Exposure parameter adjusting method and device, electronic equipment and storage medium

Abstract

The invention provides an exposure parameter adjusting method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a license plate image from a received original image, and dividing the license plate image into a plurality of image blocks in response to the situation that the environment brightness information of the original image is smaller than a preset brightness threshold value, the plurality of image blocks comprise a target image block and a non-target image block, the first weight of the target image block is greater than the second weight of the non-target image block, determining the target image block corresponding to the license plate area from the plurality of image blocks, and determining the average brightness of the license plate image based on the plurality of image blocks, the first weight and the second weight, and in response to the condition that the average brightness is greater than the overexposure threshold, smoothly adjusting the image exposure parameter based on the exposure adjustment increment, thereby realizing division of the target image block and the non-target image block from the license plate image, reducing the interference of the non-license plate image area on the exposure brightness adjustment of the license plate image area, and improving the image brightness adjustment accuracy. Therefore, effective exposure brightness adjustment of the license plate image is completed.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more particularly to a method and apparatus for adjusting exposure parameters, an electronic device, and a storage medium. Background Technology

[0002] With the development of smart parking systems, license plate image overexposure is a common technical challenge. In low-light conditions at night, smart parking systems rely on supplementary lighting to ensure clear license plate image capture. However, metal license plates experience specular reflection when directly illuminated by supplementary lighting, leading to overexposure of the license plate image area and causing system misjudgment or blurry images.

[0003] In related technologies, after calculating the average brightness of the license plate image, the exposure of the license plate image is adjusted based on the difference between a preset brightness threshold and the average brightness. However, when calculating the average brightness, the average brightness of non-license plate image areas may usually be included, which makes the exposure brightness adjustment method of the license plate image area easily affected by the non-license plate image area. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for adjusting exposure parameters to solve problems in related technologies. It achieves the division of a license plate image into target image blocks and non-target image blocks, increases the first weight of the target image block to focus the exposure brightness adjustment on the target image block, decreases the second weight of the non-target image blocks to reduce the interference of non-license plate image areas on the exposure brightness adjustment of the license plate image area, and ensures the stability of the license plate image during the exposure brightness adjustment process through exposure increment adjustment, thereby completing the effective exposure brightness adjustment of the license plate image.

[0005] According to a first aspect of this disclosure, a method for adjusting exposure parameters is provided, comprising:

[0006] Acquire a license plate image, which is determined from the received original image;

[0007] In response to the ambient brightness information of the original image being less than a preset brightness threshold, the license plate image is divided into multiple image blocks, and a target image block corresponding to the license plate area is determined from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block;

[0008] The average brightness of the license plate image is determined based on the plurality of image blocks, the first weight, and the second weight;

[0009] In response to the average brightness being greater than the overexposure threshold, the image exposure parameters are smoothly adjusted based on the exposure adjustment increment.

[0010] In some embodiments of this disclosure, determining whether the ambient brightness information of the original image is less than the preset brightness threshold includes:

[0011] Obtain the current exposure value and dynamic exposure reference value of the original image, wherein the ambient brightness information includes the current exposure value and dynamic exposure reference value;

[0012] The current exposure reference value is determined based on the current exposure value and the dynamic exposure reference value;

[0013] Based on the comparison between the current exposure reference value and the current exposure value, it is determined whether the ambient brightness information of the original image is less than the preset brightness threshold.

[0014] In some embodiments of this disclosure, dividing the license plate image into multiple image blocks and determining the target image block corresponding to the license plate region from the multiple image blocks includes:

[0015] The license plate image is divided into multiple image blocks; each image block corresponds to a unique index.

[0016] The number of rows and columns of the plurality of image blocks that construct the license plate image are halved to obtain the number of rows and columns of the target image block, and the target image block is determined based on the number of rows and columns of the target image block.

[0017] After determining the target image patch based on the number of rows and columns of the target image patch, the method further includes:

[0018] Based on the index information of each image block, a first weight for each target image block and a second weight for each non-target image block are determined.

[0019] In some embodiments of this disclosure, determining the average brightness of the license plate image based on the plurality of image blocks, the first weight, and the second weight includes:

[0020] Calculate the brightness value of the first Y component based on the target image block and the first weight;

[0021] The brightness value of the second Y component is calculated based on the non-target image block and the second weight;

[0022] The average brightness of the license plate area is obtained by weighting the brightness values ​​of the first Y component and the second Y component.

[0023] In some embodiments of this disclosure, after determining the average brightness of the license plate image, the method further includes:

[0024] The overexposure state corresponding to the average brightness of the license plate image is classified according to the preset first overexposure threshold and second overexposure threshold.

[0025] The smooth adjustment of image exposure parameters based on exposure adjustment increments includes:

[0026] In response to the average brightness being greater than or equal to the first overexposure threshold, the exposure adjustment increment is determined based on the error between the average brightness and the target brightness;

[0027] The image exposure parameters are smoothly adjusted according to the exposure adjustment increment.

[0028] In some embodiments of this disclosure,

[0029] In response to the average brightness being less than the first overexposure threshold and greater than or equal to the second overexposure threshold, the mean intensity of the area corresponding to the license plate area is calculated based on the horizontal and vertical gradients of the license plate area.

[0030] The clarity of the license plate image is determined based on the mean intensity of the region and a preset edge intensity threshold.

[0031] In some embodiments of this disclosure, the smooth adjustment of image exposure parameters based on exposure adjustment increments includes:

[0032] If the mean intensity of the region is less than the preset edge intensity threshold, then the license plate image is determined to be unclear.

[0033] The image exposure parameters are smoothly adjusted according to the exposure adjustment increment.

[0034] In some embodiments of this disclosure, calculating the mean intensity of the area corresponding to the license plate area based on the horizontal and vertical gradients of the license plate area includes:

[0035] Calculate the gradient magnitude based on the horizontal and vertical gradients of the license plate area;

[0036] The mean intensity of the area corresponding to the license plate region is calculated based on the gradient magnitude and the size of the license plate region.

[0037] In some embodiments of this disclosure,

[0038] In response to the average brightness being less than the second overexposure threshold, the target license plate image is captured; or,

[0039] In response to the mean intensity of the region being greater than or equal to the preset edge intensity threshold, the license plate image is determined to be clear, and the clear license plate image is cropped as the target license plate image.

