License plate recognition method and system based on dark vision

Abstract

The embodiment of the present application discloses a license plate recognition method and system based on dark vision, the method comprising: obtaining an ambient light brightness value; when the ambient light brightness value is lower than a preset threshold, obtaining a target image of a target vehicle through a camera, the target image including a target license plate area image of the target vehicle; intercepting the target license plate area image, and obtaining a size parameter of the target license plate area image; dividing the target license plate area image into k area images according to the size parameter and a preset character standard size, each area image corresponding to a character, k being a positive integer; recognizing the k area images respectively to obtain k character recognition results; and determining the target license plate recognition result according to the k character recognition results. The embodiment of the present application can improve the efficiency of license plate recognition in a dark vision environment, so as to improve the efficiency of vehicle monitoring.

Description

Technical Field

[0001] The present application relates to the field of electronic technology or intelligent transportation technology, and specifically to a dark vision-based license plate recognition method and system. Background Art

[0002] With the rapid development of science and technology, cars have become more and more popular, and road safety monitoring has also become a focus of attention, especially in dark vision environments. Because the light is too dim, the license plate cannot be clearly captured, thereby reducing the efficiency of vehicle monitoring. Therefore, how to improve the efficiency of license plate recognition in dark vision environments to improve the efficiency of vehicle monitoring needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a dark vision-based license plate recognition method and system, which can improve the efficiency of license plate recognition in a dark vision environment to improve the efficiency of vehicle monitoring.

[0004] In a first aspect, an embodiment of the present application provides a method for license plate recognition based on dark vision, the method comprising:

[0005] Get the ambient light brightness value;

[0006] When the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle;

[0007] Intercepting the target license plate area image and obtaining size parameters of the target license plate area image;

[0008] Dividing the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer;

[0009] Recognize the k area images respectively to obtain k character recognition results;

[0010] The target license plate recognition result is determined according to the k character recognition results.

[0011] In a second aspect, an embodiment of the present application provides a license plate recognition system based on dark vision, the system comprising: an acquisition unit, an interception unit, a division unit, an identification unit and a determination unit, wherein:

[0012] The acquisition unit is used to acquire the ambient light brightness value; when the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle;

[0013] The interception unit is used to intercept the target license plate area image and obtain the size parameters of the target license plate area image;

[0014] The division unit is used to divide the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer;

[0015] The recognition unit is used to recognize the k area images respectively to obtain k character recognition results;

[0016] The determination unit is used to determine the target license plate recognition result according to the k character recognition results.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0018] The implementation of the embodiments of the present application has the following beneficial effects:

[0019] It can be seen that the dark vision-based license plate recognition method and system described in the embodiments of the present application obtain an ambient light brightness value, and when the ambient light brightness value is lower than a preset threshold value, obtain a target image of the target vehicle through a camera, the target image includes a target license plate area image of the target vehicle, intercept the target license plate area image, and obtain the size parameters of the target license plate area image, and divide the target license plate area image into k area images according to the size parameters and the preset character standard size, each area image corresponds to a character, k is a positive integer, and the k area images are recognized respectively to obtain k character recognition results, and the target license plate recognition result is determined according to the k character recognition results. Each of the k area images can be recognized one by one to obtain k character recognition results. Since different characters are separated, during the recognition process, interference between characters in different adjacent areas occurs, which helps to ensure the correctness of character recognition, and can improve the efficiency of license plate recognition in a dark vision environment to improve vehicle monitoring efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flowchart of a dark vision-based license plate recognition method provided in an embodiment of the present application;

[0022] Figure 2 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0023] Figure 3 This is a block diagram of the functional units of a dark vision-based license plate recognition system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The following is a detailed description of the embodiments of the present application.

[0028] See also Figure 1 , Figure 1 This is a flowchart of a dark vision-based license plate recognition method provided by an embodiment of the present application, which may include the following steps:

[0029] 101. Get the ambient light brightness value.

[0030] In the embodiment of the present application, the ambient light brightness value can be obtained through the ambient light sensor.

[0031] 102. When the ambient light brightness value is lower than a preset threshold, a target image of a target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle.

[0032] The preset threshold value may be preset or set by the system by default. When the ambient light brightness is lower than the preset threshold value, it indicates that the environment is in a dark vision environment.

[0033] In an embodiment of the present application, when the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle can be acquired through the camera, the target image including the target license plate area image of the target vehicle. Specifically, the target orientation parameters between the target vehicle, the license plate area and the camera can be acquired, and the target shooting parameters corresponding to the target orientation parameters can be determined according to the mapping relationship between the preset orientation parameters and the shooting parameters, and then the target image can be acquired by shooting according to the target shooting parameters.

[0034] The target orientation parameters may include: target orientation angle and target distance.

