehicle tire area and the vehicle wading water level line, determine the vehicle wading status and depth, and trigger an alarm; this method gives full play to the capabilities of the panoramic imaging system without adding additional peripheral systems, avoiding the In addition to increasing the cost, it also solves the problem of passive monitoring relying solely on ultrasonic radar, realizes active monitoring of vehicle wading, improves the driver's situational awareness of wading, and avoids vehicle losses and safety accidents under wading conditions.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application. Apparently, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative efforts. In the attached picture:

FIG. 1 is a schematic diagram of an implementation environment of a method for determining a vehicle wading state shown in an exemplary embodiment of the present application;

Fig. 2 is a flowchart of a method for determining a vehicle wading state shown in an exemplary embodiment of the present application;

Fig. 3 is a schematic diagram of vehicle wading shown in an exemplary embodiment of the present application;

Fig. 4 is a schematic diagram of vehicle wading shown in another exemplary embodiment of the present application;

Fig. 5 is a flow chart of vehicle wading state determination shown in an exemplary embodiment of the present application;

Fig. 6 is a block diagram of a vehicle wading state determination device shown in an exemplary embodiment of the present application;

Fig. 7 is a block diagram of a vehicle wading alarm device shown in an exemplary embodiment of the present application;

Fig. 8 is a schematic diagram of the architecture of a vehicle wading sensing system shown in an exemplary embodiment of the present application;

Fig. 9 is a schematic diagram of the connection relationship of the vehicle body height engineering calibration system shown in an exemplary embodiment of the present application;

Fig. 10 is a full flowchart of vehicle wading alarm response shown in an exemplary embodiment of the present application;

FIG. 11 shows a schematic structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application.

Detailed ways

Embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, but not for limiting the protection scope of the present invention.

It should be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic ideas of the present invention, and only the components related to the present invention are shown in the diagrams rather than the number, shape and shape of the components in actual implementation. Dimensional drawing, the type, quantity and proportion of each component can be changed arbitrarily during actual implementation, and the component layout type may also be more complicated.

In the following description, numerous details are discussed in order to provide a more thorough explanation of embodiments of the invention, however, it will be apparent to those skilled in the art that embodiments of the invention can be practiced without these specific details, In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail in order to avoid obscuring the embodiments of the invention.

First of all, it needs to be explained that in the automotive field, the current vehicle wading detection is done by ultrasonic radar. However, there are two major defects in this technology. On the one hand, due to technical limitations, ultrasonic radar needs about 0.8 seconds In order to get a measured value of water depth, considering the driving speed of the vehicle during the wading process, when the vehicle receives the wading measurement value, its environment has changed, resulting in a large gap between the wading measurement value and the vehicle's environment. Delay. For example, when the outdoor driving speed of the vehicle is 25km/h, after 0.8 seconds, its driving distance is 5.56 meters. If the road section is not a straight line with equal water levels, the actual wading depth of the vehicle may have changed greatly , the practical value of the measured value is very limited. On the other hand, during the normal driving process of the vehicle, there may be surging water waves or splashing water splashes on the road surface. If the time when the ultrasonic wave is sent out happens to meet the water waves or splashes, it may cause a large error. According to the actual situation It is measured that the error can reach 40cm, and 40cm is close to 20% compared with the body height of ordinary cars (140cm-160cm), which is enough to seriously affect the vehicle's judgment of the wading depth.

Therefore, the present invention collects vehicle wading pictures by using the vehicle-mounted camera equipment, and then obtains the wading depth of the vehicle through image processing. The advantage of this method is that, on the one hand, the efficiency of image acquisition is very high. Assuming that the frame rate of the video stream of the camera is 30 frames, a signal can be collected every 33 milliseconds. A water depth measurement value can be collected within milliseconds. Assuming that the target vehicle is traveling at a speed of 25km/h, within 50 milliseconds, the vehicle’s driving distance is only 0.35 meters. There is usually no large water depth change within the range, so the water depth measurement value is valid for the current wading state of the vehicle. On the other hand, the method determines the wading depth of the vehicle through image processing. During the image processing process, the collected images can be screened to remove the influence of water splashes and water waves. Therefore, the method for determining the vehicle wading state proposed by the present invention effectively avoids the defects of the traditional method.

Fig. 1 is a schematic diagram of an implementation environment of a method for determining a vehicle wading state according to an exemplary embodiment of the present application. As shown in FIG. 1 , the system architecture may include a camera device 101 , a target vehicle 102 and a computer device 103 . Wherein, the computer device 103 may be at least one of a desktop graphics processing unit (Graphic Processing Unit, GPU) computer, a GPU computing cluster, a neural network computer, and the like. Relevant technicians can use the computer device 103 to judge the driving risk between the current vehicle and the target vehicle, and control the driving behavior of the current vehicle.

Schematically, the imaging device 101 first acquires an image of the surrounding environment of the target vehicle, and sends relevant information to the computer device 103 for processing, and the computer device 103 confirms the wading depth of the target vehicle based on the wading risk in the image information provided by the imaging device 101 1. Judging its alarm level, and sending the result to the target vehicle 102 to execute relevant alarm actions.

Fig. 2 is a flowchart of a method for determining a vehicle wading state according to an exemplary embodiment of the present application.

