A license plate recognition method, device, equipment and storage medium
By using the combination of basic image parameters and reference image parameters in the license plate recognition system, using vehicle driving direction and time period information, the problem of poor license plate recognition effect in strong backlight environments is solved, and the accuracy and stability of license plate recognition are improved sex.
Patent Information
- Application Number
- CN201911235756.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-12-05
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2039-12-05
AI Technical Summary
In a strong backlight environment, it is difficult for existing license plate recognition technology to effectively adjust image parameters, resulting in poor license plate recognition effect. Especially when the light intensity changes, the preset brightness threshold cannot be adapted, resulting in a decrease in the accuracy of license plate recognition.
Basic image parameters are used to collect basic frame images, and reference frame images are collected simultaneously using the backlight or backlight image parameters when they are not recognized. Single frame image groups are obtained through dual shutters, and reference images are determined using vehicle driving direction and time period information. Parameters to ensure effective license plate recognition in a strong backlight environment.
The license plate recognition rate in a strong backlight environment is improved, the defect of unrecognizable basic frame images is compensated, and the accuracy and stability of license plate recognition are ensured.
Smart Images

Figure CN112926560B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of image processing technology, and in particular to a license plate recognition method, device, equipment and storage medium. Background Art
[0002] License plate recognition is involved in application scenarios such as parks, ordinary roads and highways, and the requirements for the accuracy of license plate recognition are getting higher and higher. However, when the light intensity of the detection environment changes, the recognition result of the license plate will be affected to a certain extent.
[0003] In the prior art, a brightness threshold is usually set in advance, and the regional brightness of a specific area is compared with the preset brightness threshold. The image parameters are continuously adjusted according to the comparison result until the brightness of the area matches the preset brightness threshold, thereby ensuring the image effect in different light intensity environments, so as to recognize the license plate in the image.
[0004] However, when the image parameters are dynamically adjusted as described above, the adjustment range of the image parameters is limited. When the image parameters are adjusted to the upper limit value in a strong forward or backward lighting scene, the image effect is still poor, resulting in poor license plate recognition effect. In addition, if the license plate position is specified to perform regional brightness statistics for a specific area, when there are few vehicles passing by, the image parameter compensation value calculated under normal circumstances will no longer be applicable when a vehicle passes by again in a strong forward or backward lighting scene after a long time interval, resulting in poor image quality and affecting the license plate recognition effect. Summary of the invention
[0005] The present application provides a license plate recognition method, device, equipment and storage medium, so as to improve the license plate recognition rate in strong forward and backlight scenes.
[0006] In a first aspect, an embodiment of the present application provides a license plate recognition method, which is applied to an image acquisition device, comprising:
[0007] When basic frame image acquisition is performed using basic image parameters, a license plate recognition result determined according to the reference frame image is obtained as a target recognition result;
[0008] When the license plate recognition result cannot be obtained according to the basic frame image, the synchronously acquired reference frame image is processed to obtain the license plate recognition result;
[0009] The reference image parameters include front-light image parameters or back-light image parameters.
[0010] In a second aspect, the embodiment of the present application further provides a license plate recognition device, which is configured in an image acquisition device, and includes:
[0011] An image acquisition module, used for synchronously acquiring reference frame images using reference image parameters while acquiring basic frame images using basic image parameters;
[0012] A license plate recognition module, used to obtain a license plate recognition result determined according to the reference frame image as a target recognition result when a license plate recognition result cannot be obtained according to the basic frame image;
[0013] The reference image parameters include front-light image parameters or back-light image parameters.
[0014] In a third aspect, the embodiment of the present application further provides an image acquisition device, including:
[0015] one or more processors;
[0016] A memory for storing one or more programs;
[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement a license plate recognition method as provided in the first aspect embodiment.
[0018] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a license plate recognition method as provided in the embodiment of the first aspect.
