Exposure data adjustment methods, apparatus and computer equipment

Abstract

This application relates to an exposure data adjustment method, apparatus, and computer device. The method includes: determining histogram data and image quality data of a current image; determining first exposure data of the current image based on the histogram data; and determining second exposure data of the current image based on the image quality data; fusing the first exposure data and the second exposure data to obtain desired exposure data; and adjusting the first exposure data based on the difference between the first exposure data and the desired exposure data. By employing the above technical solution, the accuracy of the first exposure data adjustment result is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an exposure data adjustment method, apparatus, and computer device. Background Technology

[0002] As the requirements for vehicle intelligence continue to increase, the usage rate of in-vehicle cameras in vehicles is also gradually increasing, providing convenience for vehicle assisted driving, safety monitoring, and driving recording.

[0003] Existing vehicle-mounted cameras continuously monitor the image histogram information of each frame generated by the ISP (Image Signal Processor) based on AEC (Automatic Exposure Control) to determine the exposure data of the corresponding image frame, and adjust the exposure data in reverse based on the difference between the exposure data and the expected exposure data.

[0004] However, the above method is limited by the limited information carried by the histogram, resulting in low accuracy of the determined exposure data adjustment results. Summary of the Invention

[0005] Therefore, it is necessary to provide an exposure data adjustment method, apparatus, and computer equipment that can improve the accuracy of exposure data adjustment results in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for adjusting exposure data, including:

[0007] Determine the histogram data and image quality data of the current image;

[0008] Based on the histogram data, determine the first exposure data of the current image; and,

[0009] Based on the image quality data, determine the second exposure data of the current image;

[0010] The first exposure data and the second exposure data are fused to obtain the desired exposure data;

[0011] The first exposure data is adjusted based on the difference between the first exposure data and the desired exposure data.

[0012] In one embodiment, determining the image quality data of the current image includes: acquiring texture distribution features obtained by feature extraction of the image to be processed; wherein the image to be processed includes the current image and a reference image; and determining the image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

[0013] In one embodiment, the texture distribution features of the image to be processed are determined by: extracting the target texture features of the image to be processed; extracting the distribution features of the target texture features of the image to be processed based on a multivariate Gaussian model to obtain the texture distribution features of the image to be processed; wherein the multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0014] In one embodiment, extracting the target texture features of the image to be processed includes: extracting a first texture feature of the image to be processed based on a generalized Gaussian distribution; and extracting a second texture feature of the image to be processed in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture features include the first texture feature and / or the second texture feature.

[0015] In one embodiment, the method further includes: downsampling the image to be processed to obtain a derived image of the image to be processed; extracting a third texture feature of the derived image based on a generalized Gaussian distribution; and extracting a fourth texture feature of the derived image in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0016] In one embodiment, extracting the target texture features of the image to be processed includes: dividing the image to be processed into at least one candidate image block; for each candidate image block, determining the sharpness data of the candidate image block based on the distribution of different pixel values ​​in the candidate image block; selecting a target image block from the at least one candidate image block based on the sharpness data of each candidate image block; and extracting the target texture features of the target image block as the target texture features of the image to be processed.

[0017] In one embodiment, determining the second exposure data of the current image based on the image quality data includes: determining the second exposure data of the current image based on the image quality data using a target mapping function; wherein the target mapping function is generated by: determining reference exposure data of a reference image acquired under preset quality acquisition requirements, and the reference image quality of the reference image; and performing polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0018] In one embodiment, the method further includes: obtaining the acquisition environment type of the current image; selecting a candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; wherein the acquisition environment types of the reference images corresponding to different candidate mapping functions are different when they are generated.

[0019] Secondly, this application also provides an exposure data adjustment device, comprising:

[0020] The first determining module is used to determine the histogram data and image quality data of the current image;

[0021] The second determining module is configured to determine the first exposure data of the current image based on the histogram data; and,

[0022] The third determining module is used to determine the second exposure data of the current image based on the image quality data;

[0023] The data fusion module is used to fuse the first exposure data and the second exposure data to obtain the desired exposure data;

[0024] The data adjustment module is used to adjust the first exposure data based on the difference between the first exposure data and the desired exposure data.

