Exposure value updating method, device, electronic device and storage medium

Abstract

The embodiments of the present application provide an exposure value updating method, device, electronic device, and storage medium, relating to the field of image acquisition technology, including: extracting the brightness value and color of a license plate in a captured vehicle image; storing the brightness values ​​of the extracted license plates according to the time sequence of the vehicle image capture and the color of the extracted license plates to obtain brightness groups, each brightness group containing: the brightness values ​​of license plates with the same time sequence but different colors; determining the weights of each brightness value in a target brightness group to which the extracted brightness value belongs based on the degree of discreteness of the brightness values ​​within each brightness group; determining the expected brightness value of the license plate in the captured vehicle image based on the extracted brightness values ​​and the determined weights; and capturing the vehicle image using the expected brightness value as the current exposure value. Applying the solution provided by the embodiments of the present application can improve the quality of the captured image.

Description

Technical Field

[0001] The present application relates to the field of image acquisition technology, and in particular to an exposure value updating method, device, electronic device and storage medium. Background Art

[0002] In transportation scenarios, in order to facilitate the management of vehicles on the road, it is usually necessary to use image acquisition equipment to capture vehicle images of vehicles passing through the road. The above vehicle images can then be used to identify the vehicle's license plate number.

[0003] In the related art, a fixed exposure value is generally given in advance to an image acquisition device, and the image acquisition device acquires a vehicle image of the vehicle according to the fixed exposure value.

[0004] However, license plates on the road can vary in color, for example, there are blue, green, black, and yellow license plates. Different license plates reflect light to varying degrees, and the intensity of light at different times also varies, further leading to different levels of reflectivity for license plates of different colors at different times. Therefore, in the above scheme, if the image capture device uses a fixed exposure value to capture images of vehicles with different license plate colors at different times, the brightness of the license plate numbers in the captured vehicle images may be too high or too low, reducing the quality of the captured images. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, electronic device, and storage medium for updating exposure values ​​to improve the quality of captured images. The specific technical solutions are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for updating an exposure value, the method comprising:

[0007] Extracting the brightness value and color of the license plate in the collected vehicle image;

[0008] According to the time sequence of collecting the vehicle images and the color of the extracted license plates, the brightness values ​​of the extracted license plates are stored to obtain brightness groups, wherein each brightness group includes: the brightness values ​​of corresponding license plates with the same time sequence and different colors;

[0009] Determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group;

[0010] determining an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight;

[0011] The expected brightness value is used as the currently updated exposure value to capture the vehicle image.

[0012] In one embodiment of the present application, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain the brightness groups includes:

[0013] When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group.

[0014] In one embodiment of the present application, when the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group, including:

[0015] If the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a first brightness group, wherein the brightness values ​​stored in the first brightness group are lower than the minimum brightness value; and / or

[0016] When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a second brightness group, wherein the brightness value stored in the second brightness group is higher than the maximum brightness value.

[0017] In one embodiment of the present application, determining the expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight includes:

[0018] Normalizing the extracted brightness values;

[0019] The expected brightness value of the license plate in the captured vehicle image is calculated based on the determined weights and the normalized brightness value.

[0020] In one embodiment of the present application, the normalizing the extracted brightness value includes:

[0021] When the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, calculating a first difference between the extracted brightness value and the minimum brightness value, wherein the minimum brightness value is: the minimum brightness value among the stored brightness values;

[0022] determining a first ratio of the first difference value to the maximum difference value, calculating the sum of the first ratio and a preset normalization parameter to obtain a normalized brightness value, wherein the maximum difference value is: a difference between a maximum brightness value of each stored brightness value and the minimum brightness value;

[0023] and / or

[0024] When the extracted brightness value is higher than the highest brightness value required by the exposure qualification condition, calculating a second difference between the maximum brightness value and the extracted brightness value;

[0025] A second ratio of the second difference to the maximum difference is determined, and a sum of the second ratio and a preset normalization parameter is calculated to obtain a normalized brightness value.

[0026] In one embodiment of the present application, determining the expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight includes:

[0027] Calculating the product of the normalized brightness value and the determined weight as the brightness adjustment coefficient;

[0028] Calculating a coefficient difference between a preset maximum adjustment coefficient and the brightness adjustment coefficient, determining a product of the coefficient difference and a preset brightness adjustment amplitude to obtain a brightness adjustment value;

[0029] If the extracted brightness value is lower than the minimum brightness value, calculating the difference between the extracted brightness value and the brightness adjustment value to obtain an expected brightness value of the license plate in the captured vehicle image;

[0030] and / or

[0031] In the case that the extracted brightness value is higher than the maximum brightness value, a sum of the extracted brightness value and the brightness adjustment value is calculated to obtain an expected brightness value of the license plate in the captured vehicle image.

[0032] In one embodiment of the present application, determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group includes:

[0033] For each brightness value in the brightness group, calculating the proportion of the brightness value in the brightness group to which the brightness value belongs;

[0034] For each brightness group, the dispersion of the brightness values ​​in the brightness group is calculated using the proportion of each brightness value in the brightness group;

[0035] The weights of the respective brightness values ​​in the target brightness group to which the extracted brightness value belongs are determined according to the degree of dispersion of the brightness values ​​in each brightness group.

[0036] In one embodiment of the present application, for each brightness group, calculating the dispersion of brightness values ​​within the brightness group using the proportion of each brightness value in the brightness group includes:

[0037] For each brightness group, calculate the information entropy of the brightness group based on the corresponding proportions of each brightness value in the brightness group;

[0038] A difference between a preset entropy value threshold and the information entropy is determined as a discrete degree of the brightness values ​​within the brightness group.

[0039] In one embodiment of the present application, determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group includes:

[0040] Calculate the ratio of the discrete degree of the brightness value in the target brightness group where the extracted brightness value belongs to the total discrete degree as the weight of the brightness value in the target brightness group, wherein the total discrete degree is: the sum of the discrete degrees corresponding to each brightness group.

[0041] In a second aspect, an embodiment of the present application provides an exposure value updating device, the device comprising:

[0042] An image extraction module is used to extract the brightness value and color of the license plate in the collected vehicle image;

[0043] a brightness group obtaining module for storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates, to obtain brightness groups, wherein each brightness group includes: brightness values ​​of license plates with the same time sequence and different colors;

[0044] a weight determination module, configured to determine the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group;

[0045] an expected brightness value determination module, configured to determine an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight;

[0046] The exposure value updating module is used to use the expected brightness value as the currently updated exposure value to collect vehicle images.

[0047] In one embodiment of the present application, the brightness group obtaining module is specifically configured to:

[0048] When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group.

[0049] In one embodiment of the present application, the brightness group obtaining module is specifically configured to:

[0050] If the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a first brightness group, wherein the brightness values ​​stored in the first brightness group are lower than the minimum brightness value; and / or

[0051] When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a second brightness group, wherein the brightness value stored in the second brightness group is higher than the maximum brightness value.