[0019] The embodiment of the present application uses reference image parameters including front-lit image parameters or back-lit image parameters to simultaneously acquire reference frame images when using basic image parameters to acquire basic frame images; when the license plate recognition result cannot be obtained based on the basic frame image, the license plate recognition result determined based on the reference frame image is obtained as the target recognition result. The above technical solution uses the reference frame image acquired by the reference image parameters to perform license plate recognition in strong front-lit and back-lit environments, thereby making up for the defect that the basic frame image cannot perform license plate recognition, thereby improving the license plate recognition rate in strong front-lit and back-lit environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 is a flow chart of a license plate recognition method in Embodiment 1 of the present application;
[0021] Figure 2 is a flow chart of a license plate recognition method in Embodiment 2 of the present application;
[0022] Figure 3 is a flow chart of a license plate recognition method in Embodiment 3 of the present application;
[0023] Figure 4 is a structural diagram of a license plate recognition device in Embodiment 4 of the present application;
[0024] Figure 5 It is a structural diagram of an image acquisition device in Example 5 of the present application. DETAILED DESCRIPTION
[0025] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.
[0026] Embodiment 1
[0027] Figure 1 It is a flow chart of a license plate recognition method in Example 1 of the present application. The embodiment of the present application is applicable to the situation where the license plate of a moving vehicle is recognized in a strong forward or backlight environment. The method is executed by a license plate recognition device, which is implemented by software and / or hardware and is specifically configured in an electronic device with certain data computing capabilities. The electronic device can be an image acquisition device with an image acquisition function.
[0028] like Figure 1 A license plate recognition method shown includes:
[0029] S110. When basic image parameters are used to acquire basic frame images, reference image parameters are used to acquire reference frame images simultaneously; wherein the reference image parameters include front-light image parameters or back-light image parameters.
[0030] Among them, the basic image parameters can be the default parameters when performing image acquisition, which are used to acquire basic frame images in a non-strong forward or backward lighting environment. The acquired basic frame images can effectively perform license plate recognition in a non-strong forward or backward lighting environment.
[0031] Among them, the reference image parameters can be front-light image parameters, which are used to acquire images in a strong front-light environment. The acquired reference frame image avoids overexposure, so license plate recognition can be effectively performed; the reference image parameters can also be strong backlight image parameters, which are used to acquire images in a strong backlight environment. The acquired reference frame image avoids overdarkness, so license plate recognition can be effectively performed.
[0032] It should be understood that, since the basic frame image and the reference frame image are collected synchronously, during the single-frame recognition process, a single-frame image group including the basic frame image and the reference frame image is obtained by double-shutter capture.
[0033] S120. When a license plate recognition result cannot be obtained according to the basic frame image, a license plate recognition result determined according to the reference frame image is obtained as a target recognition result.
[0034] It is understandable that due to the differences in the time intervals of the front-light environment and the back-light environment corresponding to different months of each year, different dates of each month, and different times of each day, and due to the influence of weather, there are also differences in the intensity level limits in different environments. Therefore, it is impossible to accurately define which time period is suitable for using the basic frame image in the single-frame image group for license plate recognition, and which time period is suitable for using the reference frame image in the single-frame image group for license plate recognition.
[0035] In order to ensure that the license plate can be effectively recognized for each moving vehicle and reduce the occurrence of missed license plate recognition, the embodiment of the present application determines the license plate recognition result based on the basic frame image and the reference frame image respectively, and when the license plate recognition result cannot be obtained based on the basic frame image, the license plate recognition result determined based on the reference frame image is obtained as the target recognition result. Optionally, when the license plate recognition result is obtained based on the basic frame image, the license plate recognition result determined based on the basic frame image is obtained as the target recognition result.
[0036] It is understandable that in order to reduce the time taken to determine the target recognition result, the determination of the license plate recognition result based on the basic frame image and the determination of the license plate recognition result based on the reference frame image are implemented in a parallel execution manner.
[0037] The embodiment of the present application uses reference image parameters including front-lit image parameters or back-lit image parameters to simultaneously acquire reference frame images when using basic image parameters to acquire basic frame images; when the license plate recognition result cannot be obtained based on the basic frame image, the license plate recognition result determined based on the reference frame image is obtained as the target recognition result. The above technical solution uses the reference frame image acquired by the reference image parameters to perform license plate recognition in strong front-lit and back-lit environments, thereby making up for the defect that the basic frame image cannot perform license plate recognition, thereby improving the license plate recognition rate in strong front-lit and back-lit environments.