[0025] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0026] Determine the histogram data and image quality data of the current image;

[0027] Based on the histogram data, determine the first exposure data of the current image; and,

[0028] Based on the image quality data, determine the second exposure data of the current image;

[0029] The first exposure data and the second exposure data are fused to obtain the desired exposure data;

[0030] The first exposure data is adjusted based on the difference between the first exposure data and the desired exposure data.

[0031] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0032] Determine the histogram data and image quality data of the current image;

[0033] Based on the histogram data, determine the first exposure data of the current image; and,

[0034] Based on the image quality data, determine the second exposure data of the current image;

[0035] The first exposure data and the second exposure data are fused to obtain the desired exposure data;

[0036] The first exposure data is adjusted based on the difference between the first exposure data and the desired exposure data.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0038] Determine the histogram data and image quality data of the current image;

[0039] Based on the histogram data, determine the first exposure data of the current image; and,

[0040] Based on the image quality data, determine the second exposure data of the current image;

[0041] The first exposure data and the second exposure data are fused to obtain the desired exposure data;

[0042] The first exposure data is adjusted based on the difference between the first exposure data and the desired exposure data.

[0043] The aforementioned exposure data adjustment method, apparatus, and computer equipment, by incorporating image quality data and histogram data of the current image, replace the traditional technique of determining the desired exposure data solely based on histogram data. This allows the desired exposure data to fully consider the impact of image quality data, thereby improving the accuracy of the determined desired exposure data. Correspondingly, based on the difference between the first exposure data and the desired exposure data, the first exposure data is adjusted, making the exposure parameter adjustment process more reasonable, thus improving the accuracy of the first exposure parameter adjustment result. This, in turn, helps to improve the image quality of images acquired when using the adjusted result for image acquisition. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating an exposure data adjustment method in one embodiment;

[0046] Figure 2A This is a flowchart illustrating the steps for determining image quality data in one embodiment;

[0047] Figure 2B This is a schematic diagram of the pixel extension direction in one embodiment;

[0048] Figure 2C This is a schematic diagram of the filtering results of a target image block in one embodiment;

[0049] Figure 2D This is a schematic diagram of the filtering results for another target image block in one embodiment;

[0050] Figure 3 This is a flowchart illustrating the steps for determining the second exposure data in one embodiment;

[0051] Figure 4 This is a flowchart illustrating the exposure data adjustment method in another embodiment;

[0052] Figure 5 This is a structural block diagram of an exposure data adjustment device in one embodiment;

[0053] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] In one exemplary embodiment, such as Figure 1 As shown, an exposure data adjustment method is provided. This embodiment illustrates the method applied to a terminal, but it is understood that the method can also be applied to a server, or to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0056] S110, determine the histogram data and image quality data of the current image.

[0057] The current image can be understood as the image currently acquired by the image acquisition device that requires exposure parameter adjustment. The histogram data is used to characterize the distribution of pixel brightness in the current image, and may include at least one of data such as image brightness distribution, image pixel distribution, and histogram type; this application does not impose any new limitations on this. The image quality data is used as evaluation result data for assessing image quality from at least one dimension; this application does not impose any limitations on the evaluation dimension, for example, it may include an image sharpness dimension.

[0058] It is worth noting that the histogram data and image quality data of the current image can be determined by at least one method in the prior art, and this application does not limit the specific technical means used to determine the two.

[0059] In one optional embodiment, the computing device executing the exposure data adjustment method can directly acquire the current image and determine its histogram data and image quality data. Alternatively, to reduce the computational load of the computing device executing the exposure data adjustment method and thus improve its efficiency in adjusting exposure data, the histogram data and image quality data of the current image can be determined by an image acquisition device that acquires the current image, or by other devices communicatively connected to the image acquisition device and the computing device executing the exposure data adjustment method. When the computing device executing the exposure data adjustment method needs to adjust exposure data, the histogram data and image quality data can be directly acquired from the corresponding device.

[0060] S120, based on the histogram data, determines the first exposure data for the current image.

