License plate recognition method, device and equipment, and storage medium

Abstract

The application discloses a license plate recognition method, device and equipment and a storage medium, and is applied to the field of image recognition. The license plate recognition method comprises the following steps: acquiring a license plate image captured by a camera on a vehicle bottom detection robot; acquiring image preprocessing parameters corresponding to the type of the camera in an image preprocessing parameter library according to the type of the camera, wherein the image preprocessing parameters comprise camera calibration parameters and perspective transformation parameters, the camera calibration parameters comprise internal and external parameters and distortion coefficients of the camera; preprocessing the license plate image according to the image preprocessing parameters corresponding to the type of the camera to obtain a processed image, so that the edges of the license plate in the license plate image are straight and the shooting angle of the license plate image is improved; and performing license plate recognition based on the processed image; and the image preprocessing parameter library comprises image preprocessing parameters corresponding to various types of cameras. The license plate recognition accuracy can be improved.

Description

Technical Field

[0001] This application belongs to the field of image recognition, and in particular relates to a license plate recognition method, device, equipment and storage medium. Background Technology

[0002] The vehicle undercarriage inspection robot is used to conduct safety inspections on the vehicle chassis. It features small size, retractability, portability, wide inspection range, strong environmental adaptability, and clear image transmission.

[0003] When inspecting the undercarriage of a vehicle, the vehicle inspection robot can capture images of the license plate for license plate recognition. However, because the vehicle inspection robot is close to the ground, the license plate recognition camera mounted on it has a large shooting angle and a tilted view, which reduces the accuracy of license plate detection and recognition. In addition, the camera itself may be a wide-angle camera, which has a certain degree of distortion. Therefore, the accuracy of the captured images used directly for license plate recognition is low, and the effect is poor. Summary of the Invention

[0004] This application provides a license plate recognition method, apparatus, device, and storage medium that can improve the accuracy of license plate recognition.

[0005] In a first aspect, embodiments of this application provide a license plate recognition method, the method comprising:

[0006] Acquire license plate images captured by the camera on the under-vehicle inspection robot;

[0007] Based on the type of camera, obtain the image preprocessing parameters corresponding to the type of camera from the image preprocessing parameter library. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients.

[0008] The license plate image is preprocessed according to the image preprocessing parameters corresponding to the camera type to obtain the processed image, so as to make the license plate edge in the license plate image straight and improve the shooting angle of the license plate image;

[0009] License plate recognition based on the processed image;

[0010] The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras.

[0011] In some embodiments of this application, the license plate image is preprocessed according to the image preprocessing parameters corresponding to the type of camera to obtain a preprocessed image, including:

[0012] The license plate image is processed according to the camera calibration parameters to obtain the first license plate image;

[0013] The first license plate image is processed according to the perspective transformation parameters to obtain the second license plate image;

[0014] The second license plate image was identified as the preprocessed image.

[0015] In some embodiments of this application, the first license plate image is processed according to perspective transformation parameters to obtain the second license plate image, including:

[0016] Based on the perspective transformation parameters, the shooting angle of the first license plate image is increased to obtain the second license plate image.

[0017] In some embodiments of this application, before acquiring the license plate image captured by the camera on the robot under the vehicle, the method further includes:

[0018] For each type of camera among various types, the camera is calibrated according to a preset calibration method to obtain the corresponding camera calibration parameters. The camera is a camera installed on the under-vehicle inspection robot.

[0019] Multiple third-party license plate images were obtained by using a camera to capture license plate images;

[0020] Multiple third license plate images are processed based on camera calibration parameters to obtain multiple fourth license plate images;

[0021] Perspective transformation is performed on multiple fourth license plate images to improve the shooting angle of the license plate images and obtain the corresponding perspective transformation parameters;

[0022] An image preprocessing parameter library is generated based on the camera calibration parameters and perspective transformation parameters corresponding to various types of cameras.

[0023] In some embodiments of this application, the preset calibration method includes any one of Zhang's calibration method, Tsai's two-step method, camera calibration method based on active vision, and hierarchical stepwise calibration method.

[0024] In some embodiments of this application, various types of cameras include telephoto cameras, standard cameras, wide-angle cameras, ultra-wide-angle cameras, and fisheye cameras.