[0040] According to a second aspect of this disclosure, an exposure parameter adjustment device is provided, comprising:

[0041] An acquisition unit is used to acquire a license plate image, wherein the license plate image is determined from a received original image;

[0042] The first determining unit is configured to, in response to the ambient brightness information of the original image being less than a preset brightness threshold, divide the license plate image into multiple image blocks and determine the target image block corresponding to the license plate region from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block;

[0043] The second determining unit is used to determine the average brightness of the license plate image based on the plurality of image blocks, the first weight, and the second weight;

[0044] An adjustment unit is used to smoothly adjust the image exposure parameters based on the exposure adjustment increment in response to the average brightness being greater than the overexposure threshold.

[0045] In some embodiments of this disclosure, the apparatus further includes: a first determination unit;

[0046] The first determination unit includes:

[0047] The acquisition module is used to acquire the current exposure value and dynamic exposure reference value of the original image, wherein the ambient brightness information includes the current exposure value and dynamic exposure reference value;

[0048] The first determining module is used to determine the current exposure reference value based on the current exposure value and the dynamic exposure reference value;

[0049] The second determining module is used to determine whether the ambient brightness information of the original image is less than the preset brightness threshold based on the comparison result between the current exposure reference value and the current exposure value.

[0050] In some embodiments of this disclosure, the first determining unit includes:

[0051] The segmentation module is used to divide the license plate image into the multiple image blocks; wherein each image block corresponds to unique index information;

[0052] The third determining module is used to halve the number of rows and columns of the plurality of image blocks that construct the license plate image to obtain the number of rows and columns of the target image block, and to determine the target image block based on the number of rows and columns of the target image block.

[0053] Following the third determining module, the following is also included:

[0054] The fourth determining module is used to determine the first weight of each target image block and the second weight of each non-target image block based on the index information of each image block.

[0055] In some embodiments of this disclosure, the second determining unit includes:

[0056] The first calculation module is used to calculate the brightness value of the first Y component based on the target image block and the first weight;

[0057] The second calculation module is used to calculate the brightness value of the second Y component based on the non-target image block and the second weight;

[0058] The weighting module is used to perform a weighted average of the first Y component brightness value and the second Y component brightness value to obtain the average brightness of the license plate area.

[0059] In some embodiments of this disclosure, the apparatus further includes:

[0060] The grading unit is used to grade the overexposure state corresponding to the average brightness of the license plate image according to a preset first overexposure threshold and a second overexposure threshold after the second determining unit determines the average brightness of the license plate image.

[0061] In some embodiments of this disclosure, the adjustment unit includes:

[0062] The fifth determining module is used to determine the exposure adjustment increment based on the error between the average brightness and the target brightness in response to the average brightness being greater than or equal to the first overexposure threshold.

[0063] The first adjustment module is used to smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0064] In some embodiments of this disclosure, the apparatus further includes:

[0065] The calculation unit is configured to, in response to the average brightness being less than the first overexposure threshold and greater than or equal to the second overexposure threshold, calculate the regional mean intensity corresponding to the license plate area based on the horizontal and vertical gradients of the license plate area.

[0066] The second judgment unit is used to determine whether the license plate image is clear based on the mean intensity of the region and a preset edge intensity threshold.

[0067] In some embodiments of this disclosure, the adjustment unit further includes:

[0068] The sixth determining module is used to determine that the license plate image is unclear when the mean intensity of the region is less than the preset edge intensity threshold.

[0069] The second adjustment module is used to smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0070] In some embodiments of this disclosure, the computing unit includes:

[0071] The third calculation module is used to calculate the gradient magnitude based on the horizontal and vertical gradients of the license plate area.

[0072] The fourth calculation module is used to calculate the regional mean intensity corresponding to the license plate area based on the gradient magnitude and the size of the license plate area.

[0073] In some embodiments of this disclosure, the apparatus further includes:

[0074] The cropping unit is used to crop the target license plate image in response to the average brightness being less than the second overexposure threshold.

[0075] The cropping unit is further configured to, in response to the mean intensity of the region being greater than or equal to the preset edge intensity threshold, determine that the license plate image is clear, and crop the clear license plate image as the target license plate image.

[0076] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0077] At least one processor; and

[0078] A memory communicatively connected to the at least one processor; wherein,

[0079] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect embodiment.

[0080] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect of the present disclosure.

[0081] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in the first aspect of the preceding embodiments.

[0082] In summary, according to the exposure parameter adjustment method, apparatus, electronic device, and storage medium provided in this disclosure, the method includes: acquiring a license plate image from a received original image; dividing the license plate image into multiple image blocks in response to the ambient brightness information of the original image being less than a preset brightness threshold, wherein the multiple image blocks include target image blocks and non-target image blocks, the first weight of the target image block being greater than the second weight of the non-target image block; determining the target image block corresponding to the license plate region from the multiple image blocks; determining the average brightness of the license plate image based on the multiple image blocks, the first weight, and the second weight; and smoothly adjusting the image exposure parameters based on the exposure adjustment increment in response to the average brightness being greater than an overexposure threshold. This achieves the division of the license plate image into target image blocks and non-target image blocks, increases the first weight of the target image block to focus the exposure brightness adjustment on the target image block, decreases the second weight of the non-target image block to reduce the interference of the non-license plate image region on the exposure brightness adjustment of the license plate image region, and ensures the stability of the license plate image during the exposure brightness adjustment process through exposure increment adjustment, thereby completing the effective exposure brightness adjustment of the license plate image.

[0083] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0084] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0085] Figure 1 This is a schematic flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure.

[0086] Figure 2 This is a schematic diagram of a license plate image provided in an embodiment of this disclosure;

[0087] Figure 3 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0088] Figure 4 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0089] Figure 5 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0090] Figure 6 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0091] Figure 7A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0092] Figure 8 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0093] Figure 9 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0094] Figure 10 A schematic flowchart illustrating another method for adjusting exposure parameters provided in this embodiment of the present disclosure;

[0095] Figure 11 A schematic diagram of an exposure parameter adjustment device provided in an embodiment of this disclosure;

[0096] Figure 12 A schematic diagram of another exposure parameter adjustment device provided in an embodiment of this disclosure;

[0097] Figure 13 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0098] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0099] With the development of smart parking systems, license plate image overexposure is a common technical challenge. In low-light conditions at night, smart parking systems rely on supplementary lighting to ensure clear license plate image capture. However, metal license plates experience specular reflection when directly illuminated by supplementary lighting, leading to overexposure of the license plate image area and causing system misjudgment or blurry images.