[0035] The target shooting parameters may include at least one of the following: shooting mode, sensitivity, exposure time, resolution, etc., which are not limited here.

[0036] 103. Capture the target license plate area image, and obtain size parameters of the target license plate area image.

[0037] In the embodiment of the present application, the target license plate area image can be captured from the target image, and the size parameters of the target license plate area image can also be obtained.

[0038] 104. Divide the target license plate area image into k area images according to the size parameter and a preset character standard size, each area image corresponds to one character, and k is a positive integer.

[0039] In an embodiment of the present application, the preset character standard size can be pre-set or system default, that is, in actual applications, the size of the characters on the license plate and the number of characters on the license plate are certain. Then, the target license plate area image can be divided into k area images according to the size parameters and the preset character standard size, each area image corresponds to a character, k is a positive integer, that is, the target license plate area image is divided into as many areas as there are characters.

[0040] 105. Recognize the k area images respectively to obtain k character recognition results.

[0041] In an embodiment of the present application, an optical character recognition algorithm (OCR) can be used to identify each of the k area images one by one to obtain k character recognition results. Since different characters are separated, during the recognition process, interference between characters appearing in different adjacent areas is reduced, which helps to ensure the accuracy of character recognition.

[0042] Optionally, the above step 105, identifying the k region images respectively to obtain k character recognition results, may include the following steps:

[0043] 51. Determine an image quality evaluation value of each of the k regional images to obtain k image quality evaluation values;

[0044] 52. Select an image quality evaluation value greater than a preset image quality evaluation value from the k image quality evaluation values ​​to obtain a image quality evaluation values, and determine image quality evaluation values ​​other than the a image quality evaluation values ​​from the k image quality evaluation values ​​to obtain ka image quality evaluation values, where a is a positive integer less than k;

[0045] 53. Directly perform character recognition on the a region images corresponding to the a image quality evaluation values ​​to obtain a character recognition results;

[0046] 54. Perform image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images;

[0047] 55. Perform character recognition on the ka target area images to obtain ka character recognition results;

[0048] 56. Determine the k character recognition results based on the a character recognition results and the ka character recognition results.

[0049] The preset image quality evaluation value can be preset or set by system default. If the image quality evaluation value is greater than the preset image quality evaluation value, it means that the image quality is good and character recognition can be performed directly. Otherwise, it means that the image quality is poor and image enhancement processing is required before character recognition.

[0050] In the embodiment of the present application, at least one image quality evaluation index can be used to perform image quality evaluation on each of the k regional images to obtain k image quality evaluation values. Then, an image quality evaluation value greater than a preset image quality evaluation value is selected from the k image quality evaluation values ​​to obtain a image quality evaluation values, and image quality evaluation values ​​other than a image quality evaluation values ​​from the k image quality evaluation values ​​are determined to obtain ka image quality evaluation values, where a is a positive integer less than k, and then character recognition is directly performed on a regional images corresponding to a image quality evaluation values ​​to obtain a character recognition results.

[0051] Next, image enhancement processing can be performed on the ka area images corresponding to the ka image quality evaluation values ​​to obtain ka target area images, thereby improving the image quality, and then character recognition is performed on the ka target area images to obtain ka character recognition results. Finally, k character recognition results can be determined based on a character recognition results and ka character recognition results. In this way, the accuracy of character recognition can be improved.

[0052] Among them, in the embodiment of the present application, the image enhancement algorithm may include at least one of the following: a wavelet transform algorithm, a Retinex algorithm, a histogram equalization algorithm, a multi-scale transform algorithm, etc., which are not limited here.

[0053] Further, optionally, the above step 54, performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images, may include the following steps:

[0054] 541. Determine a target difference between the ambient light brightness value and the preset threshold value;

[0055] 542. Obtain target shooting parameters of the camera;

[0056] 543. Determine a first image enhancement algorithm corresponding to the target difference;

[0057] 544. Perform image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain a first image, where the regional image i is any regional image among the ka regional images;

[0058] 545. Determine a first signal-to-noise ratio of the first image;

[0059] 546. Determine a first smoothing processing parameter corresponding to the first signal-to-noise ratio;

[0060] 547. Perform smoothing on the first image according to the first smoothing parameter to obtain a target first image;

[0061] 548. Determine a second image enhancement algorithm corresponding to the target shooting parameter;

[0062] 549. Perform image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain a second image;

[0063] 550. Determine a second signal-to-noise ratio of the second image;

[0064] 551. Determine a second smoothing processing parameter corresponding to the second signal-to-noise ratio;

[0065] 552. Smooth the second image according to the second smoothing parameter to obtain a target second image;

[0066] 553. Fuse the target first image with the target second image to obtain a target region image corresponding to the region image i.