[0025] Secondly, embodiments of this application provide a license plate recognition device, the device comprising:

[0026] The first acquisition module is used to acquire license plate images captured by the camera on the under-vehicle inspection robot;

[0027] The second acquisition module is used to acquire image preprocessing parameters corresponding to the type of camera from the image preprocessing parameter library. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients.

[0028] The preprocessing module is used to preprocess the license plate image according to the image preprocessing parameters corresponding to the type of camera, so as to make the license plate edge in the license plate image straight and improve the shooting angle of the license plate image.

[0029] The recognition module is used for license plate recognition based on the processed image;

[0030] The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras.

[0031] In some embodiments of this application, the preprocessing module includes:

[0032] The first preprocessing module is used to process the license plate image according to the camera calibration parameters to obtain the first license plate image;

[0033] The second preprocessing module is used to process the first license plate image according to the perspective transformation parameters to obtain the second license plate image;

[0034] The determination module is used to determine the second license plate image as the preprocessed image.

[0035] Thirdly, embodiments of this application provide a license plate recognition device, which includes: a processor and a memory storing computer program instructions;

[0036] The license plate recognition method of any of the above embodiments is implemented when the processor executes computer program instructions.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the license plate recognition method of any of the above embodiments.

[0038] According to the license plate recognition method, apparatus, device, and storage medium of the embodiments of this application, since the image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras, the image preprocessing parameters of the target type camera can be quickly obtained according to the image preprocessing parameter library, and the license plate image can be preprocessed according to the image preprocessing parameters. The preprocessed license plate image eliminates the influence of camera and shooting angle factors, and license plate recognition based on the preprocessed license plate image can improve the accuracy of license plate recognition. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of the first process of the license plate recognition method provided in the embodiments of this application;

[0041] Figure 2 This is a second flowchart illustrating the license plate recognition method provided in the embodiments of this application;

[0042] Figure 3 This is a schematic diagram of a third process for a license plate recognition method provided in an embodiment of this application;

[0043] Figure 4 This is a schematic diagram of the license plate recognition device provided in the embodiments of this application;

[0044] Figure 5 This is a schematic diagram of the license plate recognition device provided in an embodiment of this application. Detailed Implementation

[0045] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0046] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0047] The vehicle undercarriage inspection robot is used to conduct safety inspections on the vehicle chassis. It features small size, retractability, portability, wide inspection range, strong environmental adaptability, and clear image transmission.

[0048] When inspecting the undercarriage of a vehicle, the vehicle inspection robot can capture images of the license plate for license plate recognition. However, because the vehicle inspection robot is close to the ground, the license plate recognition camera mounted on it has a large shooting angle and a tilted view, which reduces the accuracy of license plate detection and recognition. In addition, the camera itself may be a wide-angle camera, which has a certain degree of distortion. Therefore, the accuracy of the captured images used directly for license plate recognition is low, and the effect is poor.

[0049] To address the aforementioned technical issues, this application provides a license plate recognition method, apparatus, device, and storage medium. The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. The image preprocessing parameters of the target type camera can be quickly obtained from the image preprocessing parameter library, and the license plate image can be preprocessed according to the image preprocessing parameters. The preprocessed license plate image eliminates the influence of camera and shooting angle factors. License plate recognition based on the preprocessed license plate image can improve the accuracy of license plate recognition.

[0050] Figure 1 This is a schematic diagram of the first process of the license plate recognition method provided in the embodiments of this application;

[0051] Below, in conjunction with Figure 1 This application introduces a license plate recognition method according to embodiments of the present application. The license plate recognition method includes:

[0052] S110, acquire license plate images captured by the camera on the under-vehicle inspection robot;

[0053] S120: Based on the type of camera, obtain the image preprocessing parameters corresponding to the type of camera from the image preprocessing parameter library. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients.

[0054] S130 preprocesses the license plate image according to the image preprocessing parameters corresponding to the camera type to obtain the processed image, so as to make the license plate edge in the license plate image straight and improve the shooting angle of the license plate image;

[0055] S140, performs license plate recognition based on the processed image;

[0056] The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras.

[0057] According to the license plate recognition method provided in the embodiments of this application, the image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. The image preprocessing parameters of the target type camera can be quickly obtained according to the image preprocessing parameter library, and the license plate image is preprocessed according to the image preprocessing parameters. The preprocessed license plate image eliminates the influence of camera and shooting angle factors. License plate recognition based on the preprocessed license plate image can improve the accuracy of license plate recognition.

