A method, device, storage medium and electronic device for identifying unlicensed vehicles

By extracting and matching the vehicle's outline, logo and grayscale feature data, and establishing an identification strategy, the problem of unlicensed vehicles cannot be automatically identified is solved, automatic management is realized, and user experience is improved.

CN118781588BActive Publication Date: 2024-11-19CHENGDU YIBO INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411237736.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-11-19
Estimated Expiration
2044-09-05

AI Technical Summary

Technical Problem

The existing parking lot smart management system cannot automatically identify unlicensed vehicles, resulting in a reduced user experience and requires manual or scan the code through mobile phone to log in for management.

Method used

By obtaining the vehicle's entry image, extracting outline feature data, logo feature data and grayscale feature data, establishing an identification strategy, combining historical entry and exit images to match, and realizing automatic identification and management of unlicensed vehicles.

Benefits of technology

The automatic entry and exit management of unlicensed vehicles is realized, the user experience is improved, manual intervention is avoided, and the system's automated recognition capabilities are enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118781588B_ABST
    Figure CN118781588B_ABST
Patent Text Reader

Abstract

The embodiments of the present application disclose a method, device, storage medium and electronic device for identifying unlicensed vehicles, and relate to the field of vehicle identification technology. The present application uses feature data as identity information of unlicensed vehicles for identification, and no longer relies solely on license plate recognition for management. After the vehicle enters the parking lot, its identity information is identified as the vehicle's contour features, vehicle logo features and grayscale features. The grayscale features are the color of the vehicle. Then, images taken when unlicensed vehicles enter and exit the parking lot in the historical records and feature data on the images are retrieved. By comparing the historical entry images and historical exit images, the feature data with the best current matching degree is selected to determine the corresponding identification strategy, and then the identification features corresponding to the target identification strategy are used to identify the vehicle's exit image, so as to achieve matching of the entry and exit information of unlicensed vehicles, thereby achieving automatic management of unlicensed vehicles and improving the user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle identification technology, and in particular to a method, device, storage medium and electronic device for identifying unlicensed vehicles. Background Art

[0002] The parking lot intelligent management system is a system based on machine vision recognition. A set of entrance and exit management equipment is installed at the entrance and exit of the parking lot, making the parking lot a relatively closed place. When a vehicle enters the lot, the machine vision device recognizes the vehicle's license plate information as the vehicle's identity information, and the information is stored in the management system and the barrier is automatically lifted. When the vehicle leaves the lot, the machine vision device at the exit of the parking lot recognizes the vehicle's license plate information again. By comparing it with the identity information stored when entering the lot, the vehicle's entry and exit time, parking time, fees and other information can be obtained, and the management equipment will automatically lift the barrier and release the vehicle.

[0003] However, some newly purchased vehicles will choose to print temporary license plates in the early stage, and there is no identifiable license plate at the license plate installation site, resulting in the inability to automatically release them at the entrances and exits when they enter and exit the above-mentioned parking lots. Users can only call the management staff to manually lift the barrier, or scan the code with their mobile phones to log in to the management system to register information before the entrance and exit management equipment will release them, which reduces the user experience. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, storage medium and electronic device for identifying unlicensed vehicles, aiming to solve the problem in the prior art that unlicensed vehicles cannot be automatically identified in the vehicle entry and exit management of parking lots.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying an unlicensed vehicle, comprising the following steps:

[0007] According to the entry image of the target vehicle, feature data is obtained; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle;

[0008] Determine the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry images and historical exit images of the unlicensed vehicle;

[0009] When the target vehicle exits, the target recognition feature is confirmed in the feature data according to the target recognition strategy, and the exit image of the target vehicle is recognized according to the target recognition feature.

[0010] In a possible implementation of the first aspect, before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data, and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes:

[0011] Compare the contour feature data, vehicle logo feature data and grayscale feature data in the historical entry images and historical exit images respectively, and establish a recognition strategy;

[0012] Determine your target identification strategy, including:

[0013] Determine the target identification strategy in the identification strategy.

[0014] In a possible implementation manner of the first aspect, before determining the target recognition strategy in the recognition strategy, the method further includes:

[0015] Obtaining a first quantity according to the quantity of matched contour feature data in the historical entry image and the historical exit image;

[0016] Obtaining a second number according to the number of vehicle logo feature data that matches in the historical entry image and the historical exit image;

[0017] Obtaining a third quantity according to the quantity of the grayscale feature data matched in the historical entry image and the historical exit image;

[0018] Determine the target identification strategy in the identification strategy, including:

[0019] An object recognition strategy is determined in the recognition strategy according to a maximum value among the first number, the second number, and the third number.