[0052] In one embodiment of the present application, the expected brightness value determination module includes:

[0053] A brightness normalization unit, used for normalizing the extracted brightness value;

[0054] The expected brightness value determining unit is used to calculate the expected brightness value of the license plate in the collected vehicle image according to the determined weight and the brightness value after normalization.

[0055] In one embodiment of the present application, the brightness normalization unit is specifically configured to:

[0056] When the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, calculating a first difference between the extracted brightness value and the minimum brightness value, wherein the minimum brightness value is: the minimum brightness value among the stored brightness values;

[0057] determining a first ratio of the first difference value to the maximum difference value, calculating the sum of the first ratio and a preset normalization parameter to obtain a normalized brightness value, wherein the maximum difference value is: a difference between a maximum brightness value of each stored brightness value and the minimum brightness value;

[0058] and / or

[0059] When the extracted brightness value is higher than the highest brightness value required by the exposure qualification condition, calculating a second difference between the maximum brightness value and the extracted brightness value;

[0060] A second ratio of the second difference to the maximum difference is determined, and a sum of the second ratio and a preset normalization parameter is calculated to obtain a normalized brightness value.

[0061] In one embodiment of the present application, the expected brightness value determination module is specifically configured to:

[0062] Calculating the product of the normalized brightness value and the determined weight as the brightness adjustment coefficient;

[0063] Calculating a coefficient difference between a preset maximum adjustment coefficient and the brightness adjustment coefficient, determining a product of the coefficient difference and a preset brightness adjustment amplitude to obtain a brightness adjustment value;

[0064] If the extracted brightness value is lower than the minimum brightness value, calculating the difference between the extracted brightness value and the brightness adjustment value to obtain an expected brightness value of the license plate in the captured vehicle image;

[0065] and / or

[0066] In the case that the extracted brightness value is higher than the maximum brightness value, a sum of the extracted brightness value and the brightness adjustment value is calculated to obtain an expected brightness value of the license plate in the captured vehicle image.

[0067] In one embodiment of the present application, the weight determination module includes:

[0068] a proportion calculation unit, configured to calculate, for each brightness value in the brightness group, a proportion of the brightness value in the brightness group to which the brightness value belongs;

[0069] a dispersion degree calculation unit, configured to calculate, for each brightness group, a dispersion degree of the brightness values ​​within the brightness group using a proportion of each brightness value in the brightness group;

[0070] The weight determination unit is used to determine the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group.

[0071] In one embodiment of the present application, the discrete degree calculation unit is specifically configured to:

[0072] For each brightness group, calculate the information entropy of the brightness group based on the corresponding proportions of each brightness value in the brightness group;

[0073] A difference between a preset entropy value threshold and the information entropy is determined as a discrete degree of the brightness values ​​within the brightness group.

[0074] In one embodiment of the present application, the weight determination module is specifically configured to:

[0075] Calculate the ratio of the discrete degree of the brightness value in the target brightness group where the extracted brightness value belongs to the total discrete degree as the weight of the brightness value in the target brightness group, wherein the total discrete degree is: the sum of the discrete degrees corresponding to each brightness group.

[0076] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0077] Memory for storing computer programs;

[0078] The processor is configured to implement any of the method steps described in the first aspect when executing a program stored in the memory.

[0079] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the method steps described in the first aspect is implemented.

[0080] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-described exposure value updating methods.

[0081] Beneficial effects of the embodiments of the present application:

[0082] In the exposure value updating scheme provided in the embodiment of the present application, the brightness value and color of the license plate in the collected vehicle image can be extracted; the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group, wherein each brightness group contains: the brightness values ​​of the corresponding license plates with the same time sequence but different colors; according to the discrete degree of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs is determined, wherein the weight of the brightness value in each brightness group is proportional to the discrete degree of the brightness value in the brightness group; according to the extracted brightness value and the determined weight, the expected brightness value of the license plate in the collected vehicle image is determined; and the expected brightness value is used as the currently updated exposure value for vehicle image collection. In this way, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the solution provided by the embodiments of the present application can improve the quality of the captured images. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0084] Figure 1 A flowchart of a method for updating an exposure value provided in an embodiment of the present application;

[0085] Figure 2 A schematic diagram of a vehicle image provided in an embodiment of the present application;

[0086] Figure 3 Schematic diagram of license plates of different colors provided in an embodiment of the present application;

[0087] Figure 4 A schematic diagram of license plates of different colors in the same vehicle image provided by an embodiment of the present application;

[0088] Figure 5 A schematic diagram of an overexposed license plate in a vehicle image provided by an embodiment of the present application;

[0089] Figure 6 A schematic diagram of underexposure of a license plate in a vehicle image provided by an embodiment of the present application;

[0090] Figure 7 A flowchart of another exposure value updating method provided in an embodiment of the present application;

[0091] Figure 8 A schematic structural diagram of an exposure value updating device provided in an embodiment of the present application;

[0092] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0093] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0094] In transportation scenarios, a fixed exposure value is usually given in advance for an image acquisition device. The image acquisition device captures vehicle images of vehicles passing through the road according to the fixed exposure value, and the above vehicle images can be used to subsequently identify the passing vehicles.

[0095] The exposure value is an exposure parameter of the image acquisition device. Given a given exposure value, the image acquisition device can adjust its own parameters such as aperture size, shutter speed, and sensitivity of the photosensitive medium to achieve the above exposure value, thereby acquiring images according to the given exposure value. When the exposure value is within the ideal range, the image captured by the image acquisition device has a strong contrast, moderate brightness, and high quality. Subsequent recognition based on the image can achieve a good recognition effect. However, when the exposure value is high, the image captured by the image acquisition device may be too bright and the picture may be white. When the exposure value is low, the image captured by the image acquisition device may be low in brightness and dark. In the above cases, the image quality is low, and subsequent recognition based on the image will have a poor recognition effect.

[0096] When the exposure value of the image acquisition device is fixed, the colors of license plates on the road may be different, and the degree of reflection of license plates of different colors is different. In addition, the intensity of light is also different at different times, which further leads to different degrees of reflection of license plates of different colors at different times. Therefore, capturing images of vehicles with different license plate colors at different times with a fixed exposure value may cause the brightness value of the license plate number in the captured vehicle image to be too high or too low, thereby reducing the quality of the captured image.

[0097] In order to improve the quality of the captured images, the embodiments of the present application provide an exposure value updating method, device, electronic device, and storage medium, which are described in detail below.

[0098] The present application provides an exposure value updating method, which can be applied to electronic devices such as servers, NVRs (Network Video Recorders), DVRs (Digital Video Recorders), and CVRs (Central Video Recorders), and can also be directly applied to image acquisition devices. The method includes:

[0099] Extracting the brightness value and color of the license plate in the collected vehicle image;

[0100] According to the time sequence of capturing the vehicle images and the colors of the extracted license plates, the brightness values ​​of the extracted license plates are stored to obtain brightness groups, wherein each brightness group includes: the brightness values ​​of corresponding license plates with the same time sequence and different colors;

[0101] Determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group;

[0102] determining an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight;

[0103] The expected brightness value is used as the currently updated exposure value for vehicle image acquisition.