[0058] Regarding the S110 mentioned above, the under-vehicle inspection robot uses a scanning camera to image the vehicle's chassis. Users can control the robot via a smart wireless control terminal to view the entire chassis image and real-time footage, facilitating the timely detection of illegal activities such as concealed objects or modifications under the vehicle. Therefore, license plate images captured by the camera can be obtained through the smart wireless control terminal.

[0059] Regarding S120 above, the image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. These various types of cameras include multiple types such as telephoto cameras, standard cameras, wide-angle cameras, ultra-wide-angle cameras, and fisheye cameras, and may also include other types of cameras. No limitation is made here. The image preprocessing parameter library stores the image preprocessing parameters corresponding to these types of cameras. Therefore, the corresponding image preprocessing parameters can be obtained from the image preprocessing parameter library according to the type of camera.

[0060] The image preprocessing parameter library provides image transmission formats such as cv::mat, binary, and base64 for easy access.

[0061] Image preprocessing parameters include camera calibration parameters and perspective transformation parameters. Camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients. The camera calibration parameters are primarily used to correct license plate images, straightening wavy lines, while the perspective transformation parameters are mainly used to raise the shooting angle of the license plate image.

[0062] Regarding S130 above, once the image preprocessing parameters corresponding to the camera type are obtained, these parameters can be used to preprocess the license plate image. Specifically, the processed image is obtained by transforming the coordinates of the pixels in the image through a calibration parameter matrix and a perspective transformation matrix.

[0063] Regarding S140 above, the preprocessed license plate image eliminates the influence of camera and shooting angle factors, and license plate recognition based on the preprocessed license plate image can improve the accuracy of license plate recognition.

[0064] Figure 2 This is a second flowchart illustrating the license plate recognition method provided in the embodiments of this application;

[0065] In some embodiments of this application, combined with Figure 2 The license plate image is preprocessed according to the image preprocessing parameters corresponding to the camera type to obtain the preprocessed image, including:

[0066] S210, The license plate image is processed according to the camera calibration parameters to obtain the first license plate image;

[0067] Specifically, the camera calibration parameters are a matrix consisting of an intrinsic parameter matrix, an extrinsic parameter matrix, and a distortion coefficient multiplied together. After transforming the coordinates of the pixels in the license plate image through the matrix, the first license plate image can be obtained.

[0068] S220, The first license plate image is processed according to the perspective transformation parameters to obtain the second license plate image;

[0069] The perspective transformation parameter is a matrix. By transforming the coordinates of the pixels in the license plate image according to the perspective transformation matrix, a second license plate image can be obtained.

[0070] In some embodiments of this application, S220 includes: increasing the shooting angle of the first license plate image according to perspective transformation parameters to obtain a second license plate image.

[0071] S230, the second license plate image is identified as the preprocessed image.

[0072] Figure 3 This is a schematic diagram of a third process for a license plate recognition method provided in an embodiment of this application;

[0073] In some embodiments of this application, combined with Figure 3 Before acquiring the license plate image captured by the camera on the robot under the vehicle, the method also includes:

[0074] S310 calibrates each type of camera according to a preset calibration method to obtain the corresponding camera calibration parameters. The camera is a camera installed on the under-vehicle inspection robot.

[0075] Specifically, the various types of cameras include multiple types such as telephoto cameras, standard cameras, wide-angle cameras, ultra-wide-angle cameras, and fisheye cameras, and may also be other types of cameras, without limitation. The preset calibration method includes any one of Zhang's calibration method, Tsai's two-step method, active vision-based camera calibration method, and hierarchical stepwise calibration method. Other calibration methods in this field may also be used, without limitation.

[0076] The S320 uses a camera to capture images of license plates, obtaining multiple images of third-party license plates.

[0077] Specifically, for each type of camera, the camera is used to capture license plate images to obtain multiple third license plate images. At this time, the captured images have a certain degree of distortion, and the shooting angle is large and the viewing angle is tilted.

[0078] S330 processes multiple third license plate images based on camera calibration parameters to obtain multiple fourth license plate images;

[0079] Specifically, the coordinates of the pixels in the third image are transformed according to the camera calibration matrix, and the image is corrected to straighten the wavy lines in the image, thus obtaining the fourth license plate image.