[0020] In a possible implementation of the first aspect, when the target vehicle exits, after confirming the target recognition feature in the feature data according to the target recognition strategy and recognizing the exit image of the target vehicle according to the target recognition feature, the method further includes:

[0021] In the case where the similarity between the target identification feature and the target vehicle is lower than the similarity threshold, the number of target identification features is increased and the similarity threshold is decreased;

[0022] Determine whether the similarities of the target vehicles identified by the target identification features are not less than the reduced similarity threshold. If the judgment is no, return to the step of increasing the number of target identification features and reducing the similarity threshold when the similarity of the target vehicles identified by the target identification features is lower than the similarity threshold, and loop until the judgment is yes to complete the identification of the target vehicle.

[0023] In a possible implementation of the first aspect, when the target vehicle exits, after confirming the target recognition feature in the feature data according to the target recognition strategy and recognizing the exit image of the target vehicle according to the target recognition feature, the method further includes:

[0024] The feature data in the exit image is obtained, and the exit image and entry image of the target vehicle are added to the historical exit image and the historical entry image respectively.

[0025] In a possible implementation of the first aspect, before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data, and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes:

[0026] According to the edge detection algorithm, the contour feature data in the historical entry images and historical exit images of the unlicensed vehicles are obtained.

[0027] In a possible implementation of the first aspect, before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data, and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes:

[0028] The historical entry images and historical exit images of the unlicensed vehicles are grayed to obtain gray feature data in the historical entry images and historical exit images of the unlicensed vehicles.

[0029] In a second aspect, an embodiment of the present application provides a device for identifying an unlicensed vehicle, comprising:

[0030] An acquisition module, the acquisition module is used to obtain feature data according to the entry image of the target vehicle; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle;

[0031] A determination module, which is used to determine a target recognition strategy based on matching contour feature data, vehicle logo feature data, and grayscale feature data in historical entry images and historical exit images of unlicensed vehicles;

[0032] The recognition module is used to confirm the target recognition features in the feature data according to the target recognition strategy when the target vehicle exits the scene, and recognize the exit image of the target vehicle according to the target recognition features.

[0033] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the method for identifying unlicensed vehicles provided in any one of the first aspects above is implemented.

[0034] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein:

[0035] The memory is used to store computer programs;

[0036] The processor is used to load and execute a computer program so that the electronic device executes the method for identifying an unlicensed vehicle as provided in any one of the first aspects above.

[0037] Compared with the prior art, the beneficial effects of this application are:

[0038] The embodiments of the present application propose a method, device, storage medium and electronic device for identifying unlicensed vehicles. The method includes: obtaining feature data based on an entry image of a target vehicle; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle; determining a target recognition strategy based on the contour feature data, vehicle logo feature data and grayscale feature data that match historical entry images and historical exit images of the unlicensed vehicle; when the target vehicle exits, confirming the target recognition feature in the feature data according to the target recognition strategy, and recognizing the exit image of the target vehicle according to the target recognition feature. This application uses feature data as the identity information of vehicles without license plates to identify them, and no longer relies solely on license plate recognition for management. After a vehicle enters the parking lot, its identity information is identified as the vehicle's contour features, vehicle logo features, and grayscale features. The grayscale features are the color of the vehicle. Then, the images taken when vehicles without license plates enter and exit the parking lot in the historical records and the feature data on the images are retrieved. By comparing the historical entry images and historical exit images, the feature data with the best current matching degree is selected to determine the corresponding recognition strategy, and then the recognition features corresponding to the target recognition strategy are used to identify the vehicle's exit image, thereby achieving matching of the entry and exit information of vehicles without license plates, thereby achieving automatic management of vehicles without license plates, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the structure of an electronic device of a hardware operating environment involved in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of a flow chart of a method for identifying an unlicensed vehicle provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of a flow chart of a method for identifying unlicensed vehicles provided in an embodiment of the present application in one implementation manner;

[0042] Figure 4 A schematic diagram of a module of an unlicensed vehicle identification device provided in an embodiment of the present application;

[0043] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] See attached Figure 1 , attached Figure 1 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0046] Those skilled in the art will appreciate that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0047] As attached Figure 1 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an identification device for unlicensed vehicles.

[0048] In the attached Figure 1 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the unlicensed vehicle identification device stored in the memory 105 through the processor 101, and executes the unlicensed vehicle identification method provided in the embodiment of the present application.