[0104] In the above scheme, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained, which are used as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the scheme provided by the above embodiment can improve the quality of the captured images.

[0105] See also Figure 1 , Figure 1 A flowchart of an exposure value updating method provided in an embodiment of the present application includes the following steps S101-S105:

[0106] S101, extracting the brightness value and color of the license plate in the collected vehicle image.

[0107] Specifically, an image acquisition device may be used to capture vehicle images of vehicles on the road. After obtaining the above image, the license plate area where the license plate is located in the image is identified, and the brightness value and color of the license plate are extracted based on the pixel values ​​of the pixel points in the license plate area.

[0108] The image acquisition device is used to capture images of vehicles on the road. The image acquisition device can be an electric police camera, a bayonet camera, etc. on the road. The resolution can be 3 million pixels, 4 million pixels, 9 million pixels, etc. The image acquisition device can be installed on a gantry or monitoring pole on the side of the road. Figure 2 , Figure 2 A schematic diagram of a vehicle image provided in an embodiment of the present application.

[0109] See also Figure 3 , Figure 3Schematic diagram of license plates of different colors provided in an embodiment of the present application. Different types of vehicles usually have different license plate colors, and the front and rear license plates of the same vehicle may also have different colors. For example, civilian fuel vehicles have blue license plates, new energy vehicles have green license plates, vehicles in Hong Kong and Macau have black license plates, government vehicles have white license plates, and large trucks and motorcycles have yellow license plates.

[0110] S102 , storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a brightness group.

[0111] Each brightness group contains the brightness values ​​of license plates with the same time sequence but different colors. For example, assuming the license plate colors include blue, yellow, green, and black, the brightness value of the most recently extracted blue license plate is V1, the brightness value of the most recently extracted yellow license plate is V2, the brightness value of the most recently extracted green license plate is V3, and the brightness value of the most recently extracted black license plate is V4. The vehicle images corresponding to V1, V2, V3, and V4 were acquired in the same time sequence, so these V1, V2, V3, and V4 can be considered a brightness group.

[0112] Specifically, for each license plate color, the brightness value of that license plate color can be stored according to the order in which the corresponding vehicle image of the license plate color was captured. For example, the brightness values ​​of license plates of different colors can be stored in different queues or lists according to the corresponding time sequence. Then, from the stored brightness values ​​of license plates of different colors, the brightness values ​​of license plates of different colors with the same time sequence in which the corresponding vehicle images were captured are determined as a brightness group.

[0113] In one embodiment of the present application, the extracted brightness value can be added to the target queue according to the color of the extracted license plate, and the brightness values ​​of the license plates of each color with the same corresponding time sequence can be determined from each target queue as a brightness group.

[0114] The target queue is used to store the brightness values ​​of license plates of different colors in the order of the acquisition time of the corresponding vehicle images. For each color, the target queue stores the brightness values ​​of the latest extracted preset number of license plates of that color.

[0115] The above-mentioned preset number can be 10, 15, 20, etc.

[0116] See Table 1 below, which is a schematic diagram of target queues corresponding to license plates of different colors provided in an embodiment of the present application:

[0117] Table 1

[0118]

[0119] As shown in Table 1 above, the colors of license plates include blue, green, and yellow. Each color corresponds to a target queue. Each target queue is used to store the brightness values ​​of 6 corresponding colors of license plates in a first-in-first-out manner according to the order of the acquisition time of the corresponding vehicle images.

[0120] Each brightness group contains the brightness values ​​of license plates of different colors that were captured in the same order. Taking Table 1 as an example, each row represents a target queue corresponding to a license plate of a different color. Each target queue stores the brightness values ​​of license plates of different colors in a first-in, first-out manner, in the order in which the corresponding vehicle images were captured. In other words, the brightness values ​​in each column of Table 1 represent the brightness values ​​of license plates of different colors that were captured in the same order. Therefore, each column of brightness values ​​in Table 1 can be considered a brightness group.

[0121] Specifically, each license plate color corresponds to a target queue, which is used to store a preset number of brightness values ​​for license plates of that color in a first-in, first-out manner, in the order of the time the corresponding vehicle images were captured. After extracting the license plate color and brightness values ​​in step S101, the target queue corresponding to the extracted color is searched from target queues corresponding to multiple colors. The extracted brightness values ​​are then added to the target queue in the corresponding chronological order, thereby updating the target queue. The brightness values ​​of license plates of various colors with the same chronological order are then determined from different target queues to obtain various brightness groups.

[0122] S103 , determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group.

[0123] The weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group.

[0124] Specifically, the exposure value of the image acquisition device is dynamically updated and may change at different times. Therefore, different brightness groups can reflect the brightness values ​​of license plates of different colors in vehicle images captured by the image acquisition device at different exposure times. The degree of dispersion of the brightness values ​​within each brightness group is used to characterize the degree of difference between the brightness values ​​within the brightness group. The greater the degree of dispersion, the greater the degree of difference between the brightness values ​​within the brightness group, and thus the greater the importance of the brightness values ​​within the brightness group, and the greater the role of the brightness values ​​within the brightness group in subsequently determining the expected brightness value of the license plate in the vehicle image. The smaller the degree of dispersion, the smaller the degree of difference between the brightness values ​​within the brightness group, and thus the less important the brightness values ​​within the brightness group, and the less role of the brightness values ​​within the brightness group in subsequently determining the expected brightness value of the license plate in the vehicle image.

[0125] Based on this, the degree of discreteness of the brightness values ​​in each brightness group can be determined first, and then the importance of each brightness value in the target brightness group where the brightness value extracted in step S101 is located can be calculated according to the degree of discreteness of the brightness values ​​in each brightness group, as the weight of each brightness value in the above target brightness group.

[0126] In one embodiment of the present application, a preset statistical algorithm may be used to calculate the degree of dispersion of brightness values ​​within each brightness group, wherein the statistical algorithm may be a normal distribution algorithm, a Weibull distribution algorithm, a variance algorithm, a standard deviation algorithm, and the like.

[0127] In one embodiment of the present application, the ratio of the discrete degree of the brightness values ​​in the target brightness group where the extracted brightness value is located to the total discrete degree can be calculated as the weight of the brightness value in the target brightness group.

[0128] The total discreteness is the sum of the discreteness corresponding to each brightness group.

[0129] Specifically, the weight W of the brightness value in the target brightness group can be calculated using the following formula: j :

[0130]

[0131] Among them, the above g j represents the degree of dispersion of the brightness values ​​in the jth brightness group, and m represents the number of brightness groups obtained.

[0132] In addition, the discrete degrees corresponding to the target brightness group can also be determined in descending order among the discrete degrees corresponding to all brightness groups, and the weight corresponding to the determined size order can be found from the correspondence between the preset size order and the weight, and used as the weight of the brightness value in the target brightness group.