[0061] It is worth noting that at least one of the conventional techniques can be used to determine the first exposure data of the current image based on histogram data. This application does not limit the method of determining the first exposure data.

[0062] For example, the exposure parameter information carried in the histogram data can be directly read as the first exposure data of the current image. Alternatively, the first exposure data of the current image can be determined based on the histogram data through methods such as calling the exposure parameter interface.

[0063] S130, determine the second exposure data for the current image based on the image quality data.

[0064] For example, a mapping relationship between different image quality data and exposure data can be pre-built, and when exposure data adjustment is required, the corresponding exposure data under the mapping relationship can be found as the second exposure data through the image quality data of the current image.

[0065] The above mapping relationship can be constructed manually or obtained through a large number of experiments, and this application does not impose any restrictions on it.

[0066] It is worth noting that the magnitude of the first exposure data reflects the distribution of image brightness, while the magnitude of the second exposure data reflects the quality of the image.

[0067] It should be noted that S120 can be executed before or after S130, or both can be executed simultaneously or in an overlapping manner. This application does not impose any restrictions on the specific execution order of the two.

[0068] S140, the first exposure data and the second exposure data are fused to obtain the desired exposure data.

[0069] Among them, the expected exposure data is used to characterize the idealized optimal exposure data corresponding to the current image, that is, the clear image that meets the preset quality acquisition requirements acquired by the image acquisition device of the current image under the same image acquisition conditions.

[0070] In an optional embodiment, the first exposure data and the second exposure data can be directly summed, and the summation result can be used as the desired exposure data.

[0071] In another optional embodiment, the weights of the first exposure data and the second exposure data can be preset, and the weighted sum of the first exposure data and the second exposure data under their respective weights can be used as the desired exposure data. The weights of the first exposure data and the second exposure data can be set or adjusted by a technician based on needs or experience, or determined repeatedly through numerous experiments, as long as the sum of the two is guaranteed to be 1. This application does not impose any limitations on this. In one specific implementation, the weight of the first exposure data can be 0.7, and the weight of the second exposure data can be 0.3.

[0072] S150, adjust the first exposure data based on the difference between the first exposure data and the desired exposure data.

[0073] The first exposure data, determined solely by histogram data, is somewhat limited. While it reflects the actual exposure parameter settings of the image acquisition device during image acquisition, the desired exposure data, a fusion of the first and second exposure data, more accurately reflects the required exposure parameter settings for meeting preset quality acquisition requirements. Therefore, the difference between the first and desired exposure data can be used to determine whether adjustments to the first exposure data are necessary. Furthermore, if adjustments are required, the direction and magnitude of the adjustment can be quantified based on the specific numerical difference between the first and desired exposure data.

[0074] In an optional embodiment, the absolute value of the difference between the first exposure data and the desired exposure data can be used as the difference data to quantify the difference between the two; the exposure difference range to which the difference data belongs is determined, and the first exposure data is adjusted according to the preset adjustment direction and adjustment range under the exposure difference range. The adjustment direction and adjustment range corresponding to different exposure difference ranges can be set by technicians according to their needs or experience, or determined repeatedly through numerous experiments; this application does not impose any limitations on this.

[0075] In one specific implementation, if the aforementioned difference data is less than a first difference threshold, then no adjustment is needed to the first exposure data; if the aforementioned difference data is not less than the first difference threshold and is less than a second difference threshold, then the first exposure data is adjusted according to a first adjustment range; if the aforementioned difference data is not less than the second difference threshold and is less than a third difference threshold, then the first exposure data is adjusted according to a second adjustment range; if the aforementioned difference data is not less than the third difference threshold, then the result obtained by amplifying the current exposure data by a first preset factor can be used as a third adjustment range to adjust the first exposure data. Wherein, the first difference threshold is less than the second difference threshold, the second difference threshold is less than the third difference threshold; the first adjustment range is less than the second adjustment range; and the second adjustment range is less than the third adjustment range. At least one of the first preset factor, the first difference threshold, the second difference threshold, the third difference threshold, the first adjustment range, and the second adjustment range can be set or adjusted by a technician according to needs or experience, or determined repeatedly through numerous experiments; this application does not impose any limitations on this.