[0049] See attached Figure 2 Based on the hardware device of the aforementioned embodiment, the embodiment of the present application provides a method for identifying an unlicensed vehicle, comprising the following steps:

[0050] S10: obtaining feature data according to the entry image of the target vehicle; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle.

[0051] In the specific implementation process, the target vehicles are the unlicensed vehicles that need to enter and exit the parking lot. For the entry and exit of unlicensed vehicles, the design point is to replace the traditional license plate recognition by building a recognition strategy to identify the vehicle. When the vehicle exits, the feature data before and after can be identified to determine the identity of the vehicle and automatically release it. Therefore, when an unlicensed vehicle enters the parking lot, it only needs to capture the vehicle image through the machine vision device at the entrance, and recognize the feature data and store it as the identity information of the vehicle.

[0052] The contour feature data is the type of vehicle. Through algorithms such as image segmentation, contour detection, and edge detection, the contour of the vehicle on the image can be identified, thereby identifying whether the vehicle is a sedan, SUV, truck, etc. The vehicle logo feature data is the car brand logo on the front hood of the vehicle. When entering and leaving the site, the management equipment takes pictures from the front of the vehicle, so the vehicle logo can be effectively captured. The grayscale feature can be understood as the grayscale value feature after the image is grayed. The grayscale values ​​of different colors of the vehicle are different after graying, and different vehicles will also have different grayscale value distributions. After graying, the interference of light on the image can be reduced, and the color of the vehicle can be effectively identified. After the identification is completed, this information is stored in the management system as the identity information of the vehicle entering the site.

[0053] S20: Determine a target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle.

[0054] In the specific implementation process, the historical entry and exit information of unlicensed vehicles recorded in the management system is called, including historical entry images and historical exit images. If the unlicensed vehicles corresponding to these images are managed using the method provided by this application, then the corresponding contour features, vehicle logo features, and grayscale features on the images are also recorded. If these images are only recorded images, the aforementioned method can be used to identify the images to obtain feature data on the images. That is:

[0055] Before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes:

[0056] According to the edge detection algorithm, the contour feature data in the historical entry images and historical exit images of the unlicensed vehicles are obtained.

[0057] The historical entry images and historical exit images of the unlicensed vehicles are grayed to obtain gray feature data in the historical entry images and historical exit images of the unlicensed vehicles.

[0058] In the specific implementation process, the edge detection algorithm is a commonly used technology in digital image processing, which is used to detect the position of the edge of an object in an image, and then identify the contour features of the object in the image. Grayscale is in the RGB model. If R=G=B, the color represents a grayscale color, where the value of R=G=B is called the grayscale value, that is, the values ​​of the red, green, and blue channels of the color three-channel image are equal. Therefore, each pixel of the grayscale image only needs one byte to store the grayscale value, and the grayscale range is 0-255. In other embodiments, the image of the vehicle logo part can also be separated by image segmentation technology, and then the vehicle logo features can be identified using image comparison technology.

[0059] By comparing the above-mentioned feature data in the historical images, in the presence of other interferences such as light, a strategy with the best matching degree and the best recognition effect is selected for recognition. Before confirmation, the recognition strategy can be established based on the comparison of the feature data, that is, based on the matching contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, before determining the target recognition strategy, the method also includes:

[0060] The contour feature data, vehicle logo feature data and grayscale feature data in the historical entry images and historical exit images are compared respectively to establish a recognition strategy.

[0061] In the specific implementation process, due to the influence of lighting, the individual recognition efficiency of the above features is not the same, so when comparing each feature separately, a corresponding recognition strategy is established, which can be recorded as three strategies. The first is to identify the contour feature when exiting, and the contour feature when exiting is compared with the contour feature when entering; the second is to identify the vehicle logo feature when exiting, and the vehicle logo feature when exiting is compared with the vehicle logo feature when entering; the third is to identify the grayscale feature when exiting, and the grayscale feature when exiting is compared with the grayscale feature when entering.

[0062] Based on the above steps, determine the target identification strategy, including:

[0063] Determine the target identification strategy in the identification strategy.

[0064] In one embodiment, before determining the target recognition strategy in the recognition strategy, the method further includes:

[0065] Obtaining a first quantity according to the quantity of matched contour feature data in the historical entry image and the historical exit image;

[0066] Obtaining a second number according to the number of vehicle logo feature data that matches in the historical entry image and the historical exit image;

[0067] A third quantity is obtained according to the quantity of the matching grayscale feature data in the historical entry image and the historical exit image.