[0133] For example, assuming that the discrete degree corresponding to the target brightness group is 25, and the discrete degrees corresponding to other brightness groups are -5, 8, 56, and 23 respectively, it can be determined that the discrete degree corresponding to the target brightness group is ranked second. In the preset correspondence, the weight corresponding to order 2 is 0.45, so it can be determined that the weight of each brightness value in the target brightness group is 0.45.

[0134] S104: Determine an expected brightness value of the license plate in the captured vehicle image according to the extracted brightness value and the determined weight.

[0135] Specifically, the weight determined in step S103 can reflect the importance of the brightness value in the target brightness group. Based on the importance and the brightness value extracted in step S101, the expected brightness value of the license plate in the obtained vehicle image can be calculated. Subsequently, the expected brightness value can be used as the expected exposure value of the image acquisition device, and then the current exposure value of the image acquisition device can be updated.

[0136] In one embodiment of the present application, when determining the expected brightness value, the product between the weight and the extracted brightness value can be calculated as the expected brightness value; or the product of the weight and the preset parameter can be calculated, and the product and the extracted brightness value are summed to obtain the expected brightness value, etc. The embodiment of the present application is not limited to this.

[0137] S105 , capturing a vehicle image using the expected brightness value as the currently updated exposure value.

[0138] Specifically, the above-mentioned expected brightness value can be used as the expected exposure value, and the current exposure value of the image acquisition device can be updated to the above-mentioned expected exposure value, so that the image acquisition device captures the vehicle image according to the updated exposure value, ensuring that the brightness value of the license plate in the next vehicle image captured can approach the above-mentioned expected brightness value.

[0139] As mentioned above, license plates of different colors reflect light to different degrees, so even if the image is captured under the same lighting conditions at the same time and with the same exposure value, the brightness values ​​of license plates of different colors in the obtained vehicle images will be different. Figure 4 , Figure 4 This is a schematic diagram of license plates of different colors in the same vehicle image provided by the embodiment of the present application. It can be seen that the license plate of the vehicle on the left side of the image is relatively blurred, while the license plate of the vehicle on the right side is relatively clear. Due to the influence of lighting conditions, the degree of reflection of the license plate, and the exposure value of the image acquisition device, the license plate in the captured vehicle image may be overexposed or underexposed. For example, see Figure 5 , Figure 5 This is a schematic diagram of an overexposed license plate in a vehicle image provided by an embodiment of the present application. When the license plate is overexposed, the brightness value of the license plate will be too high, making it difficult to recognize the license plate number later; see Figure 6 , Figure 6 This is a schematic diagram of underexposure of a license plate in a vehicle image provided in an embodiment of the present application. When the license plate is underexposed, the brightness value of the license plate will be too low, making it difficult to subsequently identify the license plate number.

[0140] In the exposure value updating scheme provided in the above embodiment, the brightness value and color of the license plate in the captured vehicle image can be extracted; the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group, wherein each brightness group includes: the brightness values ​​of license plates with the same corresponding time sequence but different colors; according to the discrete degree of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs is determined, wherein the weight of the brightness value in each brightness group is proportional to the discrete degree of the brightness value in the brightness group; according to the extracted brightness value and the determined weight, the expected brightness value of the license plate in the captured vehicle image is determined; and the expected brightness value is used as the currently updated exposure value for vehicle image capture. In this way, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the solution provided by the above embodiment can improve the quality of the captured images.

[0141] In one embodiment of the present application, when obtaining the brightness group in step S102, the following steps may be performed:

[0142] When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group.

[0143] The exposure qualification condition mentioned above means that the brightness value meets the expected condition, for example, the brightness value may be greater than 100, the brightness value may be less than 180, or the brightness value may be between 110-140.

[0144] Specifically, when the brightness value of the license plate meets the above-mentioned exposure qualification condition, it is considered that the brightness value of the license plate meets expectations, and the license plate number of the vehicle can be relatively accurately recognized based on the vehicle image. In this case, it means that the quality of the vehicle image captured by the image acquisition device at the current exposure value is high, and there is no need to update the exposure value of the image acquisition device. Therefore, the brightness value does not need to be stored, and there is no need to obtain a brightness group based on the brightness value.

[0145] When the brightness value of the license plate does not meet the above-mentioned exposure qualification conditions, it is considered that the brightness value of the license plate does not meet expectations, and it is difficult to accurately identify the vehicle license plate number based on the vehicle image. In this case, it means that the quality of the vehicle image captured by the image acquisition device at the current exposure value is low, and the exposure value of the image acquisition device needs to be updated. Therefore, the above-mentioned brightness value can be stored, and then a brightness group can be obtained based on the brightness value.

[0146] In one embodiment of the present application, the above-mentioned exposure qualification condition is used to indicate the minimum brightness value and the maximum brightness value that meet the brightness requirements. When the brightness value of the license plate is between the above-mentioned minimum brightness value and the maximum brightness value, the brightness value is considered to meet the exposure qualification condition, and the license plate number can be more accurately identified based on the vehicle image; when the brightness value of the license plate is less than the above-mentioned minimum brightness value, or higher than the above-mentioned maximum brightness value, the brightness value is considered to not meet the exposure qualification condition, and it is difficult to accurately identify the license plate number based on the vehicle image.

[0147] In one embodiment of the present application, when the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a first brightness group.

[0148] The brightness value stored in the first brightness group is lower than the minimum brightness value.

[0149] Specifically, after obtaining the color and brightness value of the license plate in step S101, it can be determined whether the brightness value is lower than the above-mentioned minimum brightness value. If so, the brightness value of the extracted license plate can be stored according to the time sequence of collecting vehicle images and the color of the extracted license plate to obtain the first brightness group.

[0150] Correspondingly, when the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a second brightness group.

[0151] The brightness value stored in the second brightness group is higher than the maximum brightness value.

[0152] Specifically, after obtaining the color and brightness value of the license plate in step S101, it can be determined whether the brightness value is higher than the above-mentioned maximum brightness value. If so, the brightness value of the extracted license plate can be stored according to the time sequence of collecting vehicle images and the color of the extracted license plate to obtain a second brightness group.

[0153] In one embodiment of the present application, when the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, the extracted brightness value is added to the first target queue according to the acquisition time sequence of the extracted color and the corresponding vehicle image, and the first brightness group is obtained from the first target queue.

[0154] The first target queue is used to store: brightness values ​​of license plates of different colors that are lower than the minimum brightness value.

[0155] Specifically, after obtaining the color and brightness value of the license plate in step S101, it can be determined whether the brightness value is less than the above-mentioned minimum brightness value. If so, the first target queue corresponding to the above-mentioned color is determined, which is used to store brightness values ​​lower than the minimum brightness value. Then, the above-mentioned brightness values ​​are added to the determined first target queue in the order of the acquisition time of the corresponding vehicle images, and the first brightness group is obtained from the first target queue.

[0156] For example, see Table 2 below, which is a schematic diagram of a first target queue corresponding to license plates of different colors provided in an embodiment of the present application:

[0157] Table 2

[0158]

[0159] As shown in Table 2 above, assuming that the minimum brightness value is 110, the colors of license plates include blue, green, and yellow, and each color corresponds to a first target queue. Each first target queue is used to store 6 license plates of corresponding colors with brightness values ​​lower than 110 in a first-in-first-out manner according to the order of the acquisition time of the corresponding vehicle images. The brightness value of each column in Table 2 above can be used as a first brightness group.