[0038] Embodiment 2
[0039] Figure 2 It is a flow chart of a license plate recognition method in Example 2 of the present application. The embodiment of the present application is optimized and improved on the basis of the technical solutions of the above embodiments.
[0040] Furthermore, the operation of "using reference image parameters to acquire reference frame images" is refined into "determining the parameter type of the reference image parameters used in the current first granularity time period according to the vehicle driving direction information; wherein the parameter type is a front-light type or a back-light type; retrieving the reference image parameters of the parameter type to acquire reference frame images" to improve the reference image parameter determination mechanism.
[0041] like Figure 2 A license plate recognition method shown includes:
[0042] S210. Determine, according to the vehicle driving direction information, a parameter type of a reference image parameter used in a current first granularity time period; wherein the parameter type is a front-light type or a back-light type.
[0043] Exemplarily, the current first granularity time period may be the time period of the day, such as 00:00-12:00.
[0044] The vehicle driving direction information may be the direction in which the vehicle is traveling toward the image acquisition device. For example, in a scenario where an image acquisition device is installed at the gate of a park and license plate recognition is performed on vehicles entering the park, the vehicle driving direction information may be the vehicle's entry direction. In a scenario where license plate recognition is performed on vehicles leaving the park, the vehicle driving direction information may be the vehicle's exit direction. Exemplarily, the vehicle driving direction information includes direction information such as "from east to west", "from west to east", "from south to north" and "from north to south".
[0045] In an optional implementation of an embodiment of the present application, the parameter type of the reference image parameter used in the first granularity time period before the current year is determined based on the vehicle driving direction information, which can be: based on the correspondence between the preset vehicle driving direction, the first granularity time information and the parameter type of the reference image parameter, the parameter type of the reference image parameter used in the current first granularity time period is determined.
[0046] It is understandable that, in order to facilitate the management of vehicle driving direction information, the vehicle driving direction information can be simplified into four direction information: "from east to west", "from west to east", "from south to north" and "from north to south". Specifically, the direction from 45° north by east to 45° south by east is collectively referred to as "east"; the direction from 45° north by east to 45° north by west is collectively referred to as "north"; the direction from 45° north by west to 45° south by west is collectively referred to as "west"; the direction from 45° south by west to 45° south by east is usually "east".
[0047] Exemplarily, if the vehicle's driving direction is "from east to west" and belongs to the time period of 00:00-12:00, the parameter type of the reference image parameters is determined to be a backlight type; if the vehicle's driving direction is "from east to west" and belongs to the time period of 12:00-24:00, the parameter type of the reference image parameters is determined to be a frontlight type; if the vehicle's driving direction is "from west to east" and belongs to the time period of 00:00-12:00, the parameter type of the reference image parameters is determined to be a frontlight type; if the vehicle's driving direction is "from west to east" and belongs to the time period of 12:00-24:00, the parameter type of the reference image parameters is determined to be a backlight type; if the vehicle's driving direction is "from south to north" or "from north to south", regardless of any time period, the parameter type of the reference image parameters can be selected arbitrarily, or the reference image parameters can also be replaced with basic image parameters.
[0048] In an optional implementation of the embodiment of the present application, before determining the parameter type of the reference image parameter used in the current first granularity time period according to the vehicle driving direction information, it is also possible to: determine the current time information according to the timing device built into the image acquisition device, and determine the current first granularity time period according to the current time information; send a time information acquisition request to the timing server, and determine the current first granularity time period according to the current time information fed back by the timing server based on the time information acquisition request. Among them, the current first granularity time period can be set by the technician according to needs or experience values, or repeatedly determined through a large number of experiments. Exemplarily, the current first granularity time period is the 00:00-12:00 time period, or the 12:00-24:00 time period.