[0100] In related technologies, after calculating the average brightness of the license plate image, the exposure of the license plate image is adjusted based on the difference between a preset brightness threshold and the average brightness. However, when calculating the average brightness, the average brightness of non-license plate image areas may usually be included, which makes the exposure brightness adjustment method of the license plate image area easily affected by the non-license plate image area.

[0101] Therefore, in order to solve the problems existing in the related technologies, this disclosure proposes a method for adjusting exposure parameters. The method includes: acquiring a license plate image from a received original image; in response to the ambient brightness information of the original image being less than a preset brightness threshold, dividing the license plate image into multiple image blocks, the multiple image blocks including target image blocks and non-target image blocks, the first weight of the target image block being greater than the second weight of the non-target image block; determining the target image block corresponding to the license plate region from the multiple image blocks; determining the average brightness of the license plate image based on the multiple image blocks, the first weight, and the second weight; in response to the average brightness being greater than an overexposure threshold, smoothly adjusting the image exposure parameters based on the exposure adjustment increment. This achieves the division of the license plate image into target image blocks and non-target image blocks, increases the first weight of the target image block to focus the center of exposure brightness adjustment on the target image block, decreases the second weight of the non-target image block to reduce the interference of the non-license plate image region on the exposure brightness adjustment of the license plate image region, and ensures the stability of the license plate image during the exposure brightness adjustment process through exposure increment adjustment, thereby completing the effective exposure brightness adjustment of the license plate image.

[0102] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0103] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0104] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0105] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0106] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0107] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0108] The prefixes such as "first" and "second" in the embodiments of this disclosure are only for distinguishing different descriptive objects and do not constitute restrictions on the position, order, priority, number or content of the descriptive objects. For the description of the descriptive objects, please refer to the description in the claims or the context of the embodiments. The use of prefixes should not constitute unnecessary restrictions.

[0109] In the embodiments disclosed herein, "multiple" refers to two or more.

[0110] In the embodiments disclosed herein, terms such as “import”, “input”, and “read in” can be used interchangeably.

[0111] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0112] Figure 1 This is a schematic flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure, as shown below. Figure 1 As shown, the method for adjusting the exposure parameters includes steps 101-104.

[0113] Step 101: Obtain a license plate image, which is determined from the received original image.

[0114] In this embodiment of the disclosure, the original image refers to the initial image that has not been processed. The original image typically includes at least a scene such as a vehicle, a road, and a background environment. The original image is processed by a preset license plate detection algorithm to determine the coordinates that constitute the license plate image, and the license plate image is obtained based on the coordinates.

[0115] In this step, the original image is processed to obtain the license plate image, reducing interference from irrelevant scenes in the original image and ensuring that the processing revolves around the license plate image.

[0116] Step 102: In response to the ambient brightness information of the original image being less than a preset brightness threshold, the license plate image is divided into multiple image blocks, and the target image block corresponding to the license plate area is determined from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block.

[0117] The ambient brightness information of the original image reflects information such as the light intensity of the shooting environment. The preset brightness threshold is a critical value set in advance for the ambient brightness information. When the ambient brightness information of the original image is less than the preset brightness threshold, it is determined that the original image needs to be processed for exposure brightness adjustment.

[0118] In some embodiments, the preset brightness threshold is an empirical value. For example, when the light intensity in the ambient brightness information is 3 lux and the preset brightness threshold is 4 lux, exposure brightness adjustment processing is required. When the light intensity in the ambient brightness information is 5 lux and the preset brightness threshold is 4 lux, exposure brightness adjustment processing is not required. The specific value of the preset brightness threshold is not limited in the embodiments of this disclosure.

[0119] like Figure 2 The diagram shown is a schematic of a license plate image provided in an embodiment of this disclosure. The diagram shows the original image, the license plate image, the license plate area, and the non-license plate area. The license plate image (e.g., w1*h1) is divided into multiple image blocks (e.g., m*n) according to a preset size of the image blocks. Each image block is w*h in size, where w1 is greater than w and h1 is greater than h. The multiple image blocks are divided into target image blocks and non-target image blocks according to whether they contain content related to the license plate. The target image block is an image block that contains valid license plate information (e.g., Chinese characters, letters, vehicle type identifiers, etc.). The non-target image block is an image block other than the target image block. The area formed by the target image blocks is the license plate area, and the area formed by the non-target image blocks is the non-license plate area.

[0120] In order to focus on the license plate region in the license plate image, the weight value of the first weight of the target image block is greater than the weight value of the second weight of the non-target image block, thereby increasing the weight ratio of the target image block and reducing the interference of the non-target image block on the processing result.

[0121] Step 103: Determine the average brightness of the license plate image based on the plurality of image blocks, the first weight, and the second weight.

[0122] The target image block and its first weight, and the non-target image block and its second weight are calculated to determine the average brightness of the license plate image. The average brightness of the license plate image is a quantitative value that reflects the overall brightness level of the license plate image and is used to comprehensively describe the brightness status of the license plate area.

[0123] In some embodiments, the average brightness of the license plate image can be calculated using any calculation method in the related technologies, but not limited to any specific method. The calculation method in this disclosure is not limited.

[0124] Reduce interference from non-target image blocks on brightness assessment and avoid adjustment deviations caused by brightness interference from non-license plate areas.

[0125] Step 104: In response to the average brightness being greater than the overexposure threshold, the image exposure parameters are smoothly adjusted based on the exposure adjustment increment.

[0126] In some embodiments, the overexposure threshold can typically be preset based on experiments or experience to determine whether the brightness value of the license plate image is overexposed.

[0127] If the average brightness is greater than the overexposure threshold, it indicates that the license plate image is too bright and there is a risk of overexposure. Therefore, it is necessary to smoothly adjust the image exposure parameters based on the exposure adjustment increment. If the average brightness is less than or equal to the overexposure threshold, it indicates that the image brightness is within the normal range. Therefore, it is not necessary to perform smooth adjustment.