[0068] In the specific implementation process, the management of vehicle entry and exit will record two pieces of information corresponding to the time of entry and exit. Therefore, whether the before and after comparison can match can determine whether the identity of the vehicle can be identified. By comparing the above three features in the historical entry image and the historical exit image, the matching of the features in the entry and exit images can be obtained, that is, whether the identity of the vehicle can be identified based on the feature in the historical image. The three features have three matching numbers respectively, which can respectively represent the matching degree of identification through this feature. The larger the number, the higher the matching degree, indicating that the effect of using this feature for identification is better.

[0069] Based on the above steps, the target identification strategy is determined in the identification strategy, including:

[0070] An object recognition strategy is determined in the recognition strategy according to a maximum value among the first number, the second number, and the third number.

[0071] Therefore, the feature data corresponding to the maximum value among the first number, the second number and the third number is selected as the recognition target, and then the corresponding recognition strategy can be confirmed as the target recognition strategy in the aforementioned recognition strategy.

[0072] S30: When the target vehicle exits, the target recognition feature is confirmed in the feature data according to the target recognition strategy, and the exit image of the target vehicle is recognized according to the target recognition feature.

[0073] In the specific implementation process, when an unlicensed vehicle exits the vehicle, the corresponding features are identified according to the determined recognition strategy, and the features are used as the recognition target to perform corresponding recognition in the vehicle exit image. For example, if the target recognition strategy is the first strategy mentioned above, the corresponding target recognition feature is the contour feature. When the vehicle exits the vehicle, the contour feature in the exit image is identified to determine the identity of the vehicle. After the recognition is completed, the management system automatically lifts the barrier to release the vehicle, thus realizing the automatic recognition and management of unlicensed vehicles.

[0074] In this embodiment, feature data is used as the identity information of vehicles without license plates for identification, and management no longer relies solely on license plate recognition. After a vehicle enters the parking lot, its identity information is identified as the vehicle's contour features, vehicle logo features, and grayscale features. The grayscale features are the color of the vehicle. Then, images taken when vehicles without license plates enter and exit the parking lot in the historical records and feature data on the images are retrieved. By comparing the historical entry images and historical exit images, the feature data with the best current matching degree is selected to determine the corresponding identification strategy, and then the identification features corresponding to the target identification strategy are used to identify the vehicle's exit image, thereby achieving matching of the entry and exit information of vehicles without license plates, thereby achieving automatic management of vehicles without license plates, and improving the user experience.

[0075] In one embodiment, when the similarity between the target identification feature and the target vehicle is lower than the similarity threshold, the number of target identification features is increased and the similarity threshold is decreased;

[0076] Determine whether the similarities of the target vehicles identified by the target identification features are not less than the reduced similarity threshold. If the judgment is no, return to the step of increasing the number of target identification features and reducing the similarity threshold when the similarity of the target vehicles identified by the target identification features is lower than the similarity threshold, and loop until the judgment is yes to complete the identification of the target vehicle.

[0077] In the specific implementation process, in actual use, it is not an absolute 100% complete match when exiting the vehicle. A similarity threshold will be set. For example, under the recognition of the target feature, if the similarity of the previous and subsequent recognitions reaches more than 95%, it can be considered a successful match, and the vehicle identity is confirmed to be consistent and can be released. The aforementioned feature with the highest matching degree is only a relative value, and it cannot determine whether the required recognition rate can be achieved when exiting the vehicle. If the similarity of the selected feature with the highest matching degree does not reach the similarity threshold, you can consider introducing other features to assist in recognition, but you need to reduce the size of the similarity threshold, because the number of vehicles without license plates in the parking lot at the same time is very small. Even if the similarity is reduced, the more features, the more accurately the vehicle can be identified.

[0078] It should be noted that the reduction of the similarity threshold should follow the principle of making the similarity of the previous recognition meet the threshold requirements. For example, based on the above example, the similarity threshold cannot meet the requirements based on the recognition using contour features, and is 85%. Then the vehicle logo feature is introduced for recognition. At this time, the similarity threshold needs to be reduced to at least 85%. It can be reduced to 85% or 80%. For example, 80% is selected and recognized again. When the vehicle logo feature is used for recognition, the similarity is 82%. Then, the reduced similarity threshold of 80% is reached under the recognition of both features. Then the identity match of the vehicle can be determined, and the recognition of the vehicle without a license plate can be completed.