[0049] In an optional implementation of the embodiment of the present application, before determining the parameter type of the reference image parameter used in the current first granularity time period according to the vehicle driving direction information, the vehicle driving direction information may also be determined.
[0050] Optionally, the vehicle driving direction information can be pre-configured directly when the image acquisition device is installed according to the installation location and shooting requirements, and the configured vehicle driving direction information can be acquired when needed.
[0051] Alternatively, the vehicle driving direction information can also be determined by identifying the road sign information in the reference frame image. For example, at a traffic road intersection, road signs are generally set up, such as "×× Road" or "×× Street". On both sides of the road sign, there are also signs with opposite directions, and the direction information corresponding to the sign is marked on one side of each sign. The vehicle driving direction information can be determined by identifying the sign and the direction information.
[0052] It is understandable that in order to verify the determined vehicle driving direction information, the road name in the road sign can also be identified, and the road direction can be determined based on the road sign naming convention. Generally, the east-west direction is called "road" and the north-south direction is called "street".
[0053] S220 . When basic image parameters are used to perform basic frame image acquisition, reference image parameters of the parameter type are retrieved, and reference frame image acquisition is performed synchronously.
[0054] In this step, the reference image parameters of the parameter type are retrieved through the determined parameter type, and based on the retrieved reference parameter image, the reference frame image is synchronously captured when the basic image parameters are used for basic frame image capture, thereby providing a guarantee for effective license plate recognition in strong forward and backlight environments.
[0055] Exemplarily, reference image parameters of different parameter types may be stored in advance locally on the image acquisition device or in a storage device or cloud associated with the image acquisition device, and before acquiring a reference frame image, corresponding reference image parameters may be retrieved according to the determined parameter type, thereby acquiring a reference frame image based on the retrieved reference image parameters.
[0056] S230. When a license plate recognition result cannot be obtained according to the basic frame image, a license plate recognition result determined according to the reference frame image is obtained as a target recognition result.
[0057] The embodiment of the present application refines the reference frame image acquisition operation into determining the parameter type of the reference image parameters used in the current first granularity time period according to the vehicle driving direction information, and calls the reference image parameters of the parameter type to perform synchronous acquisition of the reference frame image acquisition, thereby improving the parameter type determination method of the reference image parameters, and calls and uses the reference image parameters through the determination of the reference type, thereby providing a guarantee for the effective acquisition of the reference frame image.
[0058] Embodiment 3
[0059] Figure 3 It is a flow chart of a license plate recognition method in Example 3 of the present application. The embodiment of the present application is optimized and improved on the basis of the technical solutions of the above embodiments.
[0060] Furthermore, the operation of "using reference image parameters to acquire reference frame images" is refined into "determining the parameter values of the reference image parameters corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters; and acquiring the reference frame image according to the determined parameter values of the reference image parameters" to improve the reference image parameter determination mechanism.
[0061] like Figure 3 A license plate recognition method shown includes:
[0062] S310: Determine the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters.
[0063] Exemplarily, the correspondence between the image acquisition location, time period information and image parameters can be established in advance locally on the image acquisition device or in a storage device or cloud associated with the image acquisition device, and when determining the parameter values of the image reference parameters, the parameter values of the reference image parameters are searched and determined according to the correspondence based on the location information of the current acquisition location and the second granularity time period to which the current acquisition moment belongs.
[0064] It is understandable that the degree of strong forward and backward lighting in the city corresponding to different image acquisition locations and different acquisition dates and time periods is also different, but there is a pattern to follow. Therefore, it is possible to pre-collect vehicle images captured at different image acquisition locations on different dates in strong forward and backward lighting environments, and use image processing tools to debug image parameters, adapt the corresponding image parameters at different locations and different dates, and thus obtain the corresponding relationship between image acquisition location, time period information and image parameters.
[0065] The time period information is a second granularity time period, and the second granularity time period may be a monthly time period. Exemplarily, the 12 months of a year may be equally divided according to a set number to obtain different monthly time periods as the second granularity time periods. For example, the time periods may be divided by quarter or by month. Typically, the second granularity time periods include January to February, March to April, April to June, July to August, September to October, and November to December, and the current second granularity time period is determined by the current collection time.
