CN110070723A - The method, apparatus and system of entrance vehicle identification - Google Patents

Abstract

The present invention provides a method, device and system for vehicle identification at an entrance and exit, and relates to the technical field of video surveillance, wherein the method for vehicle identification at an entrance and exit includes: a camera group is arranged at the entrance and exit, and the camera group includes at least one camera. , the camera group shoots the entrance and exit scene to obtain the initial image, and secondly, the camera group detects whether there is a vehicle in the captured initial image, and then, when it is detected that there is a vehicle in the initial image, the camera group performs the initial image of the vehicle. Vehicle identification, output vehicle identification results, through the above processing method, avoid the need to rely on the ground sensor coil or radar and other peripherals to trigger the license plate recognition process at the entrance and exit, effectively solve the problem of license plate inclination due to large inclination and front and rear following vehicles The problem of license plate recognition in the case of occlusion is convenient and accurate.

Description

Method, device and system for vehicle identification at entrance and exit

technical field

The present invention relates to the technical field of video surveillance, and in particular, to a method, device and system for vehicle identification at an entrance and exit.

Background technique

In recent years, there have been more and more family cars, and the parking problem of vehicles has become more and more prominent. Video parking solutions relying on license plate recognition technology are gradually emerging, in which the results of license plate recognition are used as the basis for charging. Therefore, it is critical to quickly and efficiently identify vehicle license plates at the entrances and exits of parks and parking lots.

A commonly used solution is to rely on peripherals such as ground sensing coils or radar for triggering. However, due to the poor angle of the vehicle monitored by the trigger position, that is, when the depth of the entrance and exit of the park and parking lot is short, the vehicle body will be tilted. , that is, the inclination of the license plate is very large (for example, greater than 60 degrees), which causes problems such as the license plate cannot be recognized, and the recognition error is wrong. In addition, when the traffic flow at the entrances and exits of the park and parking lot is relatively dense, the phenomenon of the front vehicle blocking the rear vehicle will occur, which will lead to the unrecognizable license plate of the rear vehicle. For parks and parking lots, if the license plate cannot be recognized, it means that it cannot be charged. If you view the passing video to obtain the license plate of the vehicle, it will not only be time-consuming and labor-intensive, but also affect the normal passage of the vehicle.

In addition, in the current technology, there is a technology that combines cameras to recognize license plates, that is, the detection of vehicles by ground-sensing coil vehicle detectors triggers license plate recognition camera recognition, and the result is sent to the main control computer. Recording cameras for license plate recognition. Relying on the triggering of the ground-sensing coil vehicle detector, intelligent capture and recognition cannot be performed based on the vehicle location. The license plate re-recording camera only controls the trigger recognition after the license plate recognition camera does not detect the sending host computer. The consequence of this is that the time is uncertain and there is an obvious front-to-back relationship, which cannot solve the problem of license plate misrecognition.

To sum up, at present, there is no favorable solution to the problems that the license plate recognition process needs to install additional peripherals such as ground sensing coils or radars underground, as well as the license plate recognition occlusion, and the inclination angle is too large.

SUMMARY OF THE INVENTION

In view of this, the purpose of the embodiments of the present invention is to provide a method, device and system for vehicle identification at entrances and exits. By setting up a camera group, etc., the tedious process of additionally installing peripherals such as ground induction coils or radars is omitted, and the license plate recognition is improved. s efficiency.

In a first aspect, an embodiment of the present invention provides a method for vehicle identification at an entrance and exit. A camera group is provided at the entrance and exit, and the camera group includes at least one camera, and the method includes:

The camera group shoots the entrance and exit scene to obtain the initial image;

The camera group detects the presence of a vehicle in the initial image;

When it is detected that a vehicle exists in the initial image, the camera group performs vehicle recognition on the initial image of the existing vehicle, and outputs the vehicle recognition result.

In conjunction with the first aspect, an embodiment of the present invention provides a first possible implementation of the first aspect, wherein the camera group includes a master camera and a slave camera;

Before outputting the vehicle identification result, the method further includes:

Acquiring vehicle identification information, where the vehicle identification information includes the first vehicle identification information identified by the main camera and the second vehicle identification information identified by the camera, and the method further includes:

The first vehicle identification information and the second vehicle identification information are compared and analyzed to obtain a vehicle identification result.