[0076] In another specific implementation, if it is determined that the first exposure data needs to be adjusted, the direction of adjustment for the first exposure data can be determined based on the relative size relationship between the first exposure data and the desired exposure data.

[0077] This application's embodiments introduce image quality data and histogram data of the current image, replacing the traditional technique of determining the desired exposure data solely based on histogram data. This allows the desired exposure data to fully consider the impact of image quality data, thereby improving the accuracy of the determined desired exposure data. Correspondingly, based on the difference between the first exposure data and the desired exposure data, the first exposure data is adjusted, making the exposure parameter adjustment process more reasonable. This improves the accuracy of the first exposure parameter adjustment result, and consequently helps to improve the image quality of the image acquired when using the adjusted result.

[0078] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment in which the step of determining image quality data in S110 is refined to improve the convenience of determining the image quality data.

[0079] See Figure 2A The steps for determining the image quality data shown include:

[0080] S210, Obtain the texture distribution features obtained by feature extraction of the image to be processed; wherein, the image to be processed includes the current image and the reference image.

[0081] The reference image can be understood as an image whose quality meets preset quality requirements, such as a clear image whose sharpness meets the sharpness requirements. The texture distribution features of the image to be processed characterize the distribution of texture features in the image, and may include the mean vector and covariance matrix of the texture features, etc., which are not limited in this application. The mean vector reflects the center position of the texture features in the image to be processed, corresponding to the center position of the color, brightness, and edge texture of the entire image; the covariance matrix reflects the correlation between different features in the texture features, as well as the shape, orientation, and spatial relationships of objects in the image.

[0082] For example, the computing device executing the exposure data adjustment method can directly extract features from the image to be processed to obtain the corresponding texture distribution features. Alternatively, to reduce the amount of data computation on the computing device and improve the efficiency of exposure data adjustment, other devices connected in communication with the computing device can extract the texture distribution features of the image to be processed, and when exposure data adjustment is required, the corresponding texture distribution features can be retrieved from the other device.

[0083] In an optional embodiment, the target texture features of the image to be processed can be directly extracted, and the distribution features of the target texture features of the image to be processed can be extracted based on a multivariate Gaussian model to obtain the texture distribution features of the image to be processed.

[0084] Among them, the target texture features of the image to be processed carry key texture information of the image to be processed, which characterizes the richness and diversity of information carried in the image to be processed.

[0085] Alternatively, a pre-trained texture feature extraction network can be used to extract the target texture features of the image to be processed.

[0086] In an alternative embodiment, the target texture features may include first texture features; correspondingly, the first texture features of the image to be processed may be extracted based on a generalized Gaussian distribution.

[0087] The first texture feature may carry at least one of the following information: the shape, kurtosis, and distribution width of the texture distribution curve in the image to be processed.

[0088] The Generalized Gaussian Distribution (GGD) is a continuous probability distribution that is a generalized form of the normal and Laplace distributions. It has the advantages of flexible form and the ability to simulate different data distribution characteristics by adjusting its shape parameters.

[0089] The distribution characteristics of the image to be processed can be determined using the following probability density function of the generalized Gaussian distribution:

[0090] ;

[0091] ;

[0092] ;

[0093] in, and All are shape parameters of the distribution; It is the width parameter of the distribution, corresponding to the standard deviation or local standard deviation of the image to be processed; It is a real number or a complex number; It is a gamma function used to ensure the normalization of the distribution.

[0094] For example, shape parameters can be pre-defined. Define the search interval and search step size to obtain the shape parameters. Candidate values. For example, The range is set to [0.2:0.001:10], meaning that within the search interval [0.2, 10], the range is calculated with a step size of 0.001. The setting of candidate values.

[0095] All of the above Substitute the candidate values ​​into the following ratio functions respectively :

[0096] ;

[0097] The following formula is used to compare the functions. Estimate the value to obtain the estimated value. :

[0098] ;

[0099] ;

[0100] ;

[0101] Wherein, random variable X(x1,x2,...,x) m () Corresponds to the pixel values ​​of the normalized image to be processed.