[0066] Optionally, before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period, the position information of the current acquisition location and the current second granularity time period may also be determined.
[0067] In an optional implementation of the embodiment of the present application, when determining the location information of the current collection location, the historical license plate recognition results of the current collection location can be classified according to the regional identifier of the license plate, and the target area identifier when the classification ratio is the largest can be determined; the longitude and latitude information corresponding to the target area identifier is used as the location information of the current collection location.
[0068] Exemplarily, the area identifier of the license plate can be the first Chinese character of the license plate. Specifically, the historical license plate recognition results of the current collection location are obtained, and the first Chinese character in the historical license plate recognition results is extracted; the extracted first Chinese characters are statistically classified, and the area corresponding to the first Chinese character with the largest proportion in the classification results is obtained as the target area; the latitude and longitude information corresponding to the target area is used as the location information of the current collection location.
[0069] It is understandable that in order to improve the matching degree between the determined current location information and the actual location information, after determining the classification proportion of the area identification, before determining the target area identification, it is also necessary to filter the area identification by setting a proportion threshold, and only use the area identification whose maximum classification proportion is greater than the set proportion threshold as the target area identification. The set proportion threshold can be determined by the technician according to needs or experience, for example, the set proportion threshold can be 60%.
[0070] In another optional implementation of the embodiment of the present application, when determining the location information of the current acquisition location, the current location information can be determined based on a positioning device built into the image acquisition device, and the latitude and longitude information of the current location information can be used as the location information.
[0071] In another optional implementation of the embodiment of the present application, when determining the location information of the current collection location, a location information acquisition request can be sent to a positioning server, and the longitude and latitude information fed back by the positioning server based on the location information acquisition request can be used as the location information.
[0072] In an optional implementation of the embodiment of the present application, when determining the current second granularity time period, the current time information can be determined based on a timing device built into the image acquisition device, and the current second granularity time period can be determined based on the current time information.
[0073] In another optional implementation of the embodiment of the present application, when determining the current second granularity time period, a time information acquisition request can be sent to a timing server, and the current second granularity time period can be determined based on the current time information fed back by the timing server based on the time information acquisition request.
[0074] S320 . When basic frame image acquisition is performed using basic image parameters, reference frame image acquisition is synchronously performed according to the determined parameter values of the reference image parameters.
[0075] S330: When a license plate recognition result cannot be obtained according to the basic frame image, a license plate recognition result determined according to the reference frame image is obtained as a target recognition result.
[0076] The embodiment of the present application refines the reference frame image acquisition operation to determine the parameter values of the reference image parameters corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters; performs reference frame image acquisition according to the determined parameter values of the reference image parameters, improves the method for determining the parameter values of the reference image parameters, and performs reference frame image acquisition through the determined parameter values, thereby providing a guarantee for the effective acquisition of reference frame images.
[0077] Embodiment 4
[0078] Figure 4 This is a structural diagram of a license plate recognition device in Example 4 of the present application. The embodiment of the present application is suitable for recognizing the license plate of a moving vehicle in a strong forward or backlight environment. The device is implemented through software and / or hardware and is specifically configured in an electronic device with a certain data computing capability. The electronic device can be an image acquisition device with an image acquisition function.
[0079] like Figure 4 The license plate recognition device shown in the figure includes: an image acquisition module 410 and a license plate recognition module 420.
[0080] An image acquisition module 410 is used to synchronously acquire a reference frame image using a reference image parameter while acquiring a basic frame image using a basic image parameter;
[0081] The license plate recognition module 420 is used to obtain the license plate recognition result determined according to the reference frame image as the target recognition result when the license plate recognition result cannot be obtained according to the basic frame image;
[0082] The reference image parameters include front-light image parameters or back-light image parameters.