In conjunction with the first possible implementation manner of the first aspect, the embodiment of the present invention provides a second possible implementation manner of the first aspect, wherein the method further includes:

When the entrance and exit road is a straight road, the master camera and the slave camera are set on the same side of the road, and the setting heights of the master camera and the slave camera are different;

When the entrance and exit roads are curved, the master camera and the slave camera are respectively set on both sides of the road.

In combination with the first aspect or the first possible implementation manner of the first aspect, the embodiment of the present invention provides a third possible implementation manner of the first aspect, wherein when a vehicle is detected in the initial image, the camera group Perform vehicle recognition on the initial image of the existing vehicle, and output the vehicle recognition result, including:

The camera group performs license plate recognition and/or vehicle feature extraction on the initial image of the existing vehicle;

If the license plate information is recognized, the camera group will use the license plate information or vehicle characteristics as the vehicle identification result;

If the license plate information is not recognized, the camera group extracts vehicle features and uses the vehicle features as the vehicle recognition result.

In conjunction with the third possible implementation manner of the first aspect, the embodiment of the present invention provides the fourth possible implementation manner of the first aspect, wherein, if the license plate information is recognized, the vehicle identification information further includes the license plate confidence;

License plate confidence includes overall license plate confidence and/or individual character confidence.

With reference to the first possible implementation manner of the first aspect, the embodiment of the present invention provides a fifth possible implementation manner of the first aspect, wherein the first vehicle identification information and the second vehicle identification information are compared and analyzed, and output Vehicle identification results, including:

Compare the overall confidence C1 of the first license plate calculated by the main camera with the overall confidence C2 of the second license plate calculated by the slave camera;

When the comparison result is equal, output the first license plate information recognized by the main camera or the second license plate information recognized by the secondary camera as the vehicle identification result;

When the comparison result is not equal, and any one of the confidence level C1 of the first license plate result or the confidence level C2 of the second license plate result is greater than the first threshold, output the overall confidence level C1 of the first license plate whose value is greater than the first threshold The corresponding first license plate information or the second license plate information corresponding to the overall confidence level C2 of the second license plate is used as the vehicle identification result;

When the comparison result is unequal, and both the overall confidence C1 of the first license plate and the overall confidence C2 of the second license plate are greater than the second threshold, output the first license plate information corresponding to the overall confidence C1 of the first license plate with a higher value Or the second license plate information corresponding to the overall confidence level C2 of the second license plate, as the vehicle identification result;

When the comparison result is not equal, and the overall confidence C1 of the first license plate and the overall confidence C2 of the second license plate are greater than the third threshold and less than or equal to the second threshold, compare the variance of the confidence of the first single character of the main camera and the variance of the confidence of the second single character collected from the camera, take the output with the smaller variance from the first license plate information corresponding to the main camera or the second license plate information corresponding to the camera, as the vehicle recognition result;

When the comparison result is not equal, and the overall confidence level C1 of the first license plate and the overall confidence level C2 of the second license plate are both less than the third threshold, compare the first vehicle feature recognized by the main camera with the second vehicle feature recognized by the secondary camera. , and output the same part of the first vehicle feature and the second vehicle feature as the vehicle identification result.

With reference to the first possible implementation manner of the first aspect, the embodiment of the present invention provides a sixth possible implementation manner of the first aspect, wherein the method further includes:

When only one of the first vehicle identification information and the second vehicle identification information is identified, and the identification time of the camera corresponding to the unidentified vehicle identification information exceeds the preset time, according to the identified first vehicle The identification information or the second vehicle identification information, and the vehicle identification result is output.

In a second aspect, an embodiment of the present invention provides a device for vehicle identification at an entrance and exit, including:

The image acquisition module is used for the camera group to shoot the entrance and exit scene to obtain the initial image;

The vehicle information detection module is used for the camera group to detect whether there is a vehicle in the initial image;

The license plate recognition module is used for the camera group to perform vehicle recognition on the initial image of the existing vehicle when it is detected that there is a vehicle in the initial image, and output the vehicle recognition result.