[0067] In the embodiment of the present application, the target difference between the ambient light brightness value and the preset threshold value can be determined, and the target shooting parameters of the camera can also be obtained.

[0068] Among them, the mapping relationship between the preset difference and the image enhancement algorithm can also be stored in advance, that is, different difference reflects different light conditions, and different image enhancement strategies are adopted based on different light conditions. The mapping relationship between the preset shooting parameters and the image enhancement algorithm can also be stored in advance, that is, the hardware conditions of the camera determine the shooting parameters of the camera, and then, the appropriate image enhancement algorithm can be adapted based on the actual situation of the camera. The mapping relationship between the preset signal-to-noise ratio and the smoothing processing parameters can also be stored in advance, that is, different signal-to-noise ratios reflect different image features. Based on different image characteristics, corresponding smoothing processing parameters can be adopted to help ensure the smoothing effect.

[0069] Next, taking regional image i as an example, regional image i is any regional image among ka regional images. According to the mapping relationship between the pre-stored preset difference and the image enhancement algorithm, a first image enhancement algorithm corresponding to the target difference can be determined, and then the regional image i is subjected to image enhancement processing according to the first image enhancement algorithm to obtain a first image, and a first signal-to-noise ratio of the first image is determined. Furthermore, according to the mapping relationship between the pre-stored preset signal-to-noise ratio and the smoothing processing parameter, a first smoothing processing parameter corresponding to the first signal-to-noise ratio can be determined, and then the first image is smoothed according to the first smoothing processing parameter to obtain a target first image.

[0070] In addition, according to the mapping relationship between the preset shooting parameters and the image enhancement algorithm, a second image enhancement algorithm corresponding to the target shooting parameters can be determined, and then the regional image i can be image enhanced according to the second image enhancement algorithm to obtain the second image, and the second signal-to-noise ratio of the second image can be determined, and then the second smoothing parameters corresponding to the second signal-to-noise ratio can be determined according to the pre-stored mapping relationship between the preset signal-to-noise ratio and the smoothing parameters, and the second image can be smoothed according to the second smoothing parameters to obtain the target second image, and the target first image and the target second image can be fused to obtain the target regional image corresponding to the regional image i. Image enhancement can be achieved from the optical influence angle (external conditions), and from the shooting influence angle (internal hardware conditions). The image enhancement effects in these two cases can be fused so that the image enhancement effect depth meets the external conditions and the internal hardware conditions, which is helpful to deeply realize image enhancement, thereby improving the subsequent character recognition accuracy.

[0071] Further, optionally, the above step 544, performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain the first image, may include the following steps:

[0072] A1. Obtaining target driving parameters of the target vehicle;

[0073] A2. Obtain target environment parameters at the time of shooting;

[0074] A3. Obtaining first default algorithm adjustment parameters of the first image enhancement algorithm, where the first default algorithm adjustment parameters include a adjustment parameters, each adjustment parameter corresponds to a driving parameter range; a is an integer greater than 1;

[0075] A4. Determine b adjustment parameters corresponding to the target driving parameter, where b is a positive integer less than or equal to a;

[0076] A5. Determine a target optimization coefficient corresponding to the target environmental parameter;

[0077] A6. Optimizing the b adjustment parameters according to the target optimization coefficient to obtain b target adjustment parameters;

[0078] A7. Update the a adjustment parameters according to the b target adjustment parameters to obtain a target adjustment parameters;

[0079] A8. Perform image enhancement processing on the regional image i according to the first image enhancement algorithm and the a target adjustment parameters to obtain the first image.

[0080] In the embodiment of the present application, the target driving parameter may include at least one of the following: driving speed, driving direction, driving acceleration, driving trajectory, etc., which are not limited here. The target environmental parameter may include at least one of the following: ambient temperature, ambient humidity, weather, atmospheric pressure, etc., which are not limited here. The shooting time is the shooting time of the target image.

[0081] In a specific implementation, the target driving parameters of the target vehicle can be obtained, the target environment parameters at the time of shooting can be obtained, and the first default algorithm adjustment parameters of the first image enhancement algorithm can be obtained. The first default algorithm adjustment parameters may include a adjustment parameters, each of which corresponds to a driving parameter range, and a is an integer greater than 1, that is, each adjustment parameter corresponds to a corresponding driving parameter range. Among them, the first default algorithm adjustment parameters are used to adjust the image enhancement effect of the first image enhancement algorithm.

[0082] Next, b adjustment parameters corresponding to the target driving parameters can be determined, where b is a positive integer less than or equal to a, that is, only the adjustment parameters corresponding to the driving parameters are adjusted, that is, targeted enhancement effect adjustment can be achieved for different driving parameters.