[0083] In the embodiment of the present application, when the image acquisition module uses the basic image parameters to acquire the basic frame image, the reference image parameters including the front-light image parameters or the back-light image parameters are used to acquire the reference frame image simultaneously; when the license plate recognition module cannot obtain the license plate recognition result according to the basic frame image, the license plate recognition result determined according to the reference frame image is obtained as the target recognition result. The above technical solution uses the reference frame image acquired by the reference image parameters to perform license plate recognition in a strong front-light and back-light environment, which makes up for the defect that the basic frame image cannot perform license plate recognition, thereby improving the license plate recognition rate in a strong front-light and back-light environment.
[0084] Furthermore, when the image acquisition module 410 acquires the reference frame image using the reference image parameters, it is specifically used to:
[0085] Determine, according to the vehicle driving direction information, a parameter type of a reference image parameter used in the current first granularity time period; wherein the parameter type is a forward lighting type or a reverse lighting type;
[0086] The reference image parameters of the parameter type are retrieved to perform reference frame image acquisition.
[0087] Furthermore, when the image acquisition module 410 acquires the reference frame image using the reference image parameters, it is specifically used to:
[0088] Determine the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters;
[0089] Reference frame image acquisition is performed according to the determined parameter values of the reference image parameters.
[0090] Furthermore, the device also includes a location information determination module, which is used to:
[0091] Before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters, the following operations are performed:
[0092] According to the regional identification of the license plate, the historical license plate recognition results of the current collection location are classified, and the target regional identification with the largest classification ratio is determined;
[0093] The longitude and latitude information corresponding to the target area identifier is used as the location information of the current collection location.
[0094] Furthermore, the device also includes a time period determination module, which is used to:
[0095] Before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters, the following operations are performed:
[0096] Determine the current time information according to the timing device built into the image acquisition device, and determine the current second granularity time period according to the current time information; or,
[0097] A time information acquisition request is sent to a timing server, and a current second granularity time period is determined according to current time information fed back by the timing server based on the time information acquisition request.
[0098] The above-mentioned license plate recognition device can execute the license plate recognition method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the license plate recognition method.
[0099] Embodiment 5
[0100] Figure 5 It is a structural diagram of an image acquisition device in Embodiment 5 of the present application, and the device includes: an input device 510, an output device 520, a processor 530 and a storage device 540.
[0101] The input device 510 is used to acquire a basic frame image using basic image parameters, and to acquire a reference frame image using reference image parameters;
[0102] Output device 520, used to display the license plate recognition result;
[0103] one or more processors 530;
[0104] The storage device 540 is used to store one or more programs.
[0105] Among them, the image acquisition equipment can be installed at the entrance and exit of the park, the highway toll station, or the traffic road intersection, etc., to identify the license plate of the moving vehicle at the installation location.
[0106] Figure 5 Taking a processor 530 as an example, the input device 510 in the image acquisition device can be connected to the output device 520, the processor 530 and the storage device 540 through a bus or other means, and the processor 530 and the storage device 540 are also connected through a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0107] In this embodiment, the processor 530 in the image acquisition device can control the input device 510 to use basic image parameters to perform basic frame image acquisition, and when performing basic frame image acquisition, control the input device 510 to synchronously use reference image parameters including front-light image parameters or back-light image parameters to perform reference frame image acquisition; it can also obtain the license plate recognition result determined according to the reference frame image as the target recognition result when the license plate recognition result cannot be obtained according to the basic frame image; it can also control the output device 520 to output and display the target recognition result.
[0108] The storage device 540 in the image acquisition device is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs, and modules, such as the program instructions / modules corresponding to the license plate recognition method in the embodiment of the present application (for example, the attached Figure 4The processor 530 executes various functional applications and data processing of the image acquisition device by running the software programs, instructions and modules stored in the storage device 540, that is, the license plate recognition method in the above method embodiment is implemented.
[0109] The storage device 540 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data, etc. (such as basic image parameters, basic frame images, reference image parameters, reference frame images, and license plate recognition results, etc. in the above-mentioned embodiments). In addition, the storage device 540 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 540 may further include a memory remotely arranged relative to the processor 530, and these remote memories may be connected to the server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0110] Embodiment 6
[0111] Embodiment 6 of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a license plate recognition device, the license plate recognition method provided by the embodiment of the present application is implemented. The method includes: when basic image parameters are used to acquire basic frame images, reference image parameters are simultaneously used to acquire reference frame images; when a license plate recognition result cannot be obtained based on the basic frame image, a license plate recognition result determined based on the reference frame image is obtained as a target recognition result; wherein the reference image parameters include front-light image parameters or back-light image parameters.