In a third aspect, an embodiment of the present invention provides a system for identifying vehicles at an entrance and exit, including: a billing client, a barrier, a display screen, and a device for identifying vehicles at an entrance and exit;

The device for vehicle identification at the entrance and exit is respectively connected with the charging client, the road gate and the display screen, and the display screen is connected with the charging client;

The barrier is lifted after receiving the first vehicle identification information or the second vehicle identification information output by the device for identifying vehicles at the entrance and exit;

The billing client calculates the time interval between the first vehicle identification information or the second vehicle identification information output by the entrance and the first vehicle identification information or the second vehicle identification information output by the exit, and calculates parking according to the time interval and the preset unit price cost;

The display screen is used to display the first vehicle identification information, the second vehicle identification information and the parking fee.

In a fourth aspect, an embodiment of the present invention further provides a terminal, including a memory and a processor, where the memory is used to store a program that supports the processor to perform the method for vehicle identification at an entrance and exit provided in the above aspect, and the processor is configured to execute the program in the memory stored program.

An embodiment of the present invention provides a method, device, and system for vehicle identification at an entrance and exit, wherein the method for identifying a vehicle at an entrance and exit includes: a camera group is provided at the entrance and exit, and the camera group includes at least one camera. During use, first, The camera group shoots the entrance and exit scene, that is, the camera group monitors the entrance and exit scene in real time, so as to obtain the initial image, and secondly, the camera group detects whether there is a vehicle in the initial image, that is, the camera group detects whether there is a license plate recognition at the entrance and exit. After that, when a vehicle is detected in the initial image, it means that there is a vehicle passing through the entrance and exit. The camera group performs vehicle identification on the initial image of the existing vehicle and outputs the vehicle identification result. The vehicle identification information mainly includes license plate information and/or Features, thereby realizing the accurate collection of vehicle information, and further ensuring the purpose of charging related venues according to the license plate, which is convenient and fast.

Other features and advantages of the present invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the description, claims and drawings.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

FIG. 1 shows a first flowchart of a method for vehicle identification at an entrance and exit provided by an embodiment of the present invention;

FIG. 2 shows a structural frame diagram of the method for vehicle identification at an entrance and exit provided by an embodiment of the present invention;

FIG. 3 shows a structural connection diagram of the method for vehicle identification at an entrance and exit provided by an embodiment of the present invention;

FIG. 4 shows a structural connection diagram of an apparatus for identifying vehicles at an entrance and exit provided by an embodiment of the present invention.

Icons: 1-image acquisition module; 2-vehicle information detection module; 3-license plate recognition module.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

At present, the problem of vehicle parking is becoming more and more prominent. Video parking solutions relying on license plate recognition technology are gradually emerging. In this solution, only the license plate recognition results are used as the basis for charging. When the depth of the entrance and exit of the park and parking lot is short, it will cause the vehicle body to tilt, that is, the inclination of the license plate is very large, which will cause problems such as the license plate cannot be recognized or incorrectly recognized. Relying on the triggering of the ground-sensing coil vehicle detector, intelligent capture and recognition cannot be performed based on the vehicle location. The license plate supplementary recording camera only controls the trigger recognition after the license plate recognition camera does not detect the sending host computer. The consequence of this is that the time is uncertain and there is an obvious front-to-back relationship. The ground induction coil or radar is pre-installed at the entrance and exit, and then the ground induction coil or radar and other peripherals are used for triggering to know whether there is a vehicle passing by the entrance and exit.

Based on this, embodiments of the present invention provide a method, device, and system for vehicle identification at an entrance and exit, which will be described below through embodiments.

Example 1

Referring to FIGS. 1 , 2 and 3 , the method for vehicle identification at an entrance and exit proposed in this embodiment specifically includes setting a camera group at the entrance and exit, and the camera group includes at least one camera, and the method for vehicle identification at an entrance and exit includes:

Step S101 : the camera group shoots the entrance and exit scene to obtain an initial image. It should be noted that the initial image is actually the YUV data of the captured image, that is, the unencoded initial data. Since the entry and exit times of vehicles at the entrances and exits of underground parking lots and parks are uncertain, the camera group set at the entrance and exit needs to shoot the entrance and exit scenes in real time to avoid missing passing vehicles. initial image.