[0083] Furthermore, the mapping relationship between the preset environmental parameters and the optimization parameters can be pre-stored, and then the target optimization coefficient corresponding to the target environmental parameter can be determined based on the mapping relationship, and then the b adjustment parameters can be optimized according to the target optimization coefficient to obtain b target adjustment parameters, so that the adjustment parameters are deeply consistent with the driving state and the environmental state. In this way, the adjustment parameters of the image enhancement algorithm under the corresponding driving environment can be adjusted in a targeted manner based on the environmental parameters, which helps to deeply improve the image enhancement effect.

[0084] Finally, a adjustment parameters are updated according to b target adjustment parameters, that is, b adjustment parameters are used to replace b adjustment parameters to obtain new a adjustment parameters, namely a target adjustment parameters, and image enhancement processing is performed on regional image i according to the first image enhancement algorithm and a target adjustment parameters to obtain the first image. In this way, the adjustment parameters of the image enhancement algorithm under the corresponding driving environment can be adjusted in a targeted manner based on the environmental parameters, which helps to deeply improve the image enhancement effect.

[0085] Optionally, the above step 549, performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain the second image, may include the following steps:

[0086] B1. Determine the target cleanliness of the lens of the camera;

[0087] B2. Obtaining a second default algorithm adjustment parameter of the second image enhancement algorithm;

[0088] B3. Determine the target influence coefficient corresponding to the target cleanliness;

[0089] B4. adjusting the second default algorithm adjustment parameter according to the target influence coefficient to obtain a target algorithm adjustment parameter;

[0090] B5. Perform image enhancement processing on the regional image i according to the second image enhancement algorithm and the target algorithm adjustment parameters to obtain the second image.

[0091] In the embodiment of the present application, an image of the lens of the camera can be captured by an auxiliary camera, and the image can be analyzed to determine the target cleanliness of the lens of the camera.

[0092] In a specific implementation, a second default algorithm adjustment parameter of the second image enhancement algorithm may be obtained, and the second default algorithm adjustment parameter is used to adjust the image enhancement effect of the second image enhancement algorithm.

[0093] Among them, the mapping relationship between the preset cleanliness and the influence coefficient can also be pre-stored, and then, the target influence coefficient corresponding to the target cleanliness can be determined based on the mapping relationship, and then the second default algorithm adjustment parameter is adjusted according to the target influence coefficient to obtain the target algorithm adjustment parameter, and then the regional image i is enhanced according to the second image enhancement algorithm and the target algorithm adjustment parameter to obtain the second image, that is, the corresponding adjustment parameters of the image enhancement algorithm can be dynamically adjusted based on the cleanliness of the lens, so that the image enhancement algorithm is more adapted to the image itself, which helps to improve the image enhancement effect.

[0094] Optionally, the above step 51, determining the image quality evaluation value of each of the k regional images to obtain k image quality evaluation values, may include the following steps:

[0095] C1. Perform image segmentation on the regional image j to obtain a target region and a background region, wherein the regional image j is any one of the k regional images;

[0096] C2. Processing the target region using morphological operations to obtain a reference target region;

[0097] C3. Expanding outward based on the outline of the reference target area to obtain the required target area;

[0098] C4. Perform image quality evaluation on the target area to obtain an image quality evaluation value of the area image j.

[0099] The purpose of morphological operations is to extract the main component information in the image, including corrosion, expansion, opening operation, closing operation, gradient operation, top hat operation, black hat operation, etc.

[0100] In the embodiment of the present application, taking regional image j as an example, regional image j is any regional image among k regional images. Regional image j can be segmented to obtain target area and background area, and then the target area is processed by morphological operation to obtain reference target area, and then the relevant target can be further completely extracted, and then the required target area is expanded outward based on the outline of the reference target area, and the required target area can wrap the reference target area, that is, after the target area is morphologically processed, the possible complete area is further extended based on this processing result, which helps to ensure the integrity of the characters and effectively remove most of the useless background areas, and then the image quality evaluation of the required target area is performed to obtain the image quality evaluation value of regional image j, that is, the target area is retained as much as possible, which also helps to improve the accuracy of image quality evaluation. After all, image quality evaluation is mainly for the target area, thereby helping to improve the accuracy of subsequent character recognition.

[0101] 106. Determine a target license plate recognition result according to the k character recognition results.

[0102] In the embodiment itself, each of the k character recognition results corresponds to a regional position, and the k character recognition results can be connected in series according to the corresponding regional positions of the k character recognition results to obtain the final target license plate recognition result.