Please refer to FIG. 2 . FIG. 2 is a flowchart of a method for determining a vehicle wading state according to an exemplary embodiment of the present application. The method can be applied to the implementation environment shown in FIG. 1 , and is specifically executed by the smart terminal 103 in the implementation environment. It should be understood that the method may also be applicable to other exemplary implementation environments, and be specifically executed by devices in other implementation environments, and this embodiment does not limit the applicable implementation environments of the method. Referring to Fig. 2, the image processing method includes at least step S210 to step S240, which are described in detail as follows:

Step S210, acquiring a target environment image of the target vehicle, where the target environment image includes a body image of at least one body of the target vehicle.

It should be understood that during the driving process of the vehicle, the surrounding environment information of the vehicle can be collected according to the vehicle's own on-board camera system. The environmental information includes the contact line between the body and ground water. The collected initial environmental information can be preliminarily processed, and the images that meet the calculation requirements can be screened out and sent to the vehicle wading detection module to obtain the wading situation of the vehicle.

In one embodiment of the present application, the existing panoramic image cameras for the driver to observe the surrounding conditions of the vehicle are used, including the forward-looking camera and the cameras arranged at the positions of the rear view mirrors on both sides of the vehicle to monitor the front and left and right sides of the vehicle body respectively. For the wading state on both sides, the environmental image information of the vehicle during driving is obtained; then, through the artificial intelligence algorithm system deployed on the camera side, that is, the edge computing module, the video data is directly processed on the camera side; at least one side including the target vehicle is obtained. The body image of the vehicle body is sent to the vehicle controller through CAN (Controller Area Network, CAN for short), and the artificial intelligence algorithm deployed on the vehicle controller performs further data processing on the obtained image information.

It should be understood that since the present invention relies on the camera equipment to collect the environmental image of the target vehicle, the intensity of ambient light will have a certain degree of impact on the clarity of the image. Relevant measures are needed to prevent the camera equipment from being unable to collect clear images of the target environment.

Acquiring a plurality of sample images of the target vehicle also includes: obtaining the ambient light intensity of the environment where the target vehicle is located; when the ambient light intensity is lower than the standard light intensity, then starting the vehicle backup light source to supplement the light, the vehicle backup light source includes a rear view mirror A welcome light positioned downwards.

In one embodiment of the present invention, the target vehicle is driving on a relatively remote road in the middle of the night, the weather is dark and the lighting capacity of the street lights is limited, the light intensity of the environment is determined by the device as A, and the preset standard light intensity is B, compared If A is less than B, and the light intensity of the environment where the target vehicle is located is lower than the standard light intensity, then turn on the welcome light in the direction of the rear view mirror to fill in the light of the environment, so that the vehicle camera can capture the available target environment image.

Step S220, based on the target environment image, determine the target vehicle wading water level line of the target vehicle.

Obtaining the target vehicle wading water level of the target vehicle based on the target environment image includes: acquiring multiple sample images of the target vehicle, the sample images including at least one body image of the target vehicle; marking the vehicle wading water level of the sample images , to obtain the training sample data set; the image recognition model is trained through the sample data set, and the trained image recognition model is used as the vehicle wading water level recognition model; the target environment image of the target vehicle is input into the vehicle wading water level recognition model model to obtain the wading water level of the target vehicle.

Obtaining the wading water level line of the target vehicle includes: obtaining multiple frames of the target environment image of the target vehicle, inputting the multiple frames of the target environment image into the vehicle wading water level recognition model to obtain multiple vehicle wading water lines; The water level is assigned a calculation weight, based on the calculation weight, the theoretical wading water level of multiple vehicle wading water levels is obtained, and the theoretical wading water level is regarded as the vehicle wading water level of the target vehicle.

It should be understood that it is first necessary to collect a large number of target environment images to train the image processing model. The target environment images include a large number of non-standard environment images with water waves or splashes. During the model training process, this part of the non-standard environment images Carry out corresponding processing, including but not limited to, eliminating images that obviously have no reference value (such as images with huge water splashes) to increase the accuracy of water level line judgment; non-linear images are collected in target images with water splashes The actual wading line, and take multiple wading monitoring points on the actual wading line to determine the wading point linear regression line of the multiple wading monitoring points, and take the obtained wading point linear regression line as the target vehicle wading water line.

Obtaining multiple sample images of the target vehicle includes: collecting the initial environment image of the target vehicle, and identifying the height of the splash and the height of the water wave in the initial environment image; taking the maximum value of the height of the splash and the height of the water wave in the initial environment image as the initial environment image The water surface fluctuation value; when the water surface fluctuation value is less than the standard water surface fluctuation value, the initial environment image is retained, and the retained initial environment image is used as the target environment image.

In one embodiment of the present invention, a large number of vehicle environment images are collected by the vehicle-mounted camera device, and there are relatively large water splashes and water waves in some of the images. Taking the standard water surface fluctuation value of 5 cm as an example, based on the collected vehicle environment images Determine the position of the highest point of the water splash or water wave in the image, and use the height difference between the position and the water surface as the water surface fluctuation value of the environmental image, compare any environmental image and the water surface fluctuation value with the standard water surface fluctuation value, when the water surface of the environmental image When the fluctuation value is greater than the standard water surface fluctuation value, the environmental image is eliminated, and the environmental image with the water surface fluctuation value less than 5cm is retained for model training.