[0160] In one embodiment of the present application, when the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the extracted brightness value is added to the second target queue according to the acquisition time sequence of the extracted color and the corresponding vehicle image, and a second brightness group is obtained from the second target queue.

[0161] The second target queue is used to store: brightness values ​​of license plates of different colors that are higher than the maximum brightness value.

[0162] Specifically, after obtaining the color and brightness value of the license plate in step S101, it can be determined whether the brightness value is greater than the above-mentioned maximum brightness value. If so, a second target queue corresponding to the above-mentioned color is determined, which is used to store brightness values ​​higher than the maximum brightness value. Then, the above-mentioned brightness values ​​are added to the determined second target queue in the order of the acquisition time of the corresponding vehicle images, and the second brightness group is subsequently obtained from the second target queue.

[0163] For example, see Table 3 below, which is a schematic diagram of a second target queue corresponding to license plates of different colors provided in an embodiment of the present application:

[0164] Table 3

[0165]

[0166] As shown in Table 3 above, assuming that the minimum brightness value is 140, the colors of the license plates include blue, green, and yellow, and each color corresponds to a second target queue. Each second target queue is used to store 6 license plates of corresponding colors with brightness values ​​higher than 140 in a first-in-first-out manner according to the order of the acquisition time of the corresponding vehicle images. The brightness value of each column in Table 3 above can be used as a second brightness group.

[0167] In one embodiment of the present application, when determining the expected brightness value in the above step S104, the extracted brightness value can be normalized; based on the determined weight and the normalized brightness value, the expected brightness value of the license plate in the captured vehicle image is calculated.

[0168] Specifically, for the brightness value extracted in step S101, the extracted brightness value can be normalized according to other stored brightness values, and then the expected brightness value of the license plate in the vehicle image is calculated based on the normalized brightness value and the weight determined in step S103.

[0169] In one embodiment of the present application, when normalizing the extracted brightness value, the normalization may be performed in different ways depending on whether the brightness value is lower than the minimum brightness value or higher than the maximum brightness value, which is described in detail below.

[0170] In one embodiment of the present application, when the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, a first difference between the extracted brightness value and the minimum brightness value is calculated, a first ratio of the first difference to the maximum difference is determined, and the sum of the first ratio and a preset normalization parameter is calculated to obtain the normalized brightness value.

[0171] The minimum brightness value is: the minimum brightness value among all stored brightness values;

[0172] The maximum difference is: the difference between the largest maximum brightness value and the minimum brightness value among the stored brightness values.

[0173] Specifically, when the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, the extracted brightness value may be normalized according to the following formula:

[0174]

[0175] Among them, i represents the number of different colors, the number of different colors is n, and the value of i is 1, 2, 3...n; j represents the number of different brightness groups, the value range of j is 1~m, and m represents the number of brightness groups obtained. ij Indicates: the brightness value of the license plate with color number i in the jth brightness group, c1 represents the preset normalization parameter, the value of c1 can be 1, 0.5, 2, etc., X' ij It represents the result of normalizing the brightness value of the license plate with color number i in the jth brightness group.

[0176] Taking Table 2 above as an example, the number of different colors is 3, that is, n is 3. It can be considered that blue is numbered 1, green is numbered 2, and yellow is numbered 3. The number of brightness values ​​corresponding to each color license plate is 6, and the number of brightness groups m is 6. The brightness group with the earliest time is numbered 1, and the numbers of each brightness group are set in turn. The brightness group with the latest time is numbered 6.

[0177] In one embodiment of the present application, when the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, a second difference between the maximum brightness value and the extracted brightness value is calculated; a second ratio of the second difference to the maximum difference is determined, and the sum of the second ratio and a preset normalization parameter is calculated to obtain the normalized brightness value.

[0178] Specifically, when the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the extracted brightness value may be normalized according to the following formula:

[0179]

[0180] Among them, c2 represents a preset normalization parameter, and the value of c2 can be 1, 0.5, 2, etc., and can be equal to the value of c1 or different from the value of c1. The embodiment of the present application is not limited to this.

[0181] In one embodiment of the present application, when calculating the expected brightness value in step S104, based on the situation in which the brightness value extracted in step S101 is lower than the minimum brightness value or higher than the maximum brightness value, the expected brightness value can be calculated in different ways, which are described in detail below.

[0182] In one embodiment of the present application, the product of the normalized brightness value and the determined weight is calculated as the brightness adjustment coefficient; the coefficient difference between the preset maximum adjustment coefficient and the brightness adjustment coefficient is calculated, and the product of the coefficient difference and the preset brightness adjustment amplitude is determined to obtain the brightness adjustment value; when the extracted brightness value is lower than the minimum brightness value, the difference between the extracted brightness value and the brightness adjustment value is calculated to obtain the expected brightness value of the license plate in the captured vehicle image.

[0183] Specifically, when the extracted brightness value is lower than the minimum brightness value, the expected brightness value Y can be calculated according to the following formula:

[0184] S h =W j *X' h

[0185] R=(1-S h )*c3

[0186] Y=X h -R

[0187] Among them, X' h Represents the result of normalization of the extracted brightness value, W j represents the weight obtained in step S104, h h Indicates the brightness adjustment coefficient, 1 is the preset maximum adjustment coefficient, c3 indicates the preset brightness adjustment range, the value of c3 can be 100, 50, 120, etc., R indicates the brightness adjustment value, X h Indicates the extracted brightness value.

[0188] In one embodiment of the present application, when the extracted brightness value is higher than the maximum brightness value, the sum of the extracted brightness value and the brightness adjustment value is calculated to obtain the expected brightness value of the license plate in the captured vehicle image.

[0189] Specifically, when the extracted brightness value is higher than the maximum brightness value, the expected brightness value Y can be calculated according to the following formula:

[0190] Y=X h +R

[0191] In one embodiment of the present application, when determining the weight in the above-mentioned step S103, for each brightness value in the brightness group, the proportion of the brightness value in the brightness group to which the brightness value belongs can be calculated; for each brightness group, the proportion of each brightness value in the brightness group can be used to calculate the degree of dispersion of the brightness values ​​in the brightness group; and based on the degree of dispersion of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs can be determined.

[0192] Specifically, for each brightness value in each brightness group, the ratio of the brightness value to the sum of all brightness values ​​in the brightness group can be calculated as the proportion of the brightness value in the brightness group; for the brightness group, the proportion corresponding to each brightness value in the brightness group can be used to determine the degree of discreteness of each brightness value in the brightness group, and then according to the degree of discreteness of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs can be determined.

[0193] In one embodiment of the present application, when calculating the degree of discreteness, the information entropy of the brightness group can be calculated for each brightness group based on the proportion corresponding to each brightness value in the brightness group; and the difference between the preset entropy value threshold and the information entropy is determined as the degree of discreteness of the brightness value in the brightness group.