[0128] Image exposure parameters are parameters that affect image brightness settings and determine the brightness of the image. These parameters include, but are not limited to, any one or more combinations of shutter speed, aperture size, ISO sensitivity, and fill light power. By adjusting the amount of change in image exposure parameters through exposure adjustment increments, the adjustment range of exposure parameters can be controlled to avoid sudden changes in image brightness due to excessive adjustments in a single instance, thus achieving a smooth adjustment of image brightness from an overexposed state to a normal state.

[0129] In summary, according to the exposure parameter adjustment method provided in this disclosure, a license plate image is obtained from the received original image. In response to the ambient brightness information of the original image being less than a preset brightness threshold, the license plate image is divided into multiple image blocks, including target image blocks and non-target image blocks. The first weight of the target image block is greater than the second weight of the non-target image block. The target image block corresponding to the license plate region is determined from the multiple image blocks. Based on the multiple image blocks, the first weight, and the second weight, the average brightness of the license plate image is determined. In response to the average brightness being greater than an overexposure threshold, the image exposure parameters are smoothly adjusted based on the exposure adjustment increment. This achieves the division of the license plate image into target image blocks and non-target image blocks, increases the first weight of the target image block to focus the exposure brightness adjustment on the target image block, and decreases the second weight of the non-target image block to reduce the interference of non-license plate image areas on the exposure brightness adjustment of the license plate image area. The stability of the license plate image is ensured during the exposure brightness adjustment process through exposure increment adjustment, thereby completing the effective exposure brightness adjustment of the license plate image.

[0130] Figure 3 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 1 The illustrated embodiment further explains step 102. Figure 3 This may include the following steps:

[0131] Step 201: Obtain the current exposure value and dynamic exposure reference value of the original image, wherein the ambient brightness information includes the current exposure value and dynamic exposure reference value.

[0132] In this embodiment of the disclosure, the current exposure value of the original image is the quantized value corresponding to the image exposure parameters. The current exposure value reflects the exposure state under the current scene. The dynamic exposure reference value can be dynamically adjusted according to the current exposure value and the historical exposure reference value within a preset adjustment period. The specific preset adjustment period is the number of adjustments (such as every 3 exposure adjustments, every 5 exposure adjustments, etc.). This embodiment of the disclosure does not limit this.

[0133] Step 202: Determine the current exposure reference value based on the current exposure value and the dynamic exposure reference value.

[0134] The result of calculating the current exposure reference value based on the current exposure value and the dynamic exposure reference value is shown in Formula 1.

[0135] WLbase2=WWLbase1*k1+k2*(exposure) Formula 1

[0136] Wherein, WLbase1 is the dynamic exposure baseline value, exposure is the current exposure value, WLbase2 is the current exposure baseline value, k1 is the weighting coefficient that retains the original WLbase1, and k2 is the weighting coefficient that introduces exposure. k1 and k2 will be adjusted according to the changes in WLbase1 and exposure, and the sum of k1 and k2 is 1.

[0137] The current exposure value, exposure, is calculated based on preset gain and exposure time. Both gain and exposure time are positively correlated with the current exposure value, WLbase2. The current exposure reference value, WLbase2, is continuously updated by performing a preset number of calculations. If the calculation continues, the current exposure reference value, WLbase2, is used as the input for the next dynamic exposure reference value, WLbase1.

[0138] For example, when k1 is 0.2 and k2 is 0.8, in the first calculation: the initial WLbase1 is 100 lux and exposure is 120 lux, so WLbase2 is calculated to be 116 lux; in the second calculation: the exposure remains at 120 lux, and WLbase1 uses the first WLbase2 value of 116 lux as input, so WLbase1 is now 116 lux, and WLbase2 is calculated to be 119.2 lux; in the third calculation: the exposure remains at 120 lux, and WLbase1 uses the second WLbase2 value of 119.2 lux as input, so WLbase1 is now 119.2 lux, and WLbase2 is calculated to be 119.84 lux. Thus, WLbase2 has continuously approached the exposure through multiple calculations. It should be noted that the above calculation count is merely an example and not a limitation on the specific input content.

[0139] Step 203: Based on the comparison result between the current exposure reference value and the current exposure value, determine whether the ambient brightness information of the original image is less than the preset brightness threshold.

[0140] The preset brightness threshold is set in advance to define whether the current ambient brightness has reached the critical value that requires special processing. After multiple calculations of Formula 1, the current exposure reference value is made to continuously approach the current exposure value. When the current exposure value in the ambient brightness information of the image is less than the preset brightness threshold, it is determined that the current ambient brightness is low and exposure brightness adjustment is required. When the current exposure value in the ambient brightness information of the image is greater than or equal to the preset brightness threshold, it is determined that the current ambient brightness is high and exposure brightness adjustment is not required.

[0141] Figure 4A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 3 The embodiment shown, Figure 4 This may include the following steps:

[0142] Step 301: Divide the license plate image into the plurality of image blocks; wherein each image block corresponds to a unique index information.

[0143] In this embodiment of the disclosure, the license plate image is divided into multiple independent sub-regions (multiple image blocks) according to a preset size. Each independent sub-region (each image block) corresponds to a unique index information. Each independent sub-region contains pixel information corresponding to the license plate image. Multiple independent sub-regions together constitute a complete license plate image.

[0144] By segmenting and refining the license plate image, subsequent operations such as license plate region recognition and weight allocation can be focused on each sub-region, enabling refined analysis of the license plate image.

[0145] Step 302: Halve the number of rows and columns of the plurality of image blocks that construct the license plate image to obtain the number of rows and columns of the target image block, and determine the target image block based on the number of rows and columns of the target image block.

[0146] The license plate image (e.g., w1*h1) is divided into multiple image blocks of a preset size, such as m*n, where m is the number of rows and n is the number of columns. The number of rows and columns of the multiple image blocks in the license plate image are halved respectively. The rectangular boundaries formed by extending outwards from the center point of the license plate image to the corresponding halved number of rows and columns constitute the license plate area. m / 2 and n / 2 are determined as the length and width of the license plate area. Multiple target image blocks are determined from the license plate area, and multiple non-target image blocks are determined from the non-license plate area outside the license plate area.