Obtaining the wading water level line of the target vehicle includes: obtaining multiple frames of the target environment image of the target vehicle, inputting the multiple frames of the target environment image into the vehicle wading water level recognition model to obtain multiple vehicle wading water lines; The water level is given calculation weights, based on the calculation weights, the theoretical wading water levels of multiple vehicle wading water levels are obtained, and the theoretical wading water levels are regarded as the vehicle wading water levels of the target vehicle.

In one embodiment of the present invention, taking the video stream with a frame rate of 30 frames as an example, that is, one signal can be collected every 30 milliseconds, then 10 vehicle environment images collected within 0.3 seconds are input to the vehicle wading water level Identify the model to obtain 10 different vehicle wading water levels, and assign different weights to the 10 vehicle wading water levels based on the clarity of each environmental image, and then based on the weight of each vehicle wading water level, fuse to obtain a Theoretical wading water level, and the theoretical wading water level is regarded as the wading water level of the target vehicle.

In one embodiment of the present invention, a large number of environmental images during driving of the vehicle are firstly collected, and through training, a convolutional neural network model is established to determine the wading water level of the target vehicle.

In one embodiment of the present invention, a real-time environment image of the target vehicle is input into the vehicle wading state recognition model after training, and it is confirmed that the target vehicle is not wading, then the vehicle is controlled to run normally, and its wading state is continuously detected. water condition.

In one embodiment of the present invention, a real-time environment image of the target vehicle is input into the vehicle wading state recognition model after training, and if it is confirmed that the target vehicle is wading, the information of the target vehicle wading is sent to the whole vehicle The controller, and the artificial intelligence algorithm deployed on the vehicle controller performs further data processing on the obtained image information.

In one embodiment of the present invention, a large number of vehicle body environment images in the process of vehicle driving are first collected, and the vehicle wading water level line in the relevant vehicle body environment images is considered to be marked to form a data set, and then based on the data set Recognition training is carried out on the image to obtain the vehicle wading water level recognition model.

In one embodiment of the present invention, the target environment image of the target vehicle is collected, and the target environment image is input into the vehicle wading water level recognition model, then the wading water level line of the target vehicle corresponding to the target environment image is obtained .

Step S230: Determine the target vehicle wading depth of the target vehicle based on the positional relationship between the wading water level line of the target vehicle and the vehicle marker position of the target vehicle.

Before obtaining the target vehicle wading water level line of the target vehicle, it also includes: based on the target environment image, determining the water accumulation position information of the water accumulation area in the target environment image and the tire position information of the target vehicle tire in the target environment image; and the tire position information to determine the water accumulation position of the water accumulation area and the tire position of the tire of the target vehicle; if the accumulation water area and the tire area overlap, it is determined that the target vehicle has waded.

In one embodiment of the present invention, a large number of environmental images in the driving process of the vehicle are first collected, and the tire location area and the water accumulation area of the target vehicle are determined based on the environmental image information, and the area where the tire is located is M1, and the water accumulation area is M1. If the area is N1, and the area M1 overlaps with the area N1, then it is determined that the target vehicle has waded.

In one embodiment of the present invention, a large number of environmental images in the driving process of the vehicle are first collected, and the tire location area and the water accumulation area of the target vehicle are determined based on the environmental image information, so that the area where the tire is located is M2, and the water accumulation area is M2. If the area is N2, where the area M2 and the area N2 are independent of each other and there is no overlapping area, then it is determined that the target vehicle is not wading.

It should be understood that during the driving process of the vehicle, due to changes in environmental factors, the reliability or clarity of the environmental image will change accordingly, so different determination methods can be used based on different environments, including The relative positional relationship of the tires or the proportion relationship of the exposed area of the tires jointly determine the wading depth of the vehicle.

Determining the wading depth of the target vehicle also includes: acquiring the depth of water in the environment where the target vehicle is located, the clarity of the water, and the blurred area of the vehicle tires, and determining the environmental index of the environment in which the target vehicle is located; The first wading depth obtained by calculating the relative positional relationship between the water level line and the target mark position, and the second wading depth calculated based on the proportional relationship between the exposed area of the tire and the complete area of the tire; based on the wading environment index, the given The first calculation weight of the first wading depth is assigned the second calculation weight of the second wading depth. When the wading environment index is greater than or equal to the standard environment index, the first calculation weight is greater than the second calculation weight Weight, when the wading environment index is less than the standard environment index, the first calculation weight is less than the second calculation weight; based on the first wading depth, the first calculation weight, the second wading depth, the second Calculate the weight to determine the wading depth of the target vehicle. In one embodiment of the present invention, when the target vehicle is driving on a muddy road in rainy weather, the vehicle is waded based on the actual environment where the vehicle is located.

Firstly, the water accumulation in the environment where the target vehicle is located and the blurred area of the vehicle tires are collected. The blurred area is generally caused by the mud on the wheel blocking the wheel area. If the depth of the accumulated water does not exceed 3/4 of the tire, 1 point will be awarded, 1 point will be awarded if the accumulated water is clearly visible, 1 point will be awarded if the tire area of the vehicle is blurred, and 0 points will be awarded otherwise, to obtain the wading environment index of the target vehicle. Taking the standard environmental index of 3 as an example, when the environmental index of the target vehicle is less than 3, the first calculation weight is greater than the second calculation weight, assuming that the larger weight is 70%, otherwise the smaller weight is 30%.