[0112] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0113] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims
1. A license plate recognition method, applied to an image acquisition device, characterized in that: include: When basic image parameters are used to acquire basic frame images, reference image parameters are used to acquire reference frame images simultaneously; When the license plate recognition result cannot be obtained according to the basic frame image, the license plate recognition result determined according to the reference frame image is obtained as the target recognition result; wherein confirming the license plate recognition result according to the basic frame image and determining the license plate recognition result according to the reference frame image are implemented in a parallel execution manner; Wherein, the reference image parameters include front-light image parameters or back-light image parameters; Wherein, using reference image parameters to collect reference frame images includes: Determine the parameter type of the reference image parameter used in the current first granularity time period according to the correspondence between the preset vehicle driving direction, the first granularity time information and the parameter type of the reference image parameter; wherein the parameter type is a forward light type or a reverse light type, and the vehicle driving direction includes a direction in which the vehicle is driving toward the image acquisition device or a direction in which the vehicle is driving away from the image acquisition device; Retrieving reference image parameters of the parameter type to perform reference frame image acquisition; Wherein, the using reference image parameters to perform reference frame image acquisition also includes: Determine the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters; Acquiring a reference frame image according to the determined parameter values of the reference image parameters; Before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters, the method further includes: According to the regional identification of the license plate, the historical license plate recognition results of the current collection location are classified, and the target regional identification with the largest classification ratio is determined; The longitude and latitude information corresponding to the target area identifier is used as the location information of the current collection location.
2. The method according to claim 1, characterized in that Before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters, the method further includes: Determine the current time information according to the timing device built into the image acquisition device, and determine the current second granularity time period according to the current time information; or, A time information acquisition request is sent to a timing server, and a current second granularity time period is determined according to current time information fed back by the timing server based on the time information acquisition request.
3. A license plate recognition device, configured in an image acquisition device, characterized in that: include: An image acquisition module, used for synchronously acquiring reference frame images using reference image parameters while acquiring basic frame images using basic image parameters; A license plate recognition module, used for obtaining a license plate recognition result determined according to the reference frame image as a target recognition result when a license plate recognition result cannot be obtained according to the basic frame image; wherein confirming the license plate recognition result according to the basic frame image and determining the license plate recognition result according to the reference frame image are implemented in a parallel execution manner; Wherein, the reference image parameters include front-light image parameters or back-light image parameters; The image acquisition module, when executing reference frame image acquisition using reference image parameters, is specifically used to: Determine the parameter type of the reference image parameter used in the current first granularity time period according to the correspondence between the preset vehicle driving direction, the first granularity time information and the parameter type of the reference image parameter; wherein the parameter type is a forward light type or a reverse light type, and the vehicle driving direction includes a direction in which the vehicle is driving toward the image acquisition device or a direction in which the vehicle is driving away from the image acquisition device; Retrieving reference image parameters of the parameter type to perform reference frame image acquisition; Wherein, the image acquisition module, when executing reference frame image acquisition using reference image parameters, is further specifically used for: Determine the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition position, time period information and image parameters; Acquiring a reference frame image according to the determined parameter values of the reference image parameters; The location information determination module is used to: before determining the parameter value of the reference image parameter corresponding to the current acquisition location in the current second granularity time period according to the pre-established correspondence between the image acquisition location, time period information and image parameters, classify the historical license plate recognition results of the current acquisition location according to the area identifier of the license plate, and determine the target area identifier when the classification accounts for the largest proportion; and use the longitude and latitude information corresponding to the target area identifier as the location information of the current acquisition location.
4. An image acquisition device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a license plate recognition method as described in any one of claims 1-2.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a license plate recognition method as described in any one of claims 1-2 is implemented.