[0102] Sure and The distance, and calculate the shape parameters in the case of minimum distance. corresponding The shape parameters are determined based on the following formula. corresponding :

[0103] .

[0104] Correspondingly, it is possible to generate parameters including shape parameters. Shape parameters and width parameter The first texture feature.

[0105] Understandably, a generalized Gaussian distribution is introduced to represent the texture distribution curve of the image to be processed. Since different images exhibit different causes of distortion during image quality assessment, the shape of the generalized Gaussian distribution curve will vary considerably. Therefore, given the aforementioned characteristics of the generalized Gaussian distribution, abnormal distributions in the image to be processed can be represented and used as constituent elements of the target texture features of the image to be processed, participating in subsequent calculations.

[0106] In another alternative embodiment, the target texture features may include second texture features; correspondingly, the second texture features of the image to be processed can be extracted in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution.

[0107] The second texture feature may carry at least one of the following information: the shape, center position, and diffusion degree of the texture distribution curve in the image to be processed. The second texture features in different pixel extension directions can reflect the texture correlation in the corresponding pixel extension direction. The number of pixel extension directions is at least one, and typically includes at least two, to improve the richness and comprehensiveness of the second texture feature.

[0108] In one specific implementation, see Figure 2B The pixel extension direction diagram shown below indicates that for a certain pixel point I(i, j) in the image to be processed, the following four directions can be used as the pixel extension directions of the second texture feature: I(i, j)I(i+1, j), I(i, j)I(i-1, j+1), I(i, j)I(i+1, j+1) and I(i, j)I(i, j+1).

[0109] Among them, the Asymmetric Generalized Gaussian Distribution (AGGD) is an important probability distribution function that can describe the distribution of data with asymmetric characteristics.

[0110] For any pixel extension direction, the distribution characteristics of the image to be processed can be determined based on the following probability density function:

[0111] ;

[0112] Where x is a random variable, corresponding to each pixel of the normalized image to be processed; It is a shape parameter of the distribution, which controls the peak value of the distribution, that is, the sharpness of the distribution; It is the scale parameter of the negative half-axis, which controls the width of the distribution on the left. It is the scale parameter of the positive semi-axis, which controls the width of the distribution on the right side; and This reflects the degree of diffusion in the distribution; the two can differ, thus demonstrating the asymmetry of the distribution. Specifically, when x ≤ 0, the distribution density follows the pattern of -x. The proportion decreases rapidly; when x≥0, the distribution density decreases rapidly with increasing x according to... The proportion of [something] decreases rapidly.

[0113] For the central position This distribution characteristic can be represented by the following formula:

[0114] ;

[0115] in, and The distribution is the gamma function at and The value at that location. The gamma function can be found in the preceding content and will not be repeated here.

[0116] For example, shape parameters can be pre-defined. Define the search interval and search step size to obtain the shape parameters. Candidate values. For example, The range is set to [0.2:0.001:10], meaning that within the search interval [0.2, 10], the range is calculated with a step size of 0.001. The setting of candidate values.

[0117] All of the above Substitute the candidate values ​​into the following ratio functions respectively :

[0118] ;

[0119] The scaling parameters of the negative semi-axis of the asymmetric generalized Gaussian grouping are determined using the following formulas. Scale parameters of the positive half axis :

[0120] ;

[0121] ;

[0122] in, It is the number of samples in the random variable whose pixel values ​​are located on the negative half-axis; It is the number of samples in a random variable whose pixel values ​​lie on the positive half-axis.

[0123] The asymmetry of the asymmetric generalized Gaussian distribution can be estimated using the following formula:

[0124] .

[0125] The following formula is used to apply the aforementioned ratio function. Estimation is performed to obtain the estimator. :

[0126] ;

[0127] ;

[0128] ;

[0129] in, It is the average of the absolute values ​​of the random variables; It is the average of the squares of the random variables.