[0147] The license plate region is the central area of ​​the license plate image that contains information about the license plate itself (such as characters, background color, etc.). It is the key target area for license plate recognition. All image blocks in the license plate region are target image blocks. Multiple image blocks contain both target and non-target image blocks. The target image block corresponding to the license plate region is determined from multiple image blocks.

[0148] Step 303: Determine the first weight of each target image block and the second weight of each non-target image block based on the index information of each image block.

[0149] Each image patch corresponds to a unique index (such as coordinate position). The index information is used to distinguish the coordinate position of each image patch. Based on the index information of each image patch, the coordinate positions of target image patches and non-target image patches are determined. Each image patch has a corresponding block weight. The block weight of each target image patch is determined based on the index information corresponding to multiple target image patches, and the block weight of multiple target image patches is determined as the first weight. The block weight of each non-target image patch is determined based on the index information corresponding to multiple non-target image patches, and the block weight of multiple non-target image patches is determined as the second weight. The block weight W(i,j) is shown in Equation 2.

[0150]

[0151] Where m and n represent image blocks with m rows and n columns in the license plate image, and the index information of each image block is (i,j), σ 2 Let σ be the variance of the weight distribution. 2 It controls the distribution range of weights across various image patches, σ 2 A larger σ indicates a slower weight decay with distance and a wider range. 2 The smaller the value, the more concentrated the weight is in the target image block, and the faster the edge decays. The smaller the range, the more concentrated it is in the target image block.

[0152] Figure 5 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 1 The illustrated embodiment further explains step 103. Figure 5 This may include the following steps:

[0153] Step 401: Calculate the brightness value of the first Y component based on the target image block and the first weight.

[0154] In this embodiment, the Y component represents the brightness information of the license plate image. The brightness value of the first Y component is calculated based on the index information of the target image block, and the corresponding weight value of the first weight is calculated based on the index information and the weight value of the first weight. The brightness value I(1) of the first Y component is shown in Formula 3.

[0155]

[0156] Where m1 and n1 represent target image blocks with m1 rows and n1 columns in the license plate image, m1 < m, n1 < n, the index information of each target image block is (i,j), I1(i,j) represents the brightness value of the target image block at the index information (i,j), and W1(i,j) represents the block weight of the target image block at the index information (i,j).

[0157] Step 402: Calculate the second Y - component brightness value based on the non - target image block and the second weight.

[0158] The second Y - component brightness value is calculated by calculating the weight value of the corresponding second weight according to the index information of the non - target image block, and calculating the corresponding brightness value according to the index information and the weight value of the second weight. The second Y - component brightness value I(2) is shown in Formula 4.

[0159]

[0160] Among them, m2 and n2 represent that there are m2 rows and n2 columns of non - target image blocks in the license plate image, m2 < m, n2 < n, m1 + m2 = m, n1 + n2 = n. The index information of each non - target image block is (i, j), I2(i, j) represents the brightness value of the non - target image block at the position with index information (i, j), and W2(i, j) represents the block weight of the non - target image block at the position with index information (i, j).

[0161] Step 403: Perform weighted averaging on the first Y - component brightness value and the second Y - component brightness value to obtain the average brightness of the license plate area.

[0162] The sum of the first Y - component brightness value and the second Y - component brightness value is used to obtain the total brightness of the license plate image. After averaging the total brightness of the license plate image and the size (area) of the license plate image, the average brightness of the license plate image is obtained. The total brightness I(all) of the license plate image is shown in Formula 5, and the average brightness I(avg) of the license plate image is shown in Formula 6.

[0163] I(all)=I(1)+I(2) Formula 5

[0164] I(avg)=I(all) / (w1 * h1) Formula 6

[0165] Among them, in Formula 5, the total brightness I(all) of the license plate image is the sum of the first Y - component brightness value I(1) and the second Y - component brightness value I(2). In Formula 6, w1 is the width of the license plate image, h1 is the height of the license plate image, w1 * h1 is the area of the license plate image, and the average brightness I(avg) of the license plate image is the total brightness I(all) of the license plate image divided by the area of the license plate image.

[0166] After determining the average brightness of the license plate image, it further includes: classifying the over - exposure state corresponding to the average brightness of the license plate image according to a preset first over - exposure threshold and a second over - exposure threshold.

[0167] The first overexposure threshold (T1) and the second overexposure threshold (T2) are pre-set critical values ​​used to define the degree of overexposure of the average brightness of the license plate image through gradient judgment. The degree of overexposure is divided into different intervals. Where T1 is greater than T2, the overexposure state corresponding to the average brightness of the license plate image is classified into three levels: the first level (severe overexposure) is the average brightness greater than or equal to T1, the second level (slight overexposure) is the average brightness greater than or equal to T2 and less than T1, and the third level (no overexposure) is the average brightness less than T2.

[0168] T1 and T2 are in a progressive relationship, with T1>T2. Overexposure levels are divided by brightness comparison to avoid the coarseness of judging the degree of overexposure by a single threshold. The first level, second level and third level are divided by the difference between T1 and T2 values, so that the exposure brightness adjustment can adapt to the further needs of license plate recognition.

[0169] Figure 6 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 1 The illustrated embodiment further explains step 104. Figure 6 This may include the following steps:

[0170] Step 501: In response to the average brightness being greater than or equal to the first overexposure threshold, the exposure adjustment increment is determined based on the error between the average brightness and the target brightness.

[0171] In this embodiment, the target brightness is a preset brightness value for the license plate image. The target brightness serves as a reference standard to measure the difference between the target brightness and the average brightness. The exposure adjustment increment is used to adjust the values ​​of exposure parameters, such as exposure time and aperture size. The exposure adjustment increment is calculated based on the error between the average brightness and the target brightness of the license plate image. It should be noted that the above is an exemplary example and not a limitation on specific input content.

[0172] The exposure adjustment increment u(k) is calculated as shown in Formula 7.