In one embodiment of the present invention, after detection, it is determined that the environment index of the target vehicle is 3, and the standard environment index is 3, then the first calculation weight is set to 70%, and the second calculation weight is set to 30%. Through the calculation, the first wading depth is 45cm, and the second wading depth is 43cm, then according to the first calculation weight and the second calculation weight, the theoretical wading depth is 44.4cm, and the wading depth of the target vehicle is considered to be 44.4 cm.

In another embodiment of the present invention, after detection, it is determined that the environmental index of the target vehicle is 2 and the standard environmental index is 3, then the first calculation weight is set to 30%, and the second calculation weight is set to 70%. Through calculation, the first wading depth is 45cm, and the second wading depth is 43cm. Then, according to the first calculation weight and the second calculation weight, the theoretical wading depth is 43.6cm, and the wading depth of the target vehicle is considered to be 43.6 cm.

Fig. 3 is a schematic diagram of vehicle wading shown in an exemplary embodiment of the present application. As shown in Figure 3, the vehicle-based camera system collects the image information of one side of the vehicle body. The image information indicates that there is a vehicle wading water level line between the vehicle and the ground water, and point A is the distance between the wading water level line and the vertical coordinate. The point of intersection between points B is the point of intersection between the horizontal line and the vertical coordinate of one of the tire marks, and h is the distance between point A and point B.

After obtaining the target vehicle wading water level line of the target vehicle, determining the target vehicle wading depth of the target vehicle includes at least one of the following: acquiring multiple vehicle marker positions in the target environment image, and based on the target vehicle wading water level line and the vehicle marker position Determine the target mark position, determine the wading depth of the target vehicle according to the positional relationship between the wading water level line of the target vehicle and the target mark position; obtain the complete area of the tire of the target vehicle, and place the part of the tire higher than the wading water level line of the target vehicle The area is regarded as the exposed area of the tire, and the wading depth of the target vehicle is determined based on the relationship between the exposed area of the tire and the complete area of the tire.

Obtain multiple vehicle markers in the target environment image, and determine the target marker based on the target vehicle's wading water level and the vehicle marker, and determine the wading depth of the target vehicle according to the positional relationship between the target vehicle's wading water level and the target marker Including: obtaining multiple vehicle markers in the target environment image; based on the target vehicle wading water level, determining multiple vehicle markers higher than the target vehicle wading water level as multiple expected markers; The vehicle marker closest to the target vehicle is determined as the target marker; based on the target marker and the positional relationship between the target marker and the wading water level line of the target vehicle, the wading depth of the target vehicle is determined.

Based on the target marker position and the positional relationship between the target marker position and the wading water level line of the target vehicle, determining the wading depth of the target vehicle includes: obtaining the actual height value of the target marker position, and dividing the distance between the target marker position and the wading water level line of the target vehicle. The distance is determined as the interval distance; based on the interval distance and the preset image distance-preset actual distance library, the actual interval of the interval distance is determined to obtain the actual interval value; the difference between the actual height value and the actual interval value based on the target mark , to determine the wading depth of the target vehicle.

In one embodiment of the present invention, according to the wading situation of the vehicle shown in Figure 3, the position of the wading water level line of the target vehicle is obtained as point A, and a marker position higher than point A and closest to point A is obtained as point B , then determine point B as the target mark position, and obtain the actual height of point B as X1, and based on the image, obtain the interval from point A of the wading water level line to the target mark position as h. In addition, the relationship between the image distance and the actual distance is determined through the internal and external parameters of the camera, and the preset image distance-preset actual distance library is obtained, so that the actual separation distance X2 is obtained based on the separation distance h on the image, and the actual height X1 of point B is obtained. and the difference between the distance X2 between point B and point A to obtain the actual height of point A, that is, the wading depth of the target vehicle.

In one embodiment of the present invention, according to its vehicle tire category "260/70R16", the tire diameter is 770 mm, and the actual height of the target mark is 385 mm, which is obtained through the preset image distance-preset actual distance library The actual distance of the separation distance h is 30 mm, then the wading depth of the target vehicle is obtained as 355 mm.

Obtain the complete area of the tire of the target vehicle, and regard the area of the tire above the wading water level of the target vehicle as the exposed area of the tire. Based on the relationship between the exposed area of the tire and the complete area of the tire, determining the wading depth of the target vehicle includes: obtaining the target vehicle The tire exposed area of the tire exposed to the water surface, and determine the complete tire area based on the vehicle model of the target vehicle; determine the tire exposed area ratio of the target vehicle based on the tire exposed area and the complete tire area; based on the tire exposed area ratio and the preset tire exposed area ratio- The target vehicle wading depth library is preset to determine the target vehicle wading depth of the target vehicle.

In one embodiment of the present invention, as shown in Figure 3, point A is the target vehicle wading water level line of the target vehicle, and the area of the vehicle tire above the water surface is obtained based on the image, that is, the area above point A is s, and The relationship between the image area and the actual area is determined by the internal and external parameters of the camera, so that the actual area of the vehicle tire exposed to the water surface is S1, and based on the model of the vehicle tire, the complete area of the vehicle tire is obtained as S0, so that the tire is obtained. Tire exposed area ratio K. According to the vehicle tire data parameters, the relationship between its area and height is obtained, thereby determining the preset tire exposed area ratio-the preset target vehicle wading depth library, and based on the tire exposed ratio obtained above, the wading area of the target vehicle is obtained.