[0079] In one embodiment, when the target vehicle exits, after confirming the target identification feature in the feature data according to the target identification strategy and identifying the exit image of the target vehicle according to the target identification feature, the method further includes:

[0080] The feature data in the exit image is obtained, and the exit image and entry image of the target vehicle are added to the historical exit image and the historical entry image respectively.

[0081] In the specific implementation process, in order to expand the historical data record, after completing the identification of the current vehicle, the feature data in the exit image can be obtained using the method provided in the embodiment of this application, and then the exit image and the entry image are matched and marked and stored in the historical exit image and the historical entry image respectively as the historical data for the next vehicle identification. The feasible samples are continuously enriched, so that the accuracy and efficiency of identification using the method provided in the embodiment of this application are getting higher and higher.

[0082] See attached Figure 3 , in the attached Figure 3 The embodiments of the present application are further described below:

[0083] First, obtain the historical data of unlicensed vehicles entering and leaving the parking lot, and record the total number as N;

[0084] Then compare and match the feature data separately and record the number of matches:

[0085] Identify the contours of the entry and exit images, calculate the eigenvalues, and compare the eigenvalues ​​of the entry and exit images. The total number of matches is recorded as N1, which is the first number. Identify and compare the vehicle logos of the entry and exit images. The total number of vehicle logo matches is recorded as N2, which is the second number. Identify the grayscale eigenvalues ​​of the entry and exit images, and compare the eigenvalues ​​of the entry and exit images. The total number of eigenvalue matches is recorded as N3, which is the third number.

[0086] Finally, the best unlicensed vehicle recognition strategy is selected according to the maximum values ​​of N1, N2 and N3 to realize the identity recognition management of vehicles.

[0087] See attached Figure 4 Based on the same inventive concept as in the above-mentioned embodiment, the embodiment of the present application further provides a device for identifying vehicles without license plates, including:

[0088] An acquisition module, the acquisition module is used to obtain feature data according to the entry image of the target vehicle; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle;

[0089] A determination module, which is used to determine a target recognition strategy based on matching contour feature data, vehicle logo feature data, and grayscale feature data in historical entry images and historical exit images of unlicensed vehicles;

[0090] The recognition module is used to confirm the target recognition features in the feature data according to the target recognition strategy when the target vehicle exits the scene, and recognize the exit image of the target vehicle according to the target recognition features.

[0091] Those skilled in the art should understand that the division of the various modules in the embodiment is merely a division of logical functions, and in actual application, all or part of them can be integrated into one or more actual carriers, and these modules can be implemented entirely in the form of software called by a processing unit, or entirely in the form of hardware, or in the form of a combination of software and hardware. It should be noted that each module in the device for identifying unlicensed vehicles in this embodiment corresponds one-to-one to each step in the method for identifying unlicensed vehicles in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned method for identifying unlicensed vehicles, and will not be repeated here.

[0092] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, a method for identifying unlicensed vehicles as provided in an embodiment of the present application is implemented.

[0093] Based on the same inventive concept as in the above-mentioned embodiment, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein:

[0094] The memory is used to store computer programs;

[0095] The processor is used to load and execute a computer program so that the electronic device executes the method for identifying unlicensed vehicles provided in the embodiment of the present application.

[0096] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0097] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0098] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0099] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0100] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0101] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0103] In summary, the present application provides a method, device, storage medium and electronic device for identifying unlicensed vehicles, the method comprising: obtaining feature data based on an entry image of a target vehicle; wherein the feature data comprises contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle; determining a target recognition strategy based on the contour feature data, vehicle logo feature data and grayscale feature data that match historical entry images and historical exit images of the unlicensed vehicle; when the target vehicle exits, confirming the target recognition feature in the feature data according to the target recognition strategy, and recognizing the exit image of the target vehicle according to the target recognition feature. This application uses feature data as the identity information of vehicles without license plates to identify them, and no longer relies solely on license plate recognition for management. After a vehicle enters the parking lot, its identity information is identified as the vehicle's contour features, vehicle logo features, and grayscale features. The grayscale features are the color of the vehicle. Then, the images taken when vehicles without license plates enter and exit the parking lot in the historical records and the feature data on the images are retrieved. By comparing the historical entry images and historical exit images, the feature data with the best current matching degree is selected to determine the corresponding recognition strategy, and then the recognition features corresponding to the target recognition strategy are used to identify the vehicle's exit image, thereby achieving matching of the entry and exit information of vehicles without license plates, thereby achieving automatic management of vehicles without license plates, and improving the user experience.