Step S102: The camera group detects whether there is a vehicle in the initial image. In order to further check whether a vehicle passes by the entrance and exit, the camera group detects whether there is a vehicle in the initial image. When it is detected that there is no vehicle in the initial image, it means that there is no vehicle passing by the entrance. In this case, it is unnecessary to process the captured initial image.

Step S103: When it is detected that there is a vehicle in the initial image, it means that there is a vehicle passing by the entrance. In this case, the camera group performs vehicle recognition on the initial image of the existing vehicle, and outputs the vehicle recognition result. In the specific implementation process, the vehicle The recognition result is usually the license plate information or vehicle characteristics of the vehicle, that is, the vehicle is identified and marked through the license plate information or vehicle characteristics.

The following is a further detailed description. As an embodiment of this technical solution, if the camera group contains only one camera, the camera first performs license plate recognition on the initial image of the existing vehicle. If the license plate information is recognized, the camera group uses the license plate information as the vehicle identification. The result is uploaded to the billing client; if the license plate information is not recognized, the camera group extracts vehicle features from the initial image of the existing vehicle, such as the model, color, logo, etc., and uploads the vehicle features as the vehicle recognition result to the Billing client.

As another embodiment of this technical solution, if there is only one camera in the camera group, the camera first performs license plate recognition on the initial image of the existing vehicle, and if the license plate information is recognized, the license plate confidence is calculated, and the license plate confidence includes the license plate. Overall confidence or single-character confidence. When the overall confidence of the license plate is greater than or equal to the first preset value or the variance of the single-character confidence is less than the second preset value, the camera group will use the license plate information as the vehicle recognition result and upload it to billing Client; when the overall confidence of the license plate is less than the first preset value or the variance of the single-character confidence is greater than or equal to the second preset value, the camera group extracts vehicle features on the initial image of the existing vehicle, for example, the model, color, vehicle If the license plate information is not recognized, the camera group extracts the vehicle features from the initial image of the existing vehicle, such as model, color, vehicle logo, etc. Upload the vehicle features to the billing client as the vehicle identification result.

The technical solutions in the above embodiments can perform intelligent capture and identification of the vehicle according to the vehicle position, without relying on peripheral triggers such as ground-sensing coil vehicle detectors, and when the vehicle has no license plate or the license plate confidence is too low, the model, color, Vehicle features such as car logos are identified and marked, which effectively improves the accuracy of vehicle identification.

In the specific implementation process, the above-mentioned camera group may include a master camera and a slave camera. The dual setting of the master camera and the slave camera can effectively solve the problems of the large license plate inclination and the inability to collect and recognize the license plate from the front and rear following vehicles. In the identification method, before outputting the vehicle identification result, the above method further includes:

Step S104: Obtain vehicle identification information, where the vehicle identification information includes the first vehicle identification information identified by the main camera and the second vehicle identification information identified by the camera;

Step S105: Compare and analyze the first vehicle identification information and the second vehicle identification information to obtain a vehicle identification result.

The first vehicle identification information and the second vehicle identification information are compared and analyzed to obtain the vehicle identification result. Specifically, in the hardware design process, the configuration of the master camera and the slave camera can be the same, that is, both the master camera and the slave camera include built-in cameras. The processor, in this case, the initial image captured by the master camera can be transmitted to the slave camera, and the processor built in the slave camera compares and analyzes the first vehicle identification information and the second vehicle identification information, of course, the slave camera captures The obtained initial image can be sent to the main camera, and the processor built in the main camera can compare and analyze the first vehicle identification information and the second vehicle identification information; the configuration of the main camera and the slave camera can also be different, that is, the main camera or the slave camera. In this case, the initial image captured by the master camera (or the slave camera) can be transmitted to the slave camera (or the master camera), and the built-in processor of the slave camera (or the master camera) The first vehicle identification information and the second vehicle identification information are compared and analyzed; the master camera and the slave camera may not include a built-in processor, in this case, both the master camera and the slave camera are connected with newly added independent processors , the initial images captured by the main camera and the slave camera are sent to an independent processor, and the independent processor performs a comparative analysis on the first vehicle identification information and the second vehicle identification information.