In one embodiment of the present invention, according to the wheel model, the complete area S0 of the vehicle tire is obtained as 0.47 square meters, and based on the exposed area of the tire in the image, the actual exposed area S1 of the tire is obtained as 0.235 square meters, that is, the tire exposed area of the tire is obtained. The area ratio K is 1/2, and the wading depth of the target vehicle is obtained according to the preset wheel wading area ratio-the preset wading depth library to be 385 mm.

Step S240, based on the wading depth of the target vehicle, determine the wading state of the target vehicle.

Determining the wading state of the target vehicle based on the wading depth of the target vehicle includes: determining the wading depth value of the target vehicle based on the wading depth of the target vehicle, and determining the target vehicle when the wading depth of the target vehicle is greater than or equal to a preset first threshold The wading state of the target vehicle is a first-level wading; when the wading depth of the target vehicle is greater than or equal to the preset second threshold, it is determined that the wading state of the target vehicle is a second-level wading; the preset first threshold is less than the preset second threshold .

Fig. 4 is a schematic diagram of vehicle wading shown in an exemplary embodiment of the present application. When the target vehicle is driving on a road with a certain slope, the wading depth of the front and rear tires is different. According to the national standard "Technical Standards for Highway Engineering" (JTGB01-2003), the maximum slope ratio of the road can be obtained as 9%. Therefore, It can be calculated that there is only a centimeter-level difference in the wading depth of the front and rear wheels under the condition of the extreme slope of the road. Therefore, in the actual application environment, methods including but not limited to lowering the warning standard or taking a higher wading depth as an early warning are adopted. Realize wheel wading warning.

Determining the target vehicle wading depth of the target vehicle further includes: acquiring a plurality of wading water levels of the target vehicle, and determining the plurality of wading water levels as expected wading water levels; The water level line determines the expected wading depth of the target vehicle, and obtains the maximum value of the expected wading depth; the maximum value of the expected wading depth is determined as the wading depth of the target vehicle.

In one embodiment of the present invention, since the target vehicle is driving on a slope section, there is a difference in the wading depth of the front and rear tires, the greater value of the wading depth is taken as the vehicle wading depth to complete the vehicle wading warning , taking the wading depth of the front tires of the vehicle as 40cm, the wading depth of the rear tires as 48cm, and the h _warning as 45cm as an example, the wading depth of the rear tires is taken as the wading depth of the vehicle, because the wading depth of the vehicle is 48cm If it is greater than h _warning 45cm, then control the vehicle to issue a corresponding alarm.

It should be understood that the same effect as the above solution can also be achieved by lowering the standard threshold of water wading warning.

In one embodiment of the present invention, since the target vehicle is driving on a slope section, there are differences in the wading depths of the front and rear tires. Taking the preset standard early warning depth h _{early warning} = 45cm as an example, since the vehicle is driving on a sloping road section, the early warning depth is lowered. Taking the reduction of 5 cm as an example, when the wading depth of the vehicle is 40 cm, an early warning is issued to the target vehicle.

Fig. 5 is a flowchart showing a vehicle wading state determination according to an exemplary embodiment of the present application.

As shown in Figure 5, first go back to the target environment image of the target vehicle, and then determine whether the target vehicle is wading based on the environment image, if the target vehicle is not wading, continue to detect its wading state, if the target vehicle has , then determine the wading water level of the target vehicle, determine the wading depth of the target vehicle based on the wading water level of the target vehicle, and determine the wading state of the target vehicle based on the obtained wading depth and a preset threshold.

In one embodiment of the present invention, if it is determined that the target vehicle is not wading based on the collected target environment image, no response is made, and the vehicle operates normally and continuously detects the wading situation of the target vehicle.

In one embodiment of the present invention, the preset first threshold is h _{early warning} , the second threshold is h _limit , and h _{early warning} < h _limit , and based on the above vehicle wading water level line identification model, the wading depth of the target vehicle is h _wading , compare the relationship between h _wading and h _{early warning} , if h _wading < h _{early warning} , then the target vehicle has waded, but does not make any response, operates normally and continuously detects the wading situation of the target vehicle.

In one embodiment of the present invention, the preset first threshold is h _{early warning} , the second threshold is h _limit , and h _{early warning} < h _limit , and the wading depth of the target vehicle is obtained based on the vehicle wading water level line identification model above h _wading , compare the relationship between h _wading and h _{early warning} , if h _wading ≥ h _{early warning} , then it is determined that the wading state of the target vehicle is a first-level wading.

In one embodiment of the present invention, the preset first threshold is h _{early warning} , the second threshold is h _limit , and h _{early warning} < h _limit , and the wading depth of the target vehicle is obtained based on the vehicle wading water level line identification model above h _wading , compare the relationship between h _wading and h _{early warning} , and get h _wading ≥ h _limit , then it is determined that the wading state of the target vehicle is a second-level wading.

Fig. 6 is a block diagram of an apparatus for determining a vehicle wading state according to an exemplary embodiment of the present application. The device can be applied to the implementation environment shown in FIG. 1 and is specifically configured in the smart terminal 103 . The apparatus may also be applicable to other exemplary implementation environments, and be specifically configured in other devices, and this embodiment does not limit the implementation environments applicable to the apparatus.

As shown in FIG. 6 , the exemplary vehicle wading state determination device includes: an image acquisition module 610 , a wading determination module 620 , a wading depth determination module 630 , and a wading state determination module 640 .