[0194] Specifically, the proportion P of each brightness value in the brightness group to which it belongs can be calculated using the following formula: ij :

[0195]

[0196] The value of j ranges from 1 to m. The above formula can be used to calculate the proportion of each brightness value in each brightness group.

[0197] For each brightness group, the discrete degree g of the brightness value within the brightness group can be calculated according to the following formula: j :

[0198]

[0199] g j =c5-e j

[0200] Among them, i represents the number of different colors, the number of different colors is n, j represents the number of different brightness groups, the value range of j is 1 to m, m represents the number of brightness groups obtained, P ij Indicates: the proportion of the brightness value of the license plate with color number i in the jth brightness group, e j represents the information entropy of the brightness value in the j-th brightness group. The information entropy can reflect the degree of discreteness of the brightness value in the j-th brightness group. The larger the information entropy, the smaller the discreteness, and the smaller the information entropy, the larger the discreteness. c5 represents the preset entropy threshold. The value of c5 can be 1, 0.9, 1.2, etc. k represents: a constant determined based on the number of brightness groups m. The value of k can be greater than 0.

[0201] In one embodiment of the present application, the value of k can be calculated according to the following formula:

[0202] k=1 / ln m

[0203] When the above formula is used to determine the value of k, k can be greater than 0, and e j The value range is between 0 and 1, and the discrete degree g j The value range of is also between 0 and 1, which is convenient for determining the importance of the weight based on the above discrete degree.

[0204] See also Figure 7 , Figure 7 A flowchart of another exposure value updating method provided in an embodiment of the present application is provided. The method includes the following steps S701-S712:

[0205] S701, obtaining a vehicle image captured by an image capture device, extracting the brightness value of the license plate in the vehicle image, and extracting the color of the license plate in the vehicle image.

[0206] S702: When the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, the extracted brightness value is added to the first target queue according to the extracted color.

[0207] The first target queue is used to store: a preset number of brightness values ​​of license plates of different colors that are lower than a minimum brightness value.

[0208] S703 , normalizing the extracted brightness values ​​in a manner of normalizing brightness values ​​that are lower than the minimum brightness value required by the exposure qualification condition.

[0209] Specifically, when the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, the extracted brightness value is normalized according to the following formula:

[0210]

[0211] Among them, i represents the number of different colors, the number of different colors is n, j represents the number of different brightness groups, the value range of j is 1 to m, m represents the preset number, X ij Indicates: the brightness value of the license plate with color number i in the jth brightness group, X' ij It represents the result of normalizing the brightness value of the license plate with color number i in the jth brightness group.

[0212] S704: When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the extracted brightness value is added to the second target queue according to the extracted color.

[0213] The second target queue is used to store: a preset number of brightness values ​​of license plates of different colors that are higher than the maximum brightness value.

[0214] S705 , normalizing the extracted brightness values ​​in a manner of normalizing the brightness values ​​that are higher than the highest brightness value required by the exposure qualification condition.

[0215] Specifically, when the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the extracted brightness value is normalized according to the following formula:

[0216]

[0217] S706 , for each brightness value in the target queue, calculate the proportion of the brightness value in the brightness group to which the brightness value belongs.

[0218] Specifically, the proportion P of each brightness value in the brightness group to which it belongs can be calculated using the following formula: ij :

[0219]

[0220] The value of j ranges from 1 to m. The above formula can be used to calculate the proportion of each brightness value in each brightness group.

[0221] S707 , for each brightness group, using the proportion of each brightness value in the brightness group, calculate the information entropy of the brightness values ​​in the brightness group.

[0222] Specifically, for each brightness group, the information entropy e of the brightness value in the brightness group is calculated according to the following formula: j :

[0223]

[0224] k=1 / ln m

[0225] Among them, i represents the number of different colors, the number of different colors is n, j represents the number of different brightness groups, the value range of j is 1 to m, m represents the preset number, P ij Indicates: the proportion of the brightness value of the license plate with color number i in the jth brightness group, e j represents the information entropy of the brightness value in the jth brightness group.

[0226] S708 , calculating the discreteness of each brightness group based on the information entropy.

[0227] Specifically, for each brightness group, the discrete degree g of the brightness value in the brightness group is calculated according to the following formula: j :

[0228] g j =1-e j

[0229] S709 , calculating the ratio of the discrete degree of the brightness values ​​in the target brightness group where the extracted brightness value belongs to the total discrete degree, and using the ratio as the weight of the brightness value in the target brightness group.

[0230] The total discreteness is the sum of the discreteness corresponding to each brightness group.

[0231] Specifically, the weight W of the brightness value in the target brightness group can be calculated using the following formula: j :

[0232]

[0233] Among them, the above g j represents the discrete degree of brightness values ​​in the jth brightness group, and m represents the preset number.

[0234] S710 , when the extracted brightness value is lower than the minimum brightness value, calculating the expected brightness value of the license plate in the vehicle image captured by the image capture device by using the brightness value lower than the minimum brightness value to calculate the expected brightness value.

[0235] Specifically, the expected brightness value Y is calculated using the following formula:

[0236] S h =W j *X' h

[0237] Y=X h -(1-S h )*100

[0238] Among them, X' h Represents the result of normalization of the extracted brightness value, W j Represents the obtained weight.

[0239] S711 , when the extracted brightness value is higher than the maximum brightness value, calculating the expected brightness value of the license plate in the vehicle image captured by the image capture device by using the brightness value higher than the maximum brightness value to calculate the expected brightness value.

[0240] Specifically, the expected brightness value Y is calculated using the following formula:

[0241] Y=X h +(1-S h )*100

[0242] S712: Update the current exposure value of the image acquisition device by using the expected brightness value as the expected exposure value.

[0243] In the exposure value updating scheme provided in the above embodiment, the brightness value and color of the license plate in the captured vehicle image can be extracted; the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group, wherein each brightness group includes: the brightness values ​​of license plates with the same corresponding time sequence but different colors; according to the discrete degree of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs is determined, wherein the weight of the brightness value in each brightness group is proportional to the discrete degree of the brightness value in the brightness group; according to the extracted brightness value and the determined weight, the expected brightness value of the license plate in the captured vehicle image is determined; and the expected brightness value is used as the currently updated exposure value for vehicle image capture. In this way, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the solution provided by the above embodiment can improve the quality of the captured images.

[0244] Corresponding to the above-mentioned exposure value updating method, an embodiment of the present application further provides an exposure value updating device, which is described in detail below.

[0245] See also Figure 8 , Figure 8 This is a schematic structural diagram of an exposure value updating device provided in an embodiment of the present application, the device comprising:

[0246] The image extraction module 801 is used to extract the brightness value and color of the license plate in the collected vehicle image;

[0247] The brightness group obtaining module 802 is configured to store the brightness values ​​of the extracted license plates according to the time sequence of the vehicle images and the colors of the extracted license plates to obtain brightness groups, wherein each brightness group includes the brightness values ​​of license plates with the same time sequence but different colors;

[0248] a weight determination module 803 for determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group;

[0249] An expected brightness value determination module 804 is used to determine an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight;

[0250] The exposure value updating module 805 is configured to use the expected brightness value as the currently updated exposure value to perform vehicle image acquisition.