In addition, the method for vehicle identification at the entrance and exit also includes:

(1) When the entrance and exit road is a straight road, the problem of front and rear occlusion of the vehicle is easy to occur when the entrance and exit road is a straight road. In this case, the main camera and the slave camera are set on the same side of the road, and the main camera and the slave camera are on the same side. Different heights are set to identify the vehicle at different heights. Preferably, the horizontal interval between the master camera and the slave camera is 2 meters, so as to detect different positions of the vehicle at the same time. In addition, in order to take into account the occlusion relationship of the camera itself, the height of the main camera is adjusted to 1.5 meters, and the height of the secondary camera is adjusted to 1 meter to realize the collection of license plate information at different heights. It should be noted that the position settings of the master camera and the slave camera can be flexibly set according to the usage scenarios.

(2) When the entrance and exit road is a curve, the problem of excessive vehicle inclination is easy to occur when the entrance and exit road is a curve. In this case, the main camera and the slave camera are respectively set on both sides of the road. Preferably, the height of the master camera is adjusted to 1 meter, and the height of the slave camera is adjusted to 1 meter, that is, the master camera and the slave camera are set relative to each other, so as to be able to capture license plates with an excessively large angle of inclination. It should be noted that the position and height settings of the master camera and the slave camera can be flexibly set according to the usage scenarios.

In the above step S104, when it is detected that there is a vehicle in the initial image, the camera group performs vehicle identification on the initial image of the existing vehicle to obtain vehicle identification information, which specifically includes:

The camera group performs license plate recognition on the initial image of the existing vehicle,

If the camera group recognizes the license plate information, the camera group uses the license plate information as vehicle identification information.

If the license plate information is not recognized, the camera group extracts vehicle features, and uses the vehicle features as vehicle identification information, for example, vehicle features such as model, color, and vehicle logo as vehicle identification information.

If the license plate information is recognized, the vehicle identification information also includes the license plate confidence level calculated by the camera group, and the license plate confidence level includes the overall license plate confidence level and the individual character confidence level.

The master camera calculates the overall confidence C1 of the first license plate of the first vehicle identification information, and the slave camera calculates the overall confidence C2 of the second license plate of the second vehicle identification information. It should be noted here that, unlike the prior art, the master camera and the slave The camera collects and compares the overall confidence of the vehicle's license plate respectively.

Preferably, if the license plate information is identified, in step 105, the above-mentioned first vehicle identification information and the above-mentioned second vehicle identification information are compared and analyzed to obtain a vehicle identification result, which specifically includes:

The overall confidence level C1 of the first license plate and the overall confidence level C2 of the second license plate are compared to check whether the overall confidence level of the license plate of the same vehicle collected by the main camera and the secondary camera is equal.

When the comparison result is equal, it is determined that both the master camera and the slave camera have collected the vehicle license plate information. In this case, the first license plate information recognized by the master camera or the second license plate information recognized by the slave camera is output. As the vehicle identification result, the first license plate information or the second license plate information may be taken as the vehicle identification result.

When the comparison result is not equal, and any one of the overall confidence C1 of the first license plate or the overall confidence C2 of the second license plate is greater than the first threshold, output the overall confidence C1 of the first license plate whose value is greater than the first threshold The first license plate information or the second license plate information corresponding to the overall confidence level C2 of the second license plate is used as the vehicle identification result. In the implementation process, the size of the first threshold is preferably 95%. It is explained here that in the case of unequal comparison results, when one of C1 or C2 is greater than 95%, it is sufficient to output the license plate information collected by the corresponding camera. Since the confidence value is high, even if the comparison result is not If the license plate information corresponding to the confidence level greater than 95% is output, the accurate license plate information can be obtained. The size of the first threshold can be flexibly set according to the situation.