[0130] Sure and The distance, and calculate the shape parameters in the case of minimum distance. corresponding The scale parameters are determined based on the following formula. corresponding and scale parameters corresponding :

[0131] ;

[0132] ;

[0133] Correspondingly, for any pixel extension direction, it is possible to generate parameters including shape parameters. Scale parameters and and central location These four second texture features.

[0134] It should be noted that for each image to be processed, a first texture feature including shape and width parameters can be generated, and a second texture feature including shape, center position, negative half-axis width, and positive half-axis width (i.e., diffusion degree) parameters can be generated for each pixel extension direction. If there are 4 pixel extension directions, a total of 18 target texture features can be generated; including 2 first texture features and 4×4 second texture features.

[0135] To further enhance the richness of the extracted target texture features, for each image to be processed, the image to be processed can be downsampled to obtain a derived image of the image to be processed, and texture features can be extracted based on the derived image, thereby achieving the purpose of enriching the target texture features.

[0136] The number of downsampling operations and the sampling interval can be set or adjusted by technicians according to their needs or experience. This application does not impose any restrictions on these aspects.

[0137] For example, a third texture feature of the derived image can be extracted based on a generalized Gaussian distribution; and a fourth texture feature of the derived image in at least one pixel extension direction can be extracted based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0138] Taking a 1 / 2 downsampling to generate a derived image as an example, the derived image can be used as a new random variable to replace the aforementioned image to be processed and re-extract texture features to obtain new target texture features.

[0139] In one specific implementation, for a derived image, if the pixel extension direction is 4, a total of 18 target texture features can be generated; including 2 third texture features and 4×4 fourth texture features.

[0140] It is worth noting that when performing the aforementioned feature extraction of target texture features, feature extraction can be performed on the entire image to be processed or on a local region within the image to be processed. To reduce the amount of data computation in the feature extraction process, in an optional embodiment, the image to be processed can be divided into at least one candidate image block; a target image block can be selected from the at least one candidate image block; and the target texture features of only the target image block can be extracted as the target texture features of the image to be processed.

[0141] For example, for each candidate image block, the sharpness data of the candidate image block can be determined based on the distribution of different pixel values ​​in the candidate image block; and the target image block can be selected from at least one candidate image block based on the sharpness data of each candidate image block.

[0142] Among them, the sharpness data reflects the regional changes in the information carried by the candidate image patch.

[0143] In one specific implementation, the image to be processed can be divided into at least one candidate image block according to a preset size, and an index value (b=1, 2, ..., B) can be established for each candidate image block. For each candidate image block, the sharpness data of the candidate image block is determined according to the average of the standard deviation (or local standard deviation) of each pixel in the candidate image block. The sharpness data of each candidate image block is sorted, and a sharpness filtering threshold is determined according to the sorting result. The candidate image blocks whose sharpness data is greater than the sharpness filtering threshold are taken as target image blocks.

[0144] Optionally, the sharpness data located at a preset quantile (e.g., 80%) in the ascending sort results can be used as the sharpness filtering threshold. Alternatively, the product of the maximum value in the sharpness data and a preset percentage (e.g., 80%) can be used as the sharpness filtering threshold.

[0145] See Figure 2C and Figure 2D The diagram shows the filtering results of the target image blocks. The image blocks retained in the diagram are the target image blocks. Compared with the non-target image blocks, the target image blocks carry relatively rich texture information.

[0146] It is worth noting that the aforementioned normalization process for the image to be processed can be implemented using at least one traditional normalization method.

[0147] In an optional embodiment, the original acquired image to be processed can be normalized in the following manner:

[0148] ;

[0149] in, The average pixel value of the image to be processed; is the standard deviation of pixels in the image to be processed; Set a preset value to avoid a denominator of 0; for example, it could be 1. For the image to be processed at the pixel point The pixel value on the screen.

[0150] It is understandable that the image normalization result obtained by normalizing the image to be processed using the above method has a lower dependence on the strength of image texture, and the image features extracted subsequently have higher practicality.

[0151] The pixel mean and pixel standard deviation can be achieved using traditional methods for determining the mean and standard deviation, or by using local image processing methods. This application does not impose any limitations on these methods.