[0104] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for identifying unlicensed vehicles, characterized in that: The following steps are involved: According to the entry image of the target vehicle, feature data is obtained; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle; Determine the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry images and historical exit images of the unlicensed vehicle; When the target vehicle exits, the target recognition feature is confirmed in the feature data according to the target recognition strategy, and the exit image of the target vehicle is recognized according to the target recognition feature; when the target vehicle exits, the target recognition feature is confirmed in the feature data according to the target recognition strategy, and the exit image of the target vehicle is recognized according to the target recognition feature, the method further includes: In the case where the similarity between the target identification feature and the target vehicle is lower than a similarity threshold, increasing the number of target identification features and decreasing the similarity threshold; Determine whether the similarities of the target vehicle identified by the target identification features are not less than the reduced similarity threshold. If the judgment is no, return to the step of increasing the number of target identification features and reducing the similarity threshold when the similarity of the target vehicle identified by the target identification features is lower than the similarity threshold, and loop until the judgment is yes to complete the identification of the target vehicle.

2. The method for identifying unlicensed vehicles according to claim 1, characterized in that: Before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes: Respectively comparing the contour feature data, the vehicle logo feature data and the grayscale feature data in the historical entry image and the historical exit image to establish a recognition strategy; The determining of the target identification strategy comprises: A target recognition strategy is determined in the recognition strategy.

3. The method for identifying unlicensed vehicles according to claim 2, characterized in that: Before determining the target recognition strategy in the recognition strategy, the method further includes: Obtaining a first number according to the number of the contour feature data that matches in the historical entry image and the historical exit image; Obtaining a second number according to the number of the vehicle logo feature data that matches in the historical entry image and the historical exit image; Obtaining a third number according to the number of the grayscale feature data that matches in the historical entry image and the historical exit image; Determining the target identification strategy in the identification strategy includes: An object recognition strategy is determined in the recognition strategy according to a maximum value among the first number, the second number, and the third number.

4. The method for identifying unlicensed vehicles according to claim 1, characterized in that: When the target vehicle exits, after confirming the target identification feature in the feature data according to the target identification strategy and identifying the exit image of the target vehicle according to the target identification feature, the method further includes: The feature data in the exit image is obtained, and the exit image and the entry image of the target vehicle are added to the historical exit image and the historical entry image respectively.

5. The method for identifying unlicensed vehicles according to claim 1, characterized in that: Before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes: According to the edge detection algorithm, the contour feature data in the historical entry image and the historical exit image of the unlicensed vehicle is obtained.

6. The method for identifying unlicensed vehicles according to claim 1, characterized in that: Before determining the target recognition strategy based on the matched contour feature data, vehicle logo feature data and grayscale feature data in the historical entry image and the historical exit image of the unlicensed vehicle, the method further includes: The historical entry images and the historical exit images of the unlicensed vehicle are grayed to obtain the gray feature data in the historical entry images and the historical exit images of the unlicensed vehicle.

7. A device for identifying unlicensed vehicles, characterized in that: include: An acquisition module, the acquisition module is used to obtain feature data according to the entry image of the target vehicle; wherein the feature data includes contour feature data, vehicle logo feature data and grayscale feature data of the target vehicle; A determination module, the determination module is used to determine a target recognition strategy based on matching contour feature data, vehicle logo feature data and grayscale feature data in historical entry images and historical exit images of unlicensed vehicles; A recognition module, wherein the recognition module is used to confirm the target recognition feature in the feature data according to the target recognition strategy when the target vehicle exits, and recognize the exit image of the target vehicle according to the target recognition feature; after confirming the target recognition feature in the feature data according to the target recognition strategy when the target vehicle exits, and recognizing the exit image of the target vehicle according to the target recognition feature, the recognition module further includes: In the case where the similarity between the target identification feature and the target vehicle is lower than a similarity threshold, increasing the number of target identification features and decreasing the similarity threshold; Determine whether the similarities of the target vehicle identified by the target identification features are not less than the reduced similarity threshold. If the judgment is no, return to the case where the similarity of the target vehicle identified by the target identification features is lower than the similarity threshold, increase the number of target identification features, and reduce the similarity threshold, and loop until the judgment is yes to complete the identification of the target vehicle.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by a processor, the method for identifying an unlicensed vehicle as described in any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is used to load and execute the computer program so that the electronic device executes the method for identifying an unlicensed vehicle as described in any one of claims 1-6.