[0173] u(k)=Kp*e(k)+Ki*i(k)+Kd*d(k) Formula 7

[0174] Where Kp is the proportional term, Ki is the integral term, Kd is the differential term, e(k) represents the error between the current average brightness and the target brightness, i(k) represents the cumulative sum of errors throughout history, and d(k) represents the rate of change of the error. The calculation steps are proportional increment Kp*e(k), integral increment ki*i(k), and differential increment Kd*d(k), and finally the exposure adjustment increment u(k) is calculated.

[0175] When the license plate image is at level three, the exposure adjustment increment is determined based on the difference between the average brightness and the target brightness. For example, if Kp is 0.5, Ki is 0.01, Kd is 0.1, the current average brightness is 200, and the preset target brightness is 128, then e(k) is 72. If e(k) of 72 represents the first accumulated error, then i(k) is 72. If the brightness at the previous moment is the same as the current brightness, then d(k) is 0. Using formula 6, u(k) is calculated to be 36.72. It should be noted that the above is merely an example and not a limitation on specific input content.

[0176] Step 502: Smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0177] The image exposure parameters are smoothly adjusted based on the exposure adjustment increment. The smooth adjustment adopts a gradual adjustment method to prevent drastic changes in image exposure parameters from causing sudden changes in image brightness, thus ensuring the stability of license plate image quality during the adjustment process and improving the stability of license plate image processing.

[0178] Figure 7 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 6 The embodiment shown, Figure 7 It may also include the following steps:

[0179] Step 601: In response to the average brightness being less than the first overexposure threshold and greater than or equal to the second overexposure threshold, calculate the regional mean intensity corresponding to the license plate area based on the horizontal and vertical gradients of the license plate area.

[0180] When the license plate image is at the second level, the horizontal and vertical gradients of the license plate region corresponding to the target image block in the license plate image are calculated. Based on the horizontal and vertical gradients, the mean intensity of the region corresponding to the license plate region can be calculated.

[0181] Step 602: Determine whether the license plate image is clear based on the mean intensity of the region and the preset edge intensity threshold.

[0182] The average intensity of the determined license plate area is compared with a preset edge intensity threshold. When the average intensity of the area is greater than or equal to the preset edge intensity threshold, the license plate area is determined to be of the first edge density, and the license plate image is clear. When the average intensity of the area is less than the preset edge intensity threshold, the license plate area is determined to be of the second edge density, and the license plate image is not clear.

[0183] By setting a preset edge strength threshold, a unified standard is established for judging the clarity of license plate images, avoiding inconsistencies caused by subjective judgment differences and improving the accuracy and reliability of clarity judgment.

[0184] Figure 8 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 7 The illustrated embodiment further explains step 104. Figure 8 This may include the following steps:

[0185] Step 701: If the average intensity of the region is less than the preset edge intensity threshold, then the license plate image is determined to be unclear.

[0186] When the license plate area reaches the second edge density, the license plate image is determined to be unclear (e.g., blurred character edges, loss of character details, etc.), and exposure brightness adjustment continues. It should be noted that the above is an illustrative example and not a limitation on specific input content.

[0187] Step 702: Smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0188] For license plate images at the second level and with the license plate area at the second edge density, the image exposure parameters are smoothly adjusted based on the exposure adjustment increment. The brightness correction requirement is converted into specific parameters for adjustment through the exposure adjustment increment, ensuring precise adjustment direction. The smooth adjustment method avoids drastic fluctuations in image exposure parameters, reduces recognition errors caused by unstable exposure, and improves the system's adaptability in complex lighting environments.

[0189] Figure 9 A flowchart illustrating a method for adjusting exposure parameters provided in an embodiment of this disclosure is further illustrated. Based on Figure 7 The illustrated embodiment further explains step 701. Figure 9 This may include the following steps:

[0190] Step 801: Calculate the gradient magnitude based on the horizontal and vertical gradients of the license plate area.

[0191] When the license plate image is at the second level, calculate the horizontal and vertical gradients of the license plate region corresponding to the target license plate block. The horizontal gradient G x and vertical gradient G y As shown in Formulas 8 and 9.

[0192]

[0193]

[0194] Among them, I x This is the horizontal grayscale matrix of the license plate region corresponding to the target license plate block. Used to extract horizontal edges, Iy This is the grayscale matrix of the license plate region corresponding to the target license plate block in the vertical direction. Used to extract vertical edges.

[0195] The gradient magnitude of the license plate area is calculated using the horizontal and vertical gradients, and the gradient magnitude E(x,y) is shown in Formula 10.

[0196] E(x,y)=|Gx|+|Gy| Formula 10

[0197] If the license plate image is overexposed, the pixels of the target image block in the license plate area will reach or approach the maximum value, the edge gradient will disappear, and the gradient magnitude will tend to 0. At this time, the license plate area is at the second edge density, and the license plate image is not clear.

[0198] Step 802: Calculate the mean intensity of the area corresponding to the license plate area based on the gradient amplitude and the size of the license plate area.

[0199] Calculate the mean intensity E(avg) and size w2*h2 of the license plate area based on the gradient amplitude, as shown in the figure.

[0200] As shown in Equation 11.

[0201]

[0202] Where w2*h2 represents the area of ​​the license plate region, w2 is the width of the license plate region, h2 is the height of the license plate region, and the regional mean intensity is a comprehensive index calculated by statistical averaging based on the horizontal and vertical gradients of the license plate region, representing the overall gradient strength within the license plate region.

[0203] In order to capture the target license plate image, the following is also included:

[0204] In response to the average brightness being less than the second overexposure threshold, the target license plate image is captured; or,

[0205] In response to the mean intensity of the region being greater than or equal to the preset edge intensity threshold, the license plate image is determined to be clear, and the clear license plate image is cropped as the target license plate image.

[0206] The target license plate image is an image of the license plate area that meets the recognition standards (such as brightness and image clarity) after exposure and brightness adjustment. When the license plate image is at the third level, the target license plate image is directly cropped, or when the license plate image is at the second level and the license plate area is at the second edge density, a clear target license plate image is cropped.

[0207] like Figure 10The diagram shown is a flowchart illustrating a method for adjusting exposure parameters according to an embodiment of this disclosure. Steps S1-S9 include:

[0208] S1: Process the original image using a preset license plate detection algorithm to obtain a license plate image.

[0209] S2: Determine whether the ambient brightness information of the original image is less than the preset brightness threshold.