[0152] In one specific implementation, a Gaussian model can be applied to the image using the following formula to determine the local mean and local standard deviation. Correspondingly, the local mean can be used as the aforementioned pixel mean, and the local standard deviation can be used as the aforementioned pixel standard deviation.

[0153] ;

[0154] ;

[0155] Where K is the length of the pixel along the length of the image; L is the length of the pixel along the height of the image. The corresponding pixel number.

[0156] The above details the process of extracting target texture features from the image to be processed. The following will explain the multivariate Gaussian model and its application.

[0157] In an alternative embodiment, the multivariate Gaussian model is fitted based on the target texture features extracted from at least one sample image.

[0158] The sample image can be an image that meets the quality requirements and is acquired under preset quality acquisition conditions.

[0159] For example, the target texture features of the image to be processed can be input into the expression of a multivariate Gaussian model; the expression of the multivariate Gaussian model can be estimated, for example, by maximum likelihood estimation, to obtain the mean vector and covariance matrix of the model, which can be used as the texture distribution features of the image to be processed.

[0160] In a specific implementation, the multivariate Gaussian model can be expressed by the following formula:

[0161] ;

[0162] in, For a multivariate Gaussian model function; A target texture feature containing k elements; It is the mean vector of the multivariate Gaussian model; It is the covariance matrix of a multivariate Gaussian model.

[0163] S220, determine the image quality data of the current image based on the difference between the texture distribution characteristics of the current image and the texture distribution characteristics of the reference image.

[0164] For example, the distance between the texture distribution features of the current image and the texture distribution features of the reference image can be determined. This distance value can then be used to quantify the difference in texture distribution features between the two images, and based on this distance value, the image quality data of the current image can be determined. The image quality data changes monotonically with the distance value; for example, the image quality data can monotonically increase or decrease with the distance value.

[0165] In one specific implementation, the image quality data of the current image can be determined using the following formula:

[0166] ;

[0167] in, Image quality data for the current image; and These are the mean vector and covariance matrix of the reference image, respectively; and These are the mean vector and covariance matrix of the current image, respectively.

[0168] This application embodiment introduces the texture distribution features of the current image and the texture distribution features of the reference image, and determines the image quality data of the current image based on the difference between the two. The determination process is convenient and quick, with a small amount of data computation, which helps to improve the execution efficiency of the exposure data adjustment method.

[0169] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment in which the step of determining the second exposure data in S130 is refined to improve the accuracy of the second exposure data determination result.

[0170] See Figure 3 The steps for determining the second exposure data shown include:

[0171] S310, based on the target mapping function, determines the second exposure data of the current image according to the image quality data.

[0172] The target mapping function characterizes the mapping transformation relationship between image quality data and exposure data. Through this mapping transformation, the second exposure data corresponding to different image quality data can be determined. The input data of the target mapping function corresponds to the image quality data; the output data of the target mapping function corresponds to the second exposure data of the current image.

[0173] For example, image quality data is used as input data to a target mapping function to obtain the second exposure data of the current image.

[0174] In one embodiment, the target mapping function can be generated as follows: determine the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; perform polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0175] The reference image acquired under the preset quality acquisition requirements can be understood as a standard, clear image, meaning an image whose image quality data meets the requirements. The reference exposure data of the reference image can be understood as the exposure data used when acquiring the reference image under the preset quality acquisition requirements, or it can be the exposure data determined based on the histogram data of the reference image. The reference image quality can be understood as the image quality data corresponding to the reference image determined using the image quality data determination steps in the aforementioned embodiments.

[0176] For example, the exposure data of multiple reference images can be used as independent variables, the quality of the corresponding reference images can be used as dependent variables, polynomial fitting can be performed based on a preset polynomial model, and the fitting result can be used as the target mapping function.

[0177] Since the quality of images acquired in different image acquisition scenarios usually varies, such as the differences in road environments (highways, urban roads, rural roads, garages, tunnels, etc.) in driving scenarios, and the differences in high-light environments (daytime, nighttime, etc.), the differences in image quality and exposure parameters of reference images that can meet the preset quality acquisition requirements for the same area are relatively significant. Therefore, when constructing the mapping function between exposure data and image quality data, scene-related factors can be introduced for differentiated treatment.