When the comparison result is not equal, and both the overall confidence C1 of the first license plate and the overall confidence C2 of the second license plate are greater than the second threshold, the first license plate corresponding to the overall confidence C1 of the first license plate with a higher value is output. The license plate information or the second license plate information corresponding to the overall confidence level C2 of the second license plate is used as the vehicle identification result. It is explained here that in the case where the comparison results are not equal, when both C1 and C2 are greater than the second threshold, take the value between C1 and C2. Accurate license plate information can be obtained by using the license plate information corresponding to the confidence level with a larger value. In the implementation process, the size of the second threshold is preferably 80%.

When the comparison result is not equal, and the overall confidence level C1 of the first license plate and the result confidence level C2 of the second license plate are greater than the third threshold and less than or equal to the second threshold, compare the variance of the confidence level of the first single character of the main camera and the variance of the confidence of the second single character collected from the camera, take the output with the smaller variance in the first license plate information corresponding to the main camera or the second license plate information corresponding to the camera, as the vehicle identification As a result, in the implementation process, preferably, the size of the third threshold is 60%. In the case of the first license plate information corresponding to the main camera or the second license plate information corresponding to the camera taking the output with the smaller variance, it is explained here that when the comparison results are not equal, when C1 and C2 are between 60% and 80%, The variance is calculated according to the single-character confidence obtained by each camera, and the license plate information with the smaller variance of the single-character confidence is used as the output. By combining the calculation of the variance, the specific calculation formula of the variance is as follows: or It can effectively filter out accurate license plate information.

When the comparison result is not equal, and the overall confidence level C1 of the first license plate and the overall confidence level C2 of the second license plate are both less than the third threshold, compare the first vehicle feature recognized by the master camera with the feature recognized by the slave camera. For the second vehicle feature, the same part of the first vehicle feature and the second vehicle feature is output as a vehicle identification result. It is explained here that in the case of unequal comparison results, in the case that C1 and C2 are both relatively small, in order to output more accurate license plate information, the same part of the model, color, car logo, etc. contained in the license plate information is used as the output, so that Vehicles can be identified by model, color, logo, etc.

Preferably, if the license plate information is not identified, step 105 specifically further includes:

Comparing the first vehicle feature identified by the master camera with the second vehicle feature identified by the slave camera, and outputting the same part of the first vehicle feature and the second vehicle feature as a vehicle identification result.

In addition, the method for vehicle identification at the entrance and exit further includes: when only one of the first vehicle identification information and the second vehicle identification information is identified, and the identification time of the camera that does not identify the vehicle identification information exceeds a preset time, according to the The identified first vehicle identification information or the second vehicle identification information outputs a vehicle identification result. That is, only one camera in the main camera or the slave camera has collected the vehicle identification information and the other camera that has not collected the vehicle identification information has exceeded the preset time. It should be noted here that the preset time is the preset peak value collected by the camera. time, and output the collected first vehicle identification information or vehicle identification information. In this case, the vehicle identification result can be output directly according to a collected vehicle identification information.

To sum up, the method for vehicle identification at the entrance and exit provided by this embodiment includes: a camera group is arranged at the entrance and exit. It should be noted that the camera group includes at least one camera. Shooting to obtain the initial image, secondly, the camera group detects whether there is a vehicle in the initial image, and then, when it is detected that there is a vehicle in the initial image, the camera group performs vehicle recognition on the initial image of the existing vehicle, and outputs the vehicle recognition result. Through the above processing The process saves the tedious process of setting up ground sensing coils and radars at the entrance and exit, and realizes the simultaneous recognition of license plate information by dual cameras. Combined with the comparison of confidence, it realizes the effective identification of vehicles, which is convenient and accurate.

Example 2

Referring to FIG. 4 , this embodiment provides an apparatus for vehicle identification at an entrance and exit, including: an image acquisition module 1, used by the camera group to photograph the entrance and exit scene to obtain an initial image, and a vehicle information detection module 2, used by the camera group to detect whether the initial image is There is a vehicle, and the license plate recognition module 3 is used for, when detecting that a vehicle exists in the initial image, the camera group performs vehicle recognition on the initial image of the existing vehicle, and outputs the vehicle recognition result.