Wherein, the image acquisition module 610 is used to acquire the target environment image of the target vehicle, and the target environment image includes the body image of at least one side body of the target vehicle; the wading determination module 620 is used to obtain the target vehicle of the target vehicle based on the target environment image. The wading water level line; the wading depth determination module 630 is used to determine the target vehicle wading depth of the target vehicle based on the positional relationship between the target vehicle wading water level line and the target vehicle preset flag position; the wading state determination module 640 uses Based on the wading depth of the target vehicle, the wading state of the target vehicle is determined.

The cameras included in the above-mentioned image acquisition module 610 are all existing panoramic video cameras of the vehicle itself for the driver to observe the surrounding conditions of the vehicle, so there is no need to add additional peripheral equipment to save costs. In addition, when the vehicle is running, the on-board camera is always on, which can automatically monitor the vehicle's wading situation, and send a reminder when the wading depth exceeds the preset threshold, without the driver actively triggering the wading depth sensing system .

It should be noted that the device for determining the vehicle wading state provided in the above-mentioned embodiments and the method for determining the vehicle wading state provided in the above-mentioned embodiments belong to the same concept, and the specific operation methods of each module and unit have been described in the method embodiment has been described in detail, and will not be repeated here. In the actual application of the road condition refreshing device provided by the above-mentioned embodiments, the above-mentioned function allocation can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. , which is not limited here.

Based on the wading depth of the target vehicle, after determining the wading state of the target vehicle, it also includes: when the wading state of the target vehicle is a first-level wading, a first-level alarm is issued to remind the driver that the current vehicle has waded; when the target vehicle is wading The state is level 2 wading, and a level 2 alarm is issued to remind the driver that the current vehicle parts have been wading.

Fig. 7 is a block diagram of a vehicle wading alarm device according to an exemplary embodiment of the present application.

As shown in FIG. 7 , the vehicle wading warning device includes: a display module 710 , an indicator light module 720 and a speaker module 730 .

Among them, the display module 710, the display module includes at least one display screen, which is used to send text alarm information based on the wading state of the target vehicle; the indicator light module 720, the indicator light module includes at least 2 kinds of color indicator lights, used for The status activates indicator lights of different colors to send out light alarm information; the speaker module 730, the speaker module includes at least one buzzer, and is used to send out voice alarm information based on the wading state of the target vehicle.

In one embodiment of the present invention, based on the above judgment conditions, it is determined that the wading state of the target vehicle is a first-level wading, and then the target vehicle is controlled to issue a first-level alarm, which includes but is not limited to through the instrument panel or the central control system. The screen displays the current wading depth, and at the same time activates the yellow indicator light, and sends out a voice broadcast through the buzzer or horn that "the current water depth has exceeded the warning depth, and continuing to drive may cause the risk of flameout" to remind the driver to change the driving in time route.

In one embodiment of the present invention, based on the above judgment conditions, it is determined that the wading state of the target vehicle is a secondary wading state, and then the target vehicle is controlled to issue a secondary alarm, which includes but is not limited to the instrument panel or central control The screen displays the current wading depth, and at the same time starts the red indicator light, and sends out the voice broadcast of "a certain important part of the vehicle has begun to enter the water, please exit the current water area immediately" through the buzzer or horn to remind the driver to stop immediately OK and check the vehicle status.

Fig. 8 is a schematic structural diagram of a device for determining a vehicle wading state shown in an exemplary embodiment of the present application; Fig. 9 is a schematic diagram of the connection relationship of a device for determining a vehicle wading state shown in an exemplary embodiment of the present application.

As shown in Fig. 8 and Fig. 9, the vehicle wading state determination device includes: a vehicle-mounted camera module 910 (equivalent to the above-mentioned image acquisition module 610), a vehicle wading detection module 920 (equivalent to the above-mentioned wading state determination module 620), a vehicle body Altitude engineering calibration module 930 (equivalent to the above-mentioned wading depth determination module 630), vehicle controller module 940 (equivalent to the above-mentioned wading state determination module 640), early warning and alarm module 950 (equivalent to the above-mentioned vehicle wading shown in FIG. water alarm device).

The on-board camera module includes a front-view camera and two side-view cameras, which can ensure all-round monitoring of the wading state around the vehicle through the imaging system surrounding the vehicle body. Based on the vehicle-mounted camera module shown in Figure 8 and Figure 9, the vehicle wading detection module, the vehicle body height engineering calibration module, the vehicle controller module, and the connection relationship between the early warning and alarm module are: the vehicle-mounted camera module and the vehicle wading detection module The vehicle wading detection module is connected to the vehicle controller module, the vehicle controller module is connected to the early warning and alarm module, and the body height engineering calibration module is connected to the vehicle controller module.

Fig. 10 is a full flowchart of vehicle wading alarm response shown in an exemplary embodiment of the present application.

As shown in Figure 10, the camera recognizes the vehicle wading state, and decides whether to trigger the vehicle wading depth sensing according to the situation. At the same time, the vehicle controller combines the camera and the vehicle body height engineering calibration system to calculate the vehicle wading depth information and judge the current warning level. When the wading depth is greater than the warning depth but less than the limit wading depth, the current wading depth will be displayed on the instrument panel or the central control screen, and the buzzer or horn will send out "the current water depth has exceeded the warning depth, continuing to drive may lead to flameout risk" voice broadcast to remind the driver to change the driving route in time. When the wading depth is greater than the limit wading depth, the current wading depth will be displayed on the instrument panel or the central control screen, and the buzzer or horn will send out the message "some important part of the vehicle has begun to enter water, please exit the current water area immediately" Voice broadcast to remind the driver to stop immediately and check the vehicle status. In addition, the above-mentioned safety warning playback will always exist until the vehicle has left the wading environment or the wading depth is no longer within the above-mentioned warning range.