[0178] In an optional embodiment, reference exposure data and reference image quality of the reference image to be acquired under the preset quality acquisition requirements can be determined in advance for different acquisition environment types (corresponding to different scenarios); for the same acquisition environment type, a polynomial fitting is performed based on the reference exposure data and corresponding reference image quality of each reference image under that acquisition environment type to obtain the candidate mapping function under that acquisition environment type.

[0179] Correspondingly, during the determination of the second exposure data for the current image, the acquisition environment type of the current image can be obtained in advance. From at least one candidate mapping function, the candidate mapping function corresponding to the acquisition environment type is selected as the target mapping function. The different candidate mapping functions are generated based on different acquisition environment types of the reference image. The advantage of this approach is that it allows for the construction of candidate mapping functions tailored to the differences in acquisition environment types. Consequently, by incorporating the acquisition environment type of the current image during the determination of the second exposure data, the influence of different acquisition environment types on the determined second exposure data can be avoided, improving the accuracy of the second exposure data determination result. This, in turn, improves the accuracy of the desired exposure data determination result, and further contributes to improving the accuracy of the first exposure data adjustment result.

[0180] This application embodiment obtains a target mapping function by incorporating reference exposure data and corresponding reference image quality from at least two reference images and performing polynomial fitting. Based on this target mapping function, the second exposure data is directly determined from the image quality data. This approach replaces the traditional table lookup method for determining the second exposure data, resulting in higher computational efficiency and eliminating the need for significant upfront investment in data table construction, thus reducing the initial cost of determining the second exposure data.

[0181] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment in which the exposure data adjustment method is described in detail.

[0182] See Figure 4 The exposure data adjustment method shown includes:

[0183] S401, Determine the histogram data of the current image.

[0184] S402, Divide the image into blocks: Divide the image to be processed into at least one candidate image block. The image to be processed includes the current image and the reference image.

[0185] S403, Filtering image blocks: For each candidate image block, determine the sharpness data of the candidate image block according to the distribution of different pixel values ​​in the candidate image block; select the target image block from at least one candidate image block according to the sharpness data of each candidate image block.

[0186] S404, Extract texture features: Based on a generalized Gaussian distribution, extract the first texture feature of the target image patch in the image to be processed; wherein, the image to be processed includes the current image and the reference image; based on an asymmetric generalized Gaussian distribution, extract the second texture feature of the target image patch in the image to be processed in at least one pixel extension direction; downsample the image to be processed to obtain a derived image of the target image patch in the image to be processed; based on a generalized Gaussian distribution, extract the third texture feature of the target image patch in the derived image; based on an asymmetric generalized Gaussian distribution, extract the fourth texture feature of the target image patch in the derived image in at least one pixel extension direction; wherein, the target texture features of the image to be processed include the first texture feature, the second texture feature, the third texture feature, and the fourth texture feature.

[0187] S405, Determine image quality data: Based on a multivariate Gaussian model, extract the distribution features of the target texture features of the image to be processed to obtain the texture distribution features of the image to be processed; determine the image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image. The multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0188] S406, Determine the desired exposure data: Based on the histogram data, determine the first exposure data of the current image; obtain the acquisition environment type of the current image; select the candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; based on the target mapping function and the image quality data, determine the second exposure data of the current image; fuse the first exposure data and the second exposure data to obtain the desired exposure data;

[0189] The acquisition environment types of the reference images corresponding to the generation of different candidate mapping functions are different. The target mapping function is generated as follows: determine the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; perform polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0190] S407, Adjust exposure parameters: Adjust the first exposure data based on the difference between the first exposure data and the desired exposure data.

[0191] When it is necessary to adjust the first exposure data, the target gain coefficient can be determined first based on the difference between the first exposure data and the desired exposure data. The target gain coefficient is then divided according to the preset damping coefficient to obtain the current gain coefficient for each gain adjustment. Based on the current gain data, the gain is allocated to different exposure parameters in the first exposure data. The allocated exposure parameters are then made effective