The device for identifying an entrance and exit vehicle provided by the embodiment of the present invention has the same technical features as the method for identifying an entrance and exit vehicle provided by the above embodiment, so it can also solve the same technical problem and achieve the same technical effect.

Example 3

This embodiment provides a system for vehicle identification at the entrance and exit, including: a charging client, a barrier, a display screen, and a device for identifying vehicles at the entrance. The screen is connected to the screen. In the specific implementation, it is common that the vehicle identification device at the entrance and exit is connected to the gate through a switch or 485 line, and the display screen is connected to the billing client. During use, the gate receives the entrance and exit vehicles. After the first vehicle identification result or the second vehicle identification result output by the identification device is lifted, so that the vehicle to be parked enters, the billing client calculates the first vehicle identification result or the second vehicle identification result output by the entrance and the exit. The time interval between the outputted first vehicle identification result or the second vehicle identification result, that is, the parking time of the vehicle corresponding to the first vehicle identification result or the second vehicle identification result is calculated, and the parking time is calculated according to the time interval and the preset unit price After that, the first vehicle identification result, the second vehicle identification result and the parking fee are displayed on the display screen, so that the calculation and collection of the relevant parking fee can be realized conveniently and quickly.

To sum up, the system for vehicle identification at the entrance and exit provided in this embodiment includes: a charging client, a barrier, a display screen, and a device for identifying vehicles at the entrance. The barrier is connected to the display screen, and the display screen is connected to the billing client. During use, the barrier is first lifted after receiving the first vehicle identification result or the second vehicle identification result output by the vehicle identification device at the entrance and exit. After that, the billing client calculates the time interval between the first vehicle identification result or the second vehicle identification result output by the entrance and the first vehicle identification result or the second vehicle identification result output by the exit, and calculates the time interval according to the time interval and the predicted result. Set the unit price to calculate the parking fee, and display the first vehicle recognition result, the second vehicle recognition result and the parking fee on the display screen. Through the above processing process, the license plate recognition, fee calculation and display of the vehicle are conveniently realized, which is convenient and fast.

An embodiment of the present invention further provides a terminal, including a memory and a processor, where the memory is used to store a program that supports the processor to execute the method of the above embodiment, and the processor is configured to execute the program stored in the memory.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of any of the foregoing methods are executed.

It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. For the same and similar parts among the various embodiments, refer to each other Can. The method, device, and system for vehicle identification at entrances and exits provided by the embodiments of the present invention have the same implementation principles and technical effects as the foregoing method embodiments. For brief description, for the parts not mentioned in the device embodiments, reference may be made to the foregoing methods. Corresponding content in the examples.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. 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 in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present invention may be integrated to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. The existence of any such actual relationship or order should not be construed as indicating or implying relative importance. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention. It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. a kind of entrance vehicle identification method, which is characterized in that entrance is provided with phase unit, the phase unit includes extremely A few camera, which comprises

The phase unit shoots entrance scene, obtains initial pictures；

The phase unit, which detects, whether there is vehicle in the initial pictures；

When detecting in the initial pictures there are when vehicle, the phase unit is to there are the initial pictures of vehicle to carry out vehicle knowledge Not, vehicle identification result is exported.

2. entrance vehicle identification method according to claim 1, which is characterized in that the phase unit include main phase machine and From camera；

Before the output vehicle identification result, the method also includes:

Vehicle identification information is obtained, the vehicle identification information includes the first vehicle identification information recognized by the main phase machine With second vehicle identification information recognized from camera；

First vehicle identification information and second vehicle identification information are compared and analyzed, vehicle identification knot is obtained Fruit.

3. entrance vehicle identification method according to claim 2, which is characterized in that the method also includes:

When Entry-exit road is straight way, the main phase machine and described the same side that road is set from camera, wherein the master Camera is different from the setting height from camera；

When Entry-exit road is bend, the main phase machine and the two sides that road is separately positioned on from camera.