FIG. 11 shows a schematic structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application. It should be noted that the computer system 1000 of the electronic device shown in FIG. 11 is only an example, and should not limit the functions and scope of use of the embodiments of the present application.

As shown in FIG. 11 , the computer system 1100 includes a central processing unit (Central Processing Unit, CPU) 1101, which can be stored in a program in a read-only memory (Read-Only Memory, ROM) 1102 or loaded into a random access memory ( RandomAccessMemory, RAM) 1103 to perform various appropriate actions and processing, such as performing the methods in the above-mentioned embodiments. In RAM 1103, various programs and data necessary for system operation are also stored. The CPU 1101 , ROM 1102 , and RAM 1103 are connected to each other via a bus 1104 . An input/output (Input/Output, I/O) interface 1105 is also connected to the bus 1104 .

The following components are connected to the I/O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CathodeRayTube, CRT), a liquid crystal display (LiquidCrystalDisplay, LCD) etc., and a speaker; including a hard disk, etc. and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I/O interface 1105 as needed. A removable medium 1111 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 1110 as necessary so that a computer program read therefrom is installed into the storage section 1108 as necessary.

In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 1109, and/or installed from removable media 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are performed.

It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program thereon. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . A computer program embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Wherein, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or part of the code includes one or more executable instruction. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a A combination of dedicated hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or by hardware, and the described units may also be set in a processor. Wherein, the names of these units do not constitute a limitation of the unit itself under certain circumstances.

Another aspect of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is made to execute the method for determining a vehicle wading state as above. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

Another aspect of the present application also provides a computer program product or computer program, the computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for determining the vehicle wading state provided in the above-mentioned embodiments.

The above-mentioned embodiments only illustrate the principles and effects of the present invention, but are not intended to limit the present invention. Anyone skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed in the present invention shall still be covered by the claims of the present invention.

Claims (17)