[0210] If the brightness is determined to be less than the preset brightness threshold, then proceed to step S3; if the brightness is determined to be greater than or equal to the preset brightness threshold, then proceed to step S9.

[0211] S3: Divide the license plate image into multiple image blocks, including target image blocks and non-target image blocks. The target image blocks correspond to the first weight, and the non-target image blocks correspond to the second weight.

[0212] S4: Determine the average brightness of the license plate image based on multiple image blocks, the first weight, and the second weight.

[0213] S5: Based on the preset first overexposure threshold and second overexposure threshold, classify the overexposure state corresponding to the average brightness of the license plate image.

[0214] If the average brightness of the license plate image is greater than or equal to the first overexposure threshold, then proceed to step S8; if the average brightness of the license plate image is less than the first overexposure threshold but greater than or equal to the second overexposure threshold, then proceed to step S6; if the average brightness of the license plate image is less than the second overexposure threshold, then proceed to step S9.

[0215] S6: Calculate the mean intensity of the area corresponding to the license plate region, and determine whether the license plate image is clear based on the mean intensity of the area and the preset edge intensity threshold.

[0216] If the edge intensity is less than the preset edge intensity threshold, proceed to step S7; if the edge intensity is greater than or equal to the preset edge intensity threshold and the image is clear, proceed to step S9.

[0217] S7: The license plate image is unclear.

[0218] S8: Determine the exposure adjustment increment based on the error between the average brightness and the target brightness, and smoothly adjust the image exposure parameters according to the exposure adjustment increment; continue to execute S1.

[0219] S9: Determine if the license plate image is clear and capture the target license plate image.

[0220] For detailed descriptions of steps S1-S9, please refer to the detailed descriptions of the above embodiments.

[0221] Corresponding to the above-described method for adjusting exposure parameters, this invention also proposes an exposure parameter adjustment device. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments, and will not be repeated here.

[0222] Figure 11 This is a schematic diagram of the structure of an exposure parameter adjustment device provided in an embodiment of the present disclosure, as shown below. Figure 11 As shown, it includes: an acquisition unit 111, a first determination unit 112, a second determination unit 113, and an adjustment unit 114.

[0223] Acquisition unit 111 is used to acquire a license plate image, wherein the license plate image is determined from the received original image;

[0224] The first determining unit 112 is configured to, in response to the ambient brightness information of the original image being less than a preset brightness threshold, divide the license plate image into multiple image blocks and determine the target image block corresponding to the license plate area from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block;

[0225] The second determining unit 113 is used to determine the average brightness of the license plate image based on the plurality of image blocks, the first weight and the second weight;

[0226] The adjustment unit 114 is used to smoothly adjust the image exposure parameters based on the exposure adjustment increment in response to the average brightness being greater than the overexposure threshold.

[0227] In summary, according to the exposure parameter adjustment device provided in this disclosure, the device includes: acquiring a license plate image from a received original image; dividing the license plate image into multiple image blocks in response to the ambient brightness information of the original image being less than a preset brightness threshold, wherein the multiple image blocks include target image blocks and non-target image blocks, the first weight of the target image blocks being greater than the second weight of the non-target image blocks; determining the target image block corresponding to the license plate region from the multiple image blocks; determining the average brightness of the license plate image based on the multiple image blocks, the first weight, and the second weight; and smoothly adjusting the image exposure parameters based on the exposure adjustment increment in response to the average brightness being greater than an overexposure threshold. This achieves the division of the license plate image into target image blocks and non-target image blocks, increases the first weight of the target image blocks to focus the exposure brightness adjustment on the target image blocks, decreases the second weight of the non-target image blocks to reduce the interference of non-license plate image regions on the exposure brightness adjustment of the license plate image region, and ensures the stability of the license plate image during the exposure brightness adjustment process through exposure increment adjustment, thereby completing the effective exposure brightness adjustment of the license plate image.

[0228] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the device further includes: a first determination unit 115; the first determination unit 115 includes:

[0229] The acquisition module 1151 is used to acquire the current exposure value and dynamic exposure reference value of the original image, wherein the ambient brightness information includes the current exposure value and dynamic exposure reference value;

[0230] The first determining module 1152 is used to determine the current exposure reference value based on the current exposure value and the dynamic exposure reference value;

[0231] The second determining module 1153 is used to determine whether the ambient brightness information of the original image is less than the preset brightness threshold based on the comparison result between the current exposure reference value and the current exposure value.

[0232] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the first determining unit 112 includes:

[0233] The segmentation module 1121 is used to divide the license plate image into the plurality of image blocks; wherein each image block corresponds to unique index information;

[0234] The third determining module 1122 is used to halve the number of rows and columns of the plurality of image blocks that construct the license plate image to obtain the number of rows and columns of the target image block, and to determine the target image block based on the number of rows and columns of the target image block.

[0235] Following the third determining module 1122, the following is also included:

[0236] The fourth determining module 1123 is used to determine the first weight of each target image block and the second weight of each non-target image block based on the index information of each image block.

[0237] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the second determining unit 113 includes:

[0238] The first calculation module 1131 is used to calculate the brightness value of the first Y component based on the target image block and the first weight;

[0239] The second calculation module 1132 is used to calculate the brightness value of the second Y component based on the non-target image block and the second weight.

[0240] The weighting module 1133 is used to perform a weighted average of the first Y component brightness value and the second Y component brightness value to obtain the average brightness of the license plate area.

[0241] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the device further includes:

[0242] The grading unit 116 is used to grade the overexposure state corresponding to the average brightness of the license plate image according to a preset first overexposure threshold and a second overexposure threshold after the second determining unit 113 determines the average brightness of the license plate image.

[0243] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the adjustment unit 114 includes:

[0244] The fifth determining module 1141 is used to determine the exposure adjustment increment based on the error between the average brightness and the target brightness in response to the average brightness being greater than or equal to the first overexposure threshold.

[0245] The first adjustment module 1142 is used to smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0246] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the device further includes:

[0247] The calculation unit 117 is used to calculate the regional average intensity corresponding to the license plate area based on the horizontal gradient and vertical gradient of the license plate area in response to the average brightness being less than the first overexposure threshold and greater than or equal to the second overexposure threshold.