4. entrance vehicle identification method according to claim 1 or 2, which is characterized in that described described first when detecting There are when vehicle in beginning image, the phase unit exports vehicle identification knot to there are the initial pictures of vehicle to carry out vehicle identification Fruit, comprising:

The phase unit is to there are the initial pictures of vehicle to carry out Car license recognition and/or vehicle characteristics extraction；

If identifying license board information, the phase unit is using the license board information or vehicle characteristics as vehicle identification result；

If unidentified license board information out, the phase unit is using the vehicle characteristics as vehicle identification result.

5. entrance vehicle identification method according to claim 4, which is characterized in that described if identifying license board information Vehicle identification information further includes by the calculated license plate confidence level of the phase unit；

The license plate confidence level includes license plate entirety confidence level and/or monocase confidence level.

6. entrance vehicle identification method according to claim 2, which is characterized in that described by first vehicle identification Information is compared and analyzed with second vehicle identification information, exports vehicle identification result, comprising:

The the first license plate entirety confidence level C1 and second license plate calculated from camera for comparing the main phase machine calculating are integrally set Reliability C2；

When comparing result is equal, export main phase machine identification the first license board information or the identified from camera Two license board informations, as vehicle identification result；

When comparing result is unequal, and, the first license plate result confidence level C1 or the second license plate result confidence When any one numerical value spent in C2 is greater than first threshold, output numerical value is greater than the first license plate entirety confidence level of first threshold Corresponding first license board information of C1 or corresponding second license board information of the second license plate entirety confidence level C2 are known as vehicle Other result；

When comparing result is unequal, and, the first license plate entirety confidence level C1 and the second license plate entirety confidence level When C2 is all larger than second threshold, corresponding first license board information of the higher first license plate entirety confidence level C1 of output numerical value or Corresponding second license board information of second license plate entirety confidence level C2 described in person, as vehicle identification result；

When comparing result is unequal, and, the first license plate entirety confidence level C1 and the second license plate entirety confidence level C2 be greater than third threshold value, be less than or equal to second threshold when, compare main phase machine the first monocase confidence level variance and from The size of the variance of the collected second monocase confidence level of camera, corresponding first license board information of main phase machine or from The lesser output of variance is taken in corresponding second license board information of camera, as vehicle identification result；

When comparing result is unequal, and, the first license plate entirety confidence level C1 and the second license plate entirety confidence level When C2 is respectively less than third threshold value, the first vehicle characteristics and second vehicle identified from camera of the main phase machine identification are compared Feature exports the identical part in first vehicle characteristics and second vehicle characteristics, as vehicle identification result.

7. entrance vehicle identification method according to claim 2, which is characterized in that the method also includes:

When only one in first vehicle identification information and second vehicle identification information is identified to, and, it is unidentified To vehicle identification information camera recognition time exceed preset time when, according to first vehicle identification being identified to Information or second vehicle identification information export vehicle identification result.

8. a kind of device of entrance vehicle identification characterized by comprising

Image capture module shoots entrance scene for phase unit, obtains initial pictures；

Information of vehicles detection module, detecting for the phase unit whether there is vehicle in the initial pictures；

Car license recognition module, for when detecting that the phase unit is to there are vehicles there are when vehicle in the initial pictures Initial pictures carry out vehicle identification, export vehicle identification result.

9. a kind of system of entrance vehicle identification characterized by comprising Accounting Client, banister, display screen and entrance The device of vehicle identification；

The device of the entrance vehicle identification is connected with the Accounting Client, the banister and the display screen respectively, and, The display screen is connected with the Accounting Client；

First vehicle identification information or second vehicle of the banister in the device output for receiving the entrance vehicle identification It is lifted after identification information；

The Accounting Client calculates the first vehicle identification information that entrance exports or the second vehicle identification information and exports defeated The time interval between the first vehicle identification information or the second vehicle identification information out, and according to the time interval and in advance If unit price calculates Parking Fee；

The display screen is used to show first vehicle identification information, second vehicle identification information and the parking fee With.

10. a kind of terminal, which is characterized in that including memory and processor, the memory supports processor for storing Perform claim requires the program of any one of 1 to 6 the method, the processor is configured to depositing in the memory for executing The program of storage.