[0103] It can be seen that the license plate recognition method based on dark vision described in the embodiment of the present application obtains the ambient light brightness value, and when the ambient light brightness value is lower than a preset threshold value, obtains the target image of the target vehicle through the camera, the target image includes the target license plate area image of the target vehicle, intercepts the target license plate area image, and obtains the size parameters of the target license plate area image, and divides the target license plate area image into k area images according to the size parameters and the preset character standard size, each area image corresponds to a character, k is a positive integer, and the k area images are recognized respectively to obtain k character recognition results, and the target license plate recognition result is determined according to the k character recognition results. Each area image in the k area images can be recognized one by one to obtain k character recognition results. Since different characters are separated, during the recognition process, interference between characters in different adjacent areas occurs, which helps to ensure the correctness of character recognition, and can improve the efficiency of license plate recognition in a dark vision environment to improve vehicle monitoring efficiency.

[0104] In accordance with the above embodiment, please refer to Figure 2 , Figure 2: is a structural diagram of an electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. In the embodiment of the present application, the program includes instructions for executing the following steps:

[0105] Get the ambient light brightness value;

[0106] When the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle;

[0107] Intercepting the target license plate area image and obtaining size parameters of the target license plate area image;

[0108] Dividing the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer;

[0109] Recognize the k area images respectively to obtain k character recognition results;

[0110] The target license plate recognition result is determined according to the k character recognition results.

[0111] Optionally, in the aspect of respectively identifying the k regional images to obtain k character recognition results, the program includes instructions for executing the following steps:

[0112] Determine an image quality evaluation value of each of the k regional images to obtain k image quality evaluation values;

[0113] Selecting an image quality evaluation value greater than a preset image quality evaluation value from the k image quality evaluation values ​​to obtain a image quality evaluation values, and determining image quality evaluation values ​​other than the a image quality evaluation values ​​from the k image quality evaluation values ​​to obtain ka image quality evaluation values, where a is a positive integer less than k;

[0114] Directly perform character recognition on the a region images corresponding to the a image quality evaluation values ​​to obtain a character recognition results;

[0115] Performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images;

[0116] Performing character recognition on the ka target area images to obtain ka character recognition results;

[0117] The k character recognition results are determined according to the a character recognition results and the ka character recognition results.

[0118] Optionally, in the aspect of performing image enhancement processing on the ka regional images corresponding to the ka image quality evaluation values ​​to obtain ka target regional images, the program includes instructions for executing the following steps:

[0119] Determining a target difference between the ambient light brightness value and the preset threshold value;

[0120] Obtain target shooting parameters of the camera;

[0121] Determining a first image enhancement algorithm corresponding to the target difference;

[0122] Performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain a first image, wherein the regional image i is any regional image among the ka regional images;

[0123] determining a first signal-to-noise ratio of the first image;

[0124] determining a first smoothing parameter corresponding to the first signal-to-noise ratio;

[0125] Performing smoothing on the first image according to the first smoothing parameter to obtain a target first image;

[0126] Determining a second image enhancement algorithm corresponding to the target shooting parameters;

[0127] Performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain a second image;

[0128] determining a second signal-to-noise ratio of the second image;

[0129] determining a second smoothing parameter corresponding to the second signal-to-noise ratio;

[0130] Smoothing the second image according to the second smoothing parameter to obtain a target second image;

[0131] The target first image and the target second image are fused to obtain a target region image corresponding to the region image i.

[0132] Optionally, in the aspect of performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain the first image, the program includes instructions for executing the following steps:

[0133] Acquiring target driving parameters of the target vehicle;

[0134] Obtain target environment parameters at the time of shooting;

[0135] Obtaining a first default algorithm adjustment parameter of the first image enhancement algorithm, wherein the first default algorithm adjustment parameter includes a adjustment parameters, each adjustment parameter corresponds to a driving parameter range; a is an integer greater than 1;

[0136] Determine b adjustment parameters corresponding to the target driving parameter, where b is a positive integer less than or equal to a;

[0137] Determining a target optimization coefficient corresponding to the target environmental parameter;

[0138] Optimizing the b adjustment parameters according to the target optimization coefficient to obtain b target adjustment parameters;

[0139] Update the a adjustment parameters according to the b target adjustment parameters to obtain a target adjustment parameters;

[0140] Image enhancement processing is performed on the regional image i according to the first image enhancement algorithm and the a target adjustment parameters to obtain the first image.

[0141] Optionally, in the aspect of performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain the second image, the program includes instructions for executing the following steps:

[0142] Determining a target cleanliness of a lens of the camera;

[0143] Acquire second default algorithm adjustment parameters of the second image enhancement algorithm;

[0144] Determining a target influence coefficient corresponding to the target cleanliness;

[0145] Adjusting the second default algorithm adjustment parameter according to the target influence coefficient to obtain a target algorithm adjustment parameter;

[0146] The image enhancement process is performed on the regional image i according to the second image enhancement algorithm and the target algorithm adjustment parameters to obtain the second image.