[0080] S340 performs perspective transformation processing on multiple fourth license plate images to improve the shooting angle of the license plate images and obtain the corresponding perspective transformation parameters;

[0081] Specifically, the coordinates of the pixels in the fourth license plate image are transformed to raise the shooting angle of the image, correct the license plate area to make the edges horizontal and vertical, so that the image looks close to being shot at a horizontal angle, and obtain the corresponding perspective transformation parameters.

[0082] The S350 generates an image preprocessing parameter library based on the camera calibration parameters and perspective transformation parameters corresponding to various types of cameras.

[0083] Specifically, after obtaining the camera calibration parameters and perspective transformation parameters corresponding to each type of camera, the camera type and its corresponding camera calibration parameters and perspective transformation parameters are associated and stored together in the image preprocessing parameter library. This facilitates the rapid determination of the corresponding image preprocessing parameters based on the camera type, thereby preprocessing the image, eliminating the influence of camera and shooting angle factors, and improving the accuracy of license plate recognition.

[0084] Figure 4 This is a schematic diagram of the license plate recognition device provided in the embodiments of this application;

[0085] Below, in conjunction with Figure 4 This application introduces a license plate recognition device according to an embodiment of the present application. The license plate recognition device includes:

[0086] The first acquisition module 401 is used to acquire license plate images captured by the camera on the undercarriage inspection robot;

[0087] The second acquisition module 401 is used to acquire image preprocessing parameters corresponding to the type of camera from the image preprocessing parameter library according to the type of camera. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the intrinsic and extrinsic parameters and distortion coefficients of the camera.

[0088] The preprocessing module 403 is used to preprocess the license plate image according to the image preprocessing parameters corresponding to the type of camera, so as to make the license plate edge in the license plate image straight and improve the shooting angle of the license plate image.

[0089] Recognition module 404 is used for license plate recognition based on the processed image;

[0090] The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras.

[0091] In some embodiments of this application, the preprocessing module 403 includes:

[0092] The first preprocessing module is used to process the license plate image according to the camera calibration parameters to obtain the first license plate image;

[0093] The second preprocessing module is used to process the first license plate image according to the perspective transformation parameters to obtain the second license plate image;

[0094] The determination module is used to determine the second license plate image as the preprocessed image.

[0095] In some embodiments of this application, the second preprocessing module is specifically used for:

[0096] Based on the perspective transformation parameters, the shooting angle of the first license plate image is increased to obtain the second license plate image.

[0097] In some embodiments of this application, the license plate recognition device further includes a parameter library generation module, used for:

[0098] For each type of camera among various types, the camera is calibrated according to a preset calibration method to obtain the corresponding camera calibration parameters. The camera is a camera installed on the under-vehicle inspection robot.

[0099] Multiple third-party license plate images were obtained by using a camera to capture license plate images;

[0100] Multiple third license plate images are processed based on camera calibration parameters to obtain multiple fourth license plate images;

[0101] Perspective transformation is performed on multiple fourth license plate images to improve the shooting angle of the license plate images and obtain the corresponding perspective transformation parameters;

[0102] An image preprocessing parameter library is generated based on the camera calibration parameters and perspective transformation parameters corresponding to various types of cameras.

[0103] In some embodiments of this application, the preset calibration method includes any one of Zhang's calibration method, Tsai's two-step method, camera calibration method based on active vision, and hierarchical stepwise calibration method.

[0104] In some embodiments of this application, various types of cameras include telephoto cameras, standard cameras, wide-angle cameras, ultra-wide-angle cameras, and fisheye cameras.

[0105] According to the license plate recognition device of this application embodiment, the image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. The image preprocessing parameters of the target type camera can be quickly obtained according to the image preprocessing parameter library, and the license plate image can be preprocessed according to the image preprocessing parameters. The preprocessed license plate image eliminates the influence of camera and shooting angle factors. License plate recognition based on the preprocessed license plate image can improve the license plate recognition accuracy.

[0106] Figure 5 This is a schematic diagram of the license plate recognition device provided in an embodiment of this application.

[0107] The license plate recognition device may include a processor 501 and a memory 502 storing computer program instructions.

[0108] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0109] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.

[0110] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0111] The processor 501 implements the license plate recognition method in the above embodiments by reading and executing computer program instructions stored in the memory 502.