[0248] The second judgment unit 118 is used to judge whether the license plate image is clear based on the mean intensity of the region and the preset edge intensity threshold.

[0249] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the adjustment unit 114 further includes:

[0250] The sixth determining module 1143 is used to determine that the license plate image is unclear when the mean intensity of the region is less than the preset edge intensity threshold.

[0251] The second adjustment module 1144 is used to smoothly adjust the image exposure parameters according to the exposure adjustment increment.

[0252] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the computing unit 117 includes:

[0253] The third calculation module 1171 is used to calculate the gradient magnitude based on the horizontal and vertical gradients of the license plate area.

[0254] The fourth calculation module 1172 is used to calculate the regional mean intensity corresponding to the license plate area based on the gradient magnitude and the size of the license plate area.

[0255] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 12 As shown, the device further includes:

[0256] The cropping unit 119 is used to crop the target license plate image in response to the average brightness being less than the second overexposure threshold; the cropping unit 119 determines that the license plate image is clear in response to the mean intensity of the region being greater than or equal to the preset edge intensity threshold, and crops the clear license plate image as the target license plate image.

[0257] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0258] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0259] Figure 13 A schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of products for adjusting exposure parameters, such as an IPC (Internet Protocol Camera), or other imaging devices that may be equipped with a CPU for adjusting exposure parameters. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0260] like Figure 13 As shown, the electronic device 1300 includes at least a lens 1301, an image sensor 1302, and a main control chip 1303. Light passes through the lens 1301 and enters the image sensor 1302. The photosensitive element of the image sensor 1302 converts the light signal into an electrical signal, thereby obtaining image data. The main control chip 1303 is responsible for overall scheduling, such as adjusting exposure parameters using the method provided in the embodiments of this application.

[0261] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0262] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0263] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0264] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0265] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for adjusting exposure parameters, characterized in that, The method includes: Acquire a license plate image, which is determined from the received original image; In response to the ambient brightness information of the original image being less than a preset brightness threshold, the license plate image is divided into multiple image blocks, and a target image block corresponding to the license plate area is determined from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block; The average brightness of the license plate image is determined based on the plurality of image blocks, the first weight, and the second weight; In response to the average brightness being greater than the overexposure threshold, the image exposure parameters are smoothly adjusted based on the exposure adjustment increment.

2. The method according to claim 1, characterized in that, Determining whether the ambient brightness information of the original image is less than the preset brightness threshold includes: Obtain the current exposure value and dynamic exposure reference value of the original image, wherein the ambient brightness information includes the current exposure value and dynamic exposure reference value; The current exposure reference value is determined based on the current exposure value and the dynamic exposure reference value; Based on the comparison between the current exposure reference value and the current exposure value, it is determined whether the ambient brightness information of the original image is less than the preset brightness threshold.

3. The method according to claim 2, characterized in that, The step of dividing the license plate image into multiple image blocks and determining the target image block corresponding to the license plate region from the multiple image blocks includes: dividing the license plate image into the multiple image blocks; wherein, each image block corresponds to unique index information; The number of rows and columns of the plurality of image blocks that construct the license plate image are halved to obtain the number of rows and columns of the target image block, and the target image block is determined based on the number of rows and columns of the target image block; After determining the target image patch based on the number of rows and columns of the target image patch, the method further includes: Based on the index information of each image block, a first weight for each target image block and a second weight for each non-target image block are determined.

4. The method according to claim 1, characterized in that, Determining the average brightness of the license plate image based on the plurality of image blocks, the first weight, and the second weight includes: Calculate the brightness value of the first Y component based on the target image block and the first weight; The brightness value of the second Y component is calculated based on the non-target image block and the second weight; The average brightness of the license plate area is obtained by weighting the brightness values ​​of the first Y component and the second Y component.

5. The method according to claim 1, characterized in that, After determining the average brightness of the license plate image, the method further includes: The overexposure state corresponding to the average brightness of the license plate image is classified according to the preset first overexposure threshold and second overexposure threshold. The smooth adjustment of image exposure parameters based on exposure adjustment increments includes: In response to the average brightness being greater than or equal to the first overexposure threshold, the exposure adjustment increment is determined based on the error between the average brightness and the target brightness; The image exposure parameters are smoothly adjusted according to the exposure adjustment increment.

6. The method according to claim 5, characterized in that, In response to the average brightness being less than the first overexposure threshold and greater than or equal to the second overexposure threshold, the mean intensity of the area corresponding to the license plate area is calculated based on the horizontal and vertical gradients of the license plate area. The clarity of the license plate image is determined based on the mean intensity of the region and a preset edge intensity threshold.

7. The method according to claim 6, characterized in that, The smooth adjustment of image exposure parameters based on exposure adjustment increments includes: If the mean intensity of the region is less than the preset edge intensity threshold, then the license plate image is determined to be unclear. The image exposure parameters are smoothly adjusted according to the exposure adjustment increment.

8. The method according to claim 6, characterized in that, The step of calculating the mean intensity of the area corresponding to the license plate region based on the horizontal and vertical gradients of the license plate region includes: Calculate the gradient magnitude based on the horizontal and vertical gradients of the license plate area; The mean intensity of the area corresponding to the license plate region is calculated based on the gradient magnitude and the size of the license plate region.

9. The method according to claim 7, characterized in that, In response to the average brightness being less than the second overexposure threshold, the target license plate image is captured; or, In response to the mean intensity of the region being greater than or equal to the preset edge intensity threshold, the license plate image is determined to be clear, and the clear license plate image is cropped as the target license plate image.

10. A device for adjusting exposure parameters, characterized in that, The device includes: An acquisition unit is used to acquire a license plate image, wherein the license plate image is determined from a received original image; The first determining unit is configured to, in response to the ambient brightness information of the original image being less than a preset brightness threshold, divide the license plate image into multiple image blocks and determine the target image block corresponding to the license plate region from the multiple image blocks; wherein, each image block corresponds to the same or different weights, and the first weight of the target image block is greater than the second weight of the non-target image block; The second determining unit is used to determine the average brightness of the license plate image based on the plurality of image blocks, the first weight, and the second weight; An adjustment unit is used to smoothly adjust the image exposure parameters based on the exposure adjustment increment in response to the average brightness being greater than the overexposure threshold.

Images