[0147] It can be seen that the electronic device described in the embodiment of the present application obtains the ambient light brightness value, and when the ambient light brightness value is lower than a preset threshold value, obtains the target image of the target vehicle through the camera, the target image includes the target license plate area image of the target vehicle, intercepts the target license plate area image, and obtains the size parameters of the target license plate area image, and divides the target license plate area image into k area images according to the size parameters and the preset character standard size, each area image corresponds to a character, k is a positive integer, and the k area images are recognized respectively to obtain k character recognition results, and the target license plate recognition result is determined according to the k character recognition results. Each area image in the k area images can be recognized one by one to obtain k character recognition results. Since different characters are separated, during the recognition process, interference between characters in different adjacent areas occurs, which helps to ensure the correctness of character recognition, and can improve the efficiency of license plate recognition in a dark visual environment to improve vehicle monitoring efficiency.

[0148] Among them, the electronic device may include at least one of the following: video matrix, smart camera, traffic light, mobile law enforcement equipment, etc., which are not limited here.

[0149] Figure 3 300 is a functional unit block diagram of a dark vision-based license plate recognition system 300 involved in an embodiment of the present application. The dark vision-based license plate recognition system 300 includes: an acquisition unit 301, a capture unit 302, a division unit 303, a recognition unit 304 and a determination unit 305, wherein:

[0150] The acquisition unit 301 is used to acquire the ambient light brightness value; when the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle;

[0151] The interception unit 302 is used to intercept the target license plate area image and obtain the size parameters of the target license plate area image;

[0152] The division unit 303 is used to divide the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer;

[0153] The recognition unit 304 is used to recognize the k region images respectively to obtain k character recognition results;

[0154] The determination unit 305 is used to determine the target license plate recognition result according to the k character recognition results.

[0155] Optionally, in the aspect of respectively recognizing the k regional images to obtain k character recognition results, the recognition unit 304 is specifically used for:

[0156] Determine an image quality evaluation value of each of the k regional images to obtain k image quality evaluation values;

[0157] Selecting an image quality evaluation value greater than a preset image quality evaluation value from the k image quality evaluation values ​​to obtain a image quality evaluation values, and determining image quality evaluation values ​​other than the a image quality evaluation values ​​from the k image quality evaluation values ​​to obtain ka image quality evaluation values, where a is a positive integer less than k;

[0158] Directly perform character recognition on the a region images corresponding to the a image quality evaluation values ​​to obtain a character recognition results;

[0159] Performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images;

[0160] Performing character recognition on the ka target area images to obtain ka character recognition results;

[0161] The k character recognition results are determined according to the a character recognition results and the ka character recognition results.

[0162] Optionally, in the aspect of performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images, the identification unit 304 is specifically used to:

[0163] Determining a target difference between the ambient light brightness value and the preset threshold value;

[0164] Obtain target shooting parameters of the camera;

[0165] Determining a first image enhancement algorithm corresponding to the target difference;

[0166] Performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain a first image, wherein the regional image i is any regional image among the ka regional images;

[0167] determining a first signal-to-noise ratio of the first image;

[0168] determining a first smoothing parameter corresponding to the first signal-to-noise ratio;

[0169] Performing smoothing on the first image according to the first smoothing parameter to obtain a target first image;

[0170] Determining a second image enhancement algorithm corresponding to the target shooting parameters;

[0171] Performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain a second image;

[0172] determining a second signal-to-noise ratio of the second image;

[0173] determining a second smoothing parameter corresponding to the second signal-to-noise ratio;

[0174] Smoothing the second image according to the second smoothing parameter to obtain a target second image;

[0175] The target first image and the target second image are fused to obtain a target region image corresponding to the region image i.

[0176] Optionally, in the aspect of performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain the first image, the recognition unit 304 is specifically used for:

[0177] Acquiring target driving parameters of the target vehicle;

[0178] Obtain target environment parameters at the time of shooting;

[0179] Obtaining a first default algorithm adjustment parameter of the first image enhancement algorithm, wherein the first default algorithm adjustment parameter includes a adjustment parameters, each adjustment parameter corresponds to a driving parameter range; a is an integer greater than 1;

[0180] Determine b adjustment parameters corresponding to the target driving parameter, where b is a positive integer less than or equal to a;

[0181] Determining a target optimization coefficient corresponding to the target environmental parameter;

[0182] Optimizing the b adjustment parameters according to the target optimization coefficient to obtain b target adjustment parameters;

[0183] Update the a adjustment parameters according to the b target adjustment parameters to obtain a target adjustment parameters;

[0184] Image enhancement processing is performed on the regional image i according to the first image enhancement algorithm and the a target adjustment parameters to obtain the first image.