[0112] In one example, the license plate recognition device may also include a communication interface 503 and a bus 510. For example, Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0113] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0114] Bus 510 includes hardware, software, or both, that couples components of the payment device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0115] The license plate recognition device executes the license plate recognition method in the embodiments of this application, thereby achieving... Figure 1 Figure 2 and Figure 3 The license plate recognition method shown.

[0116] Furthermore, in conjunction with the license plate recognition methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the license plate recognition methods in the above embodiments.

[0117] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0118] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0119] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0120] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0121] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A license plate recognition method, characterized in that, The method includes: Acquire license plate images captured by the camera on the under-vehicle inspection robot; Based on the type of camera, image preprocessing parameters corresponding to the type of camera are obtained from the image preprocessing parameter library. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients. The license plate image is preprocessed according to the image preprocessing parameters corresponding to the type of camera to obtain a processed image, so as to make the edges of the license plate in the license plate image straight and improve the shooting angle of the license plate image; License plate recognition is performed based on the processed image; The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. The step of preprocessing the license plate image according to the image preprocessing parameters corresponding to the type of camera to obtain the preprocessed image includes: The license plate image is processed according to the camera calibration parameters to obtain a first license plate image; The first license plate image is processed according to the perspective transformation parameters to obtain the second license plate image; The second license plate image is identified as the preprocessed image; Before acquiring the license plate image captured by the camera on the robot under the vehicle, the method further includes: For each type of camera among various types, the camera is calibrated according to a preset calibration method to obtain the corresponding camera calibration parameters. The camera is a camera installed on the under-vehicle inspection robot. Multiple third-party license plate images were obtained by using a camera to capture license plate images; The multiple third license plate images are processed according to the camera calibration parameters to obtain multiple fourth license plate images; Perspective transformation processing is performed on the multiple fourth license plate images to improve the shooting angle of the license plate images and obtain the corresponding perspective transformation parameters; The image preprocessing parameter library is generated based on the camera calibration parameters and perspective transformation parameters corresponding to various types of cameras.

2. The method according to claim 1, characterized in that, The step of processing the first license plate image according to the perspective transformation parameters to obtain the second license plate image includes: Based on the perspective transformation parameters, the shooting angle of the first license plate image is increased to obtain the second license plate image.

3. The method according to claim 1, characterized in that, The preset calibration method includes any one of the following: Zhang's calibration method, Tsai's two-step method, camera calibration method based on active vision, and hierarchical stepwise calibration method.

4. The method according to claim 1, characterized in that, The various types of cameras include telephoto cameras, standard cameras, wide-angle cameras, ultra-wide-angle cameras, and fisheye cameras.

5. A license plate recognition device, characterized in that, The device includes: The first acquisition module is used to acquire license plate images captured by the camera on the under-vehicle inspection robot; The second acquisition module is used to acquire, according to the type of the camera, image preprocessing parameters corresponding to the type of the camera from the image preprocessing parameter library. The image preprocessing parameters include camera calibration parameters and perspective transformation parameters. The camera calibration parameters include the camera's intrinsic and extrinsic parameters and distortion coefficients. The preprocessing module is used to preprocess the license plate image according to the image preprocessing parameters corresponding to the type of the camera, so as to make the license plate edge in the license plate image straight and improve the shooting angle of the license plate image; The recognition module is used to perform license plate recognition based on the processed image; The image preprocessing parameter library includes image preprocessing parameters corresponding to various types of cameras. The preprocessing module includes: The first preprocessing module is used to process the license plate image according to the camera calibration parameters to obtain the first license plate image; The second preprocessing module is used to process the first license plate image according to the perspective transformation parameters to obtain the second license plate image; The determining module is used to determine the second license plate image as the preprocessed image; The device further includes: The parameter library generation module is used to calibrate each type of camera (the camera mounted on the under-vehicle robot) according to a preset calibration method before acquiring the license plate image captured by the camera on the robot. This calibrates the camera to obtain corresponding camera calibration parameters. The camera is used to capture license plate images, resulting in multiple third license plate images. These images are then processed according to the camera calibration parameters to obtain multiple fourth license plate images. Perspective transformation is applied to these fourth license plate images to improve the shooting angle of the license plate images, and corresponding perspective transformation parameters are obtained. Finally, the image preprocessing parameter library is generated based on the camera calibration parameters and perspective transformation parameters corresponding to the various types of cameras.

6. A license plate recognition device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the license plate recognition method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the license plate recognition method as described in any one of claims 1 to 4.

Images