[0251] In one embodiment of the present application, the brightness group obtaining module 802 is specifically configured to:

[0252] When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group.

[0253] In one embodiment of the present application, the brightness group obtaining module 802 is specifically configured to:

[0254] If the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a first brightness group, wherein the brightness values ​​stored in the first brightness group are lower than the minimum brightness value; and / or

[0255] When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a second brightness group, wherein the brightness value stored in the second brightness group is higher than the maximum brightness value.

[0256] In one embodiment of the present application, the expected brightness value determination module 804 includes:

[0257] A brightness normalization unit, used for normalizing the extracted brightness value;

[0258] The expected brightness value determining unit is used to calculate the expected brightness value of the license plate in the collected vehicle image according to the determined weight and the brightness value after normalization.

[0259] In one embodiment of the present application, the brightness normalization unit is specifically configured to:

[0260] When the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, calculating a first difference between the extracted brightness value and the minimum brightness value, wherein the minimum brightness value is: the minimum brightness value among the stored brightness values;

[0261] determining a first ratio of the first difference value to the maximum difference value, calculating the sum of the first ratio and a preset normalization parameter to obtain a normalized brightness value, wherein the maximum difference value is: a difference between a maximum brightness value of each stored brightness value and the minimum brightness value;

[0262] and / or

[0263] When the extracted brightness value is higher than the highest brightness value required by the exposure qualification condition, calculating a second difference between the maximum brightness value and the extracted brightness value;

[0264] A second ratio of the second difference to the maximum difference is determined, and a sum of the second ratio and a preset normalization parameter is calculated to obtain a normalized brightness value.

[0265] In one embodiment of the present application, the expected brightness value determination module 804 is specifically configured to:

[0266] Calculating the product of the normalized brightness value and the determined weight as the brightness adjustment coefficient;

[0267] Calculating a coefficient difference between a preset maximum adjustment coefficient and the brightness adjustment coefficient, determining a product of the coefficient difference and a preset brightness adjustment amplitude to obtain a brightness adjustment value;

[0268] If the extracted brightness value is lower than the minimum brightness value, calculating the difference between the extracted brightness value and the brightness adjustment value to obtain an expected brightness value of the license plate in the captured vehicle image;

[0269] and / or

[0270] In the case that the extracted brightness value is higher than the maximum brightness value, a sum of the extracted brightness value and the brightness adjustment value is calculated to obtain an expected brightness value of the license plate in the captured vehicle image.

[0271] In one embodiment of the present application, the weight determination module 803 includes:

[0272] a proportion calculation unit, configured to calculate, for each brightness value in the brightness group, a proportion of the brightness value in the brightness group to which the brightness value belongs;

[0273] a dispersion degree calculation unit, configured to calculate, for each brightness group, a dispersion degree of the brightness values ​​within the brightness group using a proportion of each brightness value in the brightness group;

[0274] The weight determination unit is used to determine the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group.

[0275] In one embodiment of the present application, the discrete degree calculation unit is specifically configured to:

[0276] For each brightness group, calculate the information entropy of the brightness group based on the corresponding proportions of each brightness value in the brightness group;

[0277] A difference between a preset entropy value threshold and the information entropy is determined as a discrete degree of the brightness values ​​within the brightness group.

[0278] In one embodiment of the present application, the weight determination module 803 is specifically configured to:

[0279] Calculate the ratio of the discrete degree of the brightness value in the target brightness group where the extracted brightness value belongs to the total discrete degree as the weight of the brightness value in the target brightness group, wherein the total discrete degree is: the sum of the discrete degrees corresponding to each brightness group.

[0280] In the exposure value updating scheme provided in the above embodiment, the brightness value and color of the license plate in the captured vehicle image can be extracted; the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group, wherein each brightness group includes: the brightness values ​​of license plates with the same corresponding time sequence but different colors; according to the discrete degree of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs is determined, wherein the weight of the brightness value in each brightness group is proportional to the discrete degree of the brightness value in the brightness group; according to the extracted brightness value and the determined weight, the expected brightness value of the license plate in the captured vehicle image is determined; and the expected brightness value is used as the currently updated exposure value for vehicle image capture. In this way, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the solution provided by the above embodiment can improve the quality of the captured images.

[0281] The present application also provides an electronic device, such as Figure 9 As shown, it includes a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0282] Memory 903, used for storing computer programs;

[0283] The processor 901 is configured to implement an exposure value updating method when executing a program stored in the memory 903 .

[0284] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0285] The communication interface is used for communication between the above electronic device and other devices.

[0286] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0287] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0288] In another embodiment provided in the present application, a computer-readable storage medium is further provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of any of the above-mentioned exposure value updating methods are implemented.

[0289] In another embodiment provided by the present application, a computer program product including instructions is further provided, which, when executed on a computer, enables the computer to execute any exposure value updating method in the above embodiments.

[0290] In the exposure value updating scheme provided in the above embodiment, the brightness value and color of the license plate in the captured vehicle image can be extracted; the brightness value of the extracted license plate is stored according to the time sequence of capturing the vehicle image and the color of the extracted license plate to obtain a brightness group, wherein each brightness group includes: the brightness values ​​of license plates with the same corresponding time sequence but different colors; according to the discrete degree of the brightness values ​​in each brightness group, the weight of each brightness value in the target brightness group to which the extracted brightness value belongs is determined, wherein the weight of the brightness value in each brightness group is proportional to the discrete degree of the brightness value in the brightness group; according to the extracted brightness value and the determined weight, the expected brightness value of the license plate in the captured vehicle image is determined; and the expected brightness value is used as the currently updated exposure value for vehicle image capture. In this way, each stored brightness group contains the brightness values ​​of license plates of different colors at different times that have been captured by the image capture device. Based on the brightness groups, the expected brightness values ​​of license plates of different colors at the current moment can be obtained as the expected brightness values ​​of license plates of different colors at the next moment. The exposure values ​​of the image capture device can then be updated using the expected brightness values, so that when the image capture device captures images based on the updated exposure values, the brightness values ​​of license plates of different colors in the obtained vehicle images can all meet expectations. It can be seen that the application of the solution provided by the above embodiment can improve the quality of the captured images.

[0291] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0292] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0293] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, since the apparatus embodiments, electronic device embodiments, computer-readable storage medium embodiments, and computer program product embodiments are generally similar to the method embodiments, their descriptions are relatively simple. For related portions, reference can be made to the descriptions of the method embodiments.

[0294] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the scope of protection of the present application.

Claims

1. A method for updating an exposure value, characterized in that: The method comprises: Extracting the brightness value and color of the license plate in the collected vehicle image; According to the time sequence of collecting the vehicle images and the color of the extracted license plates, the brightness values ​​of the extracted license plates are stored to obtain brightness groups, wherein each brightness group includes: the brightness values ​​of corresponding license plates with the same time sequence and different colors; Determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group; determining an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight; The expected brightness value is used as the currently updated exposure value to capture the vehicle image.