[0185] Optionally, in the aspect of performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain the second image, the recognition unit 304 is specifically used for:

[0186] Determining a target cleanliness of a lens of the camera;

[0187] Acquire second default algorithm adjustment parameters of the second image enhancement algorithm;

[0188] Determining a target influence coefficient corresponding to the target cleanliness;

[0189] Adjusting the second default algorithm adjustment parameter according to the target influence coefficient to obtain a target algorithm adjustment parameter;

[0190] The image enhancement process is performed on the regional image i according to the second image enhancement algorithm and the target algorithm adjustment parameters to obtain the second image.

[0191] It can be seen that the dark vision-based license plate recognition system described in the embodiment of the present application obtains the ambient light brightness value, and when the ambient light brightness value is lower than a preset threshold value, obtains the target image of the target vehicle through the camera, the target image includes the target license plate area image of the target vehicle, intercepts the target license plate area image, and obtains the size parameters of the target license plate area image, and divides the target license plate area image into k area images according to the size parameters and the preset character standard size, each area image corresponds to a character, k is a positive integer, and the k area images are recognized respectively to obtain k character recognition results, and the target license plate recognition result is determined according to the k character recognition results. Each area image in the k area images can be recognized one by one to obtain k character recognition results. Since different characters are separated, during the recognition process, interference between characters in different adjacent areas occurs, which helps to ensure the correctness of character recognition, and can improve the efficiency of license plate recognition in a dark vision environment to improve vehicle monitoring efficiency.

[0192] It can be understood that the functions of each program module of the dark vision-based license plate recognition system of this embodiment can be specifically implemented according to the method in the above method embodiment, and its specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0193] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0194] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0195] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0196] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0197] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0198] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0200] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0201] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0202] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A license plate recognition method based on dark vision, characterized in that: The method comprises: Get the ambient light brightness value; When the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle; Intercepting the target license plate area image and obtaining size parameters of the target license plate area image; Dividing the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer; Recognize the k area images respectively to obtain k character recognition results; Determine the target license plate recognition result according to the k character recognition results; The k regional images are respectively recognized to obtain k character recognition results, including: Determine an image quality evaluation value of each of the k regional images to obtain k image quality evaluation values; Selecting an image quality evaluation value greater than a preset image quality evaluation value from the k image quality evaluation values ​​to obtain a image quality evaluation values, and determining image quality evaluation values ​​other than the a image quality evaluation values ​​from the k image quality evaluation values ​​to obtain ka image quality evaluation values, where a is a positive integer less than k; Directly perform character recognition on the a region images corresponding to the a image quality evaluation values ​​to obtain a character recognition results; Performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images; Performing character recognition on the ka target area images to obtain ka character recognition results; Determine the k character recognition results according to the a character recognition results and the ka character recognition results; The step of performing image enhancement processing on the ka area images corresponding to the ka image quality evaluation values ​​to obtain ka target area images includes: Determining a target difference between the ambient light brightness value and the preset threshold value; Obtain target shooting parameters of the camera; Determining a first image enhancement algorithm corresponding to the target difference; Performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain a first image, wherein the regional image i is any regional image among the ka regional images; determining a first signal-to-noise ratio of the first image; determining a first smoothing parameter corresponding to the first signal-to-noise ratio; Performing smoothing on the first image according to the first smoothing parameter to obtain a target first image; Determining a second image enhancement algorithm corresponding to the target shooting parameters; Performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain a second image; determining a second signal-to-noise ratio of the second image; determining a second smoothing parameter corresponding to the second signal-to-noise ratio; Smoothing the second image according to the second smoothing parameter to obtain a target second image; Fusing the target first image with the target second image to obtain a target region image corresponding to the region image i; The step of performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain the first image includes: Acquiring target driving parameters of the target vehicle; Obtain target environment parameters at the time of shooting; Obtaining a first default algorithm adjustment parameter of the first image enhancement algorithm, wherein the first default algorithm adjustment parameter includes a adjustment parameters, each adjustment parameter corresponds to a driving parameter range; a is an integer greater than 1; Determine b adjustment parameters corresponding to the target driving parameter, where b is a positive integer less than or equal to a; Determining a target optimization coefficient corresponding to the target environmental parameter; Optimizing the b adjustment parameters according to the target optimization coefficient to obtain b target adjustment parameters; Update the a adjustment parameters according to the b target adjustment parameters to obtain a target adjustment parameters; Image enhancement processing is performed on the regional image i according to the first image enhancement algorithm and the a target adjustment parameters to obtain the first image.