1. A method for determining a vehicle wading state, characterized in that the method comprises: acquiring a target environment image of the target vehicle, where the target environment image includes a body image of at least one body of the target vehicle; determining a target vehicle wading water level of the target vehicle based on the target environment image; Determining the target vehicle wading depth of the target vehicle based on the positional relationship between the target vehicle wading water level line and the vehicle marker position of the target vehicle; Based on the wading depth of the target vehicle, the wading state of the target vehicle is determined. 2. The vehicle wading state determination method according to claim 1, wherein, based on the target environment image, obtaining the target vehicle wading water level line of the target vehicle comprises: Acquiring a plurality of sample images of the target vehicle, the sample images including body images of at least one body of the target vehicle; Marking the vehicle wading water level line of the sample image to obtain a training sample data set; An image recognition model is trained through the sample data set, and the trained image recognition model is used as a vehicle wading water level recognition model; Inputting the target environment image of the target vehicle into the vehicle wading water level recognition model to obtain the wading water level line of the target vehicle. 3. The vehicle wading state determination method according to claim 1, characterized in that, after obtaining the target vehicle wading water level line of the target vehicle, determining the target vehicle wading depth of the target vehicle includes at least one of the following : Acquiring a plurality of vehicle marker positions in the target environment image, and determining a target marker position based on the target vehicle wading water level line and the vehicle marker position, according to the target vehicle wading water level line and the target marker position Positional relationship, determining the wading depth of the target vehicle; Obtain the complete area of the tire of the target vehicle, and regard the area of the tire above the wading water level of the target vehicle as the exposed area of the tire, and determine the wading of the target vehicle based on the relationship between the exposed area of the tire and the complete area of the tire depth. 4. The method for determining the vehicle wading state according to claim 3, wherein a plurality of vehicle marker positions in the target environment image are obtained, and the vehicle marker positions are determined based on the target vehicle wading water level line and the vehicle marker positions The target flag position, according to the positional relationship between the target vehicle wading water level line and the target flag position, determining the wading depth of the target vehicle includes: Based on the target vehicle wading water level, determining a plurality of vehicle flags higher than the target vehicle wading water level as a plurality of expected flags; Determining a vehicle flag closest to the target vehicle among the plurality of expected flags as the target flag; The wading depth of the target vehicle is determined based on the target marker position and the positional relationship between the target marker position and the wading water level line of the target vehicle. 5. The vehicle wading state determination method according to claim 4, wherein, based on the target flag and the target flag and the target vehicle wading water level line, determining the wading depth of the target vehicle includes : Obtain the actual height value of the target flag, Determining the distance between the target mark position and the wading water level line of the target vehicle as the separation distance; Based on the interval distance and the preset image distance-preset actual distance library, determine the actual interval of the interval distance, and obtain the actual interval value; The wading depth of the target vehicle is determined based on the difference between the actual height value of the target marker and the actual interval value. 6. The method for determining the wading state of a vehicle according to claim 3, wherein the complete area of the tire of the target vehicle is obtained, and the area of the tire above the wading water level of the target vehicle is regarded as the exposed area of the tire, based on The relationship between the exposed area of the tire and the complete area of the tire, determining the wading depth of the target vehicle includes: Obtaining the tire exposed area of the target vehicle tire exposed to water, and determining the complete area of the tire based on the vehicle model of the target vehicle; determining the ratio of the tire exposed area of the target vehicle based on the exposed area of the tire and the complete area of the tire; Based on the tire exposed area ratio and the preset tire exposed area ratio-preset target vehicle wading depth library, the target vehicle wading depth of the target vehicle is determined. 7. The method for determining the vehicle wading state according to claim 3, wherein, if the first and second wading depths are determined, determining the wading depth of the target vehicle further comprises: Acquiring the depth of ponded water, the clarity of ponded water and the blurred area of vehicle tires in the environment where the target vehicle is located, and determining the environmental index of the environment in which the target vehicle is located; The first wading depth is determined based on the relative positional relationship between the wading water level line of the target vehicle and the target marker position, and the second wading depth is determined based on the proportional relationship between the exposed area of the tire and the complete area of the tire; Based on the wading environment index and the standard environment index, determine the first weight of the first wading depth and the second weight of the second wading depth, when the wading environment index is greater than or equal to the standard environment index , the first weight is greater than the second weight, and when the wading environment index is less than the standard environment index, the first weight is less than the second weight; Based on the first wading depth, the first weight, the second wading depth, and the second weight, determine the wading depth of the target vehicle. 8. The vehicle wading state determination method according to claim 3, wherein determining the target vehicle wading depth of the target vehicle further comprises: Obtaining a plurality of wading water levels of the target vehicle, and determining the plurality of wading water levels as expected wading water levels; Determining an expected wading depth of the target vehicle based on the expected wading water level, to obtain a maximum value of the expected wading depth; The maximum expected wading depth is determined as the target vehicle wading depth. 9. The vehicle wading state determination method according to claim 2, wherein obtaining the wading water level line of the target vehicle comprises: acquiring multiple frames of target environment images of the target vehicle, Inputting multiple frames of the target environment image into the vehicle wading water level recognition model to obtain multiple vehicle wading water lines; Giving calculation weights to the plurality of vehicle wading water levels, obtaining theoretical wading water levels of the plurality of vehicle wading water levels based on the calculation weights, and taking the theoretical wading water levels as the target vehicle's Vehicle wading water level. 10. The vehicle wading state determination method according to claim 2, wherein obtaining a plurality of sample images of the target vehicle further comprises: Obtain the ambient light intensity of the environment where the target vehicle is located; When the ambient light intensity is lower than the standard light intensity, a vehicle backup light source is activated to supplement light on the sample image, and the vehicle backup light source includes a welcome light facing downwards at the position of the reversing mirror. 11. The vehicle wading state determination method according to claim 2, wherein acquiring a plurality of sample images of the target vehicle comprises: Collecting the initial environment image of the target vehicle, and identifying the height of the splash and the height of the water wave in the initial environment image; Using the maximum value of the splash height and the water wave height in the initial environmental image as the water surface fluctuation value of the initial environmental image; When the water surface fluctuation value is less than the standard water surface fluctuation value, keep the initial environment image, and keep the next The initial environment image of is used as the target environment image. 12. The vehicle wading state determination method according to any one of claims 1-11, characterized in that, before obtaining the target vehicle wading water level line of the target vehicle, the method further includes: Based on the target environment image, determining water accumulation position information of the water accumulation area in the target environment image and tire position information of target vehicle tires in the target environment image; determining the water accumulation location of the water accumulation area and the tire location of the target vehicle tire based on the water accumulation location information and the tire location information; If the water accumulation area overlaps with the tire area, it is determined that the target vehicle has waded. 13. The vehicle wading state determination method according to any one of claims 1-11, wherein, based on the wading depth of the target vehicle, determining the wading state of the target vehicle comprises: determining a wading depth value of the target vehicle based on the wading depth of the target vehicle, When the wading depth of the target vehicle is greater than or equal to the preset first threshold, it is determined that the wading state of the target vehicle is a first-level wading; When the wading depth of the target vehicle is greater than or equal to the preset second threshold, it is determined that the wading state of the target vehicle is a secondary wading state; The preset first threshold is smaller than the preset second threshold. 14. The vehicle wading state determination method according to claim 13, characterized in that, after determining the wading state of the target vehicle based on the wading depth of the target vehicle, further comprising: When the wading state of the target vehicle is a first-level wading, a first-level alarm is issued to remind the driver that the current vehicle has been wading; When the wading state of the target vehicle is the second-level wading, a second-level alarm is issued to remind the driver that the current vehicle parts have been wading. 15. A vehicle wading state determination device, characterized in that the device comprises: An image acquisition module, configured to acquire a target environment image of the target vehicle, where the target environment image includes a body image of at least one body of the target vehicle; A wading determination module, configured to obtain the target vehicle wading water level of the target vehicle based on the target environment image; A wading depth determination module, configured to determine the target vehicle wading depth of the target vehicle based on the positional relationship between the target vehicle's wading water level and the target vehicle's preset marker position; A wading state determining module, configured to determine the wading state of the target vehicle based on the wading depth of the target vehicle. 16. An electronic device, characterized in that the electronic device comprises: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device realizes any one of claims 1 to 14 Method for determining vehicle wading state. 17. A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is made to execute the vehicle according to any one of claims 1 to 14. Method for determining wading state.

Images