2. The method according to claim 1, characterized in that The step of storing the brightness values ​​of the extracted license plates according to the time sequence of collecting the vehicle images and the colors of the extracted license plates to obtain a brightness group includes: When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group.

3. The method according to claim 2, characterized in that When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group, including: If the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a first brightness group, wherein the brightness values ​​stored in the first brightness group are lower than the minimum brightness value; and / or When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a second brightness group, wherein the brightness value stored in the second brightness group is higher than the maximum brightness value.

4. The method according to claim 3, characterized in that Determining the expected brightness value of the license plate in the collected vehicle image based on the extracted brightness value and the determined weight includes: Normalizing the extracted brightness values; The expected brightness value of the license plate in the captured vehicle image is calculated based on the determined weights and the normalized brightness value.

5. The method according to claim 4, characterized in that The normalizing process of the extracted brightness value includes: When the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, calculating a first difference between the extracted brightness value and the minimum brightness value, wherein the minimum brightness value is: the minimum brightness value among the stored brightness values; determining a first ratio of the first difference value to the maximum difference value, calculating the sum of the first ratio and a preset normalization parameter to obtain a normalized brightness value, wherein the maximum difference value is: a difference between a maximum brightness value of each stored brightness value and the minimum brightness value; and / or When the extracted brightness value is higher than the highest brightness value required by the exposure qualification condition, calculating a second difference between the maximum brightness value and the extracted brightness value; A second ratio of the second difference to the maximum difference is determined, and a sum of the second ratio and a preset normalization parameter is calculated to obtain a normalized brightness value.

6. The method according to claim 3, characterized in that Determining the expected brightness value of the license plate in the collected vehicle image based on the extracted brightness value and the determined weight includes: Calculating the product of the normalized brightness value and the determined weight as the brightness adjustment coefficient; Calculating a coefficient difference between a preset maximum adjustment coefficient and the brightness adjustment coefficient, determining a product of the coefficient difference and a preset brightness adjustment amplitude to obtain a brightness adjustment value; If the extracted brightness value is lower than the minimum brightness value, calculating the difference between the extracted brightness value and the brightness adjustment value to obtain an expected brightness value of the license plate in the captured vehicle image; and / or In the case that the extracted brightness value is higher than the maximum brightness value, a sum of the extracted brightness value and the brightness adjustment value is calculated to obtain an expected brightness value of the license plate in the captured vehicle image.

7. The method according to any one of claims 1 to 6, characterized in that The step of determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group includes: For each brightness value in the brightness group, calculating the proportion of the brightness value in the brightness group to which the brightness value belongs; For each brightness group, the dispersion of the brightness values ​​in the brightness group is calculated using the proportion of each brightness value in the brightness group; The weights of the respective brightness values ​​in the target brightness group to which the extracted brightness value belongs are determined according to the degree of dispersion of the brightness values ​​in each brightness group.

8. The method according to claim 7, characterized in that The step of calculating the dispersion of the brightness values ​​in each brightness group by using the proportion of each brightness value in the brightness group includes: For each brightness group, calculate the information entropy of the brightness group based on the corresponding proportions of each brightness value in the brightness group; A difference between a preset entropy value threshold and the information entropy is determined as a discrete degree of the brightness values ​​within the brightness group.

9. The method according to any one of claims 1 to 6, characterized in that The step of determining the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group includes: Calculate the ratio of the discrete degree of the brightness value in the target brightness group where the extracted brightness value belongs to the total discrete degree as the weight of the brightness value in the target brightness group, wherein the total discrete degree is: the sum of the discrete degrees corresponding to each brightness group.

10. An exposure value updating device, characterized in that: The device comprises: An image extraction module is used to extract the brightness value and color of the license plate in the collected vehicle image; a brightness group obtaining module for storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates, to obtain brightness groups, wherein each brightness group includes: brightness values ​​of license plates with the same time sequence and different colors; a weight determination module, configured to determine the weight of each brightness value in the target brightness group to which the extracted brightness value belongs based on the degree of dispersion of the brightness values ​​in each brightness group, wherein the weight of the brightness value in each brightness group is proportional to the degree of dispersion of the brightness values ​​in the brightness group; an expected brightness value determination module, configured to determine an expected brightness value of the license plate in the captured vehicle image based on the extracted brightness value and the determined weight; The exposure value updating module is used to use the expected brightness value as the currently updated exposure value to collect vehicle images.

11. The device according to claim 10, characterized in that The brightness group obtaining module is specifically used to: When the extracted brightness value does not meet the preset exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a brightness group.

12. The device according to claim 11, characterized in that The brightness group obtaining module is specifically used to: If the extracted brightness value is lower than the minimum brightness value required by the exposure qualification condition, storing the brightness values ​​of the extracted license plates according to the time sequence of capturing the vehicle images and the colors of the extracted license plates to obtain a first brightness group, wherein the brightness values ​​stored in the first brightness group are lower than the minimum brightness value; and / or When the extracted brightness value is higher than the maximum brightness value required by the exposure qualification condition, the brightness value of the extracted license plate is stored according to the time sequence of collecting the vehicle image and the color of the extracted license plate to obtain a second brightness group, wherein the brightness value stored in the second brightness group is higher than the maximum brightness value.

13. The device according to claim 12, characterized in that The expected brightness value determination module includes: A brightness normalization unit, used for normalizing the extracted brightness value; The expected brightness value determining unit is used to calculate the expected brightness value of the license plate in the collected vehicle image according to the determined weight and the brightness value after normalization.

14. The device according to claim 12, characterized in that The expected brightness value determination module is specifically configured to: Calculating the product of the normalized brightness value and the determined weight as the brightness adjustment coefficient; Calculating a coefficient difference between a preset maximum adjustment coefficient and the brightness adjustment coefficient, determining a product of the coefficient difference and a preset brightness adjustment amplitude to obtain a brightness adjustment value; If the extracted brightness value is lower than the minimum brightness value, calculating the difference between the extracted brightness value and the brightness adjustment value to obtain an expected brightness value of the license plate in the captured vehicle image; and / or In the case that the extracted brightness value is higher than the maximum brightness value, a sum of the extracted brightness value and the brightness adjustment value is calculated to obtain an expected brightness value of the license plate in the captured vehicle image.

15. The device according to any one of claims 10 to 14, characterized in that The weight determination module includes: a proportion calculation unit, configured to calculate, for each brightness value in the brightness group, a proportion of the brightness value in the brightness group to which the brightness value belongs; a dispersion degree calculation unit, configured to calculate, for each brightness group, a dispersion degree of the brightness values ​​within the brightness group using a proportion of each brightness value in the brightness group; The weight determination unit is used to determine the weight of each brightness value in the target brightness group to which the extracted brightness value belongs according to the discrete degree of the brightness values ​​in each brightness group.

16. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps described in any one of claims 1 to 9 when executing a program stored in a memory.

17. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any one of claims 1 to 9 are implemented.

Images