2. The method according to claim 1, characterized in that The performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain the second image includes: Determining a target cleanliness of a lens of the camera; Acquire second default algorithm adjustment parameters of the second image enhancement algorithm; Determining a target influence coefficient corresponding to the target cleanliness; Adjusting the second default algorithm adjustment parameter according to the target influence coefficient to obtain a target algorithm adjustment parameter; The image enhancement process is performed on the regional image i according to the second image enhancement algorithm and the target algorithm adjustment parameters to obtain the second image.

3. A license plate recognition system based on dark vision, characterized in that: The system comprises: an acquisition unit, a capture unit, a division unit, a recognition unit and a determination unit, wherein: The acquisition unit is used to acquire the ambient light brightness value; when the ambient light brightness value is lower than a preset threshold, a target image of the target vehicle is acquired through a camera, wherein the target image includes a target license plate area image of the target vehicle; The interception unit is used to intercept the target license plate area image and obtain the size parameters of the target license plate area image; The division unit is used to divide the target license plate area image into k area images according to the size parameter and the preset character standard size, each area image corresponds to one character, and k is a positive integer; The recognition unit is used to recognize the k area images respectively to obtain k character recognition results; The determination unit is used to determine the target license plate recognition result according to the k character recognition results; Wherein, in the aspect of respectively recognizing the k regional images to obtain k character recognition results, the recognition unit is specifically used for: Determine an image quality evaluation value of each of the k regional images to obtain k image quality evaluation values; Selecting an image quality evaluation value greater than a preset image quality evaluation value from the k image quality evaluation values ​​to obtain a image quality evaluation values, and determining image quality evaluation values ​​other than the a image quality evaluation values ​​from the k image quality evaluation values ​​to obtain ka image quality evaluation values, where a is a positive integer less than k; Directly perform character recognition on the a region images corresponding to the a image quality evaluation values ​​to obtain a character recognition results; Performing image enhancement processing on the ka region images corresponding to the ka image quality evaluation values ​​to obtain ka target region images; Performing character recognition on the ka target area images to obtain ka character recognition results; Determine the k character recognition results according to the a character recognition results and the ka character recognition results; Wherein, in the aspect of performing image enhancement processing on the ka area images corresponding to the ka image quality evaluation values ​​to obtain the ka target area images, the recognition unit is specifically used for: Determining a target difference between the ambient light brightness value and the preset threshold value; Obtain target shooting parameters of the camera; Determining a first image enhancement algorithm corresponding to the target difference; Performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain a first image, wherein the regional image i is any regional image among the ka regional images; determining a first signal-to-noise ratio of the first image; determining a first smoothing parameter corresponding to the first signal-to-noise ratio; Performing smoothing on the first image according to the first smoothing parameter to obtain a target first image; Determining a second image enhancement algorithm corresponding to the target shooting parameters; Performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain a second image; determining a second signal-to-noise ratio of the second image; determining a second smoothing parameter corresponding to the second signal-to-noise ratio; Smoothing the second image according to the second smoothing parameter to obtain a target second image; Fusing the target first image with the target second image to obtain a target region image corresponding to the region image i; Wherein, in the aspect of performing image enhancement processing on the regional image i according to the first image enhancement algorithm to obtain the first image, the recognition unit is specifically used for: Acquiring target driving parameters of the target vehicle; Obtain target environment parameters at the time of shooting; Obtaining a first default algorithm adjustment parameter of the first image enhancement algorithm, wherein the first default algorithm adjustment parameter includes a adjustment parameters, each adjustment parameter corresponds to a driving parameter range; a is an integer greater than 1; Determine b adjustment parameters corresponding to the target driving parameter, where b is a positive integer less than or equal to a; Determining a target optimization coefficient corresponding to the target environmental parameter; Optimizing the b adjustment parameters according to the target optimization coefficient to obtain b target adjustment parameters; Update the a adjustment parameters according to the b target adjustment parameters to obtain a target adjustment parameters; Image enhancement processing is performed on the regional image i according to the first image enhancement algorithm and the a target adjustment parameters to obtain the first image.

4. The system according to claim 3, characterized in that In the aspect of performing image enhancement processing on the regional image i according to the second image enhancement algorithm to obtain the second image, the recognition unit is specifically used for: Determining a target cleanliness of a lens of the camera; Acquire second default algorithm adjustment parameters of the second image enhancement algorithm; Determining a target influence coefficient corresponding to the target cleanliness; Adjusting the second default algorithm adjustment parameter according to the target influence coefficient to obtain a target algorithm adjustment parameter; The image enhancement process is performed on the regional image i according to the second image enhancement algorithm and the target algorithm adjustment parameters to obtain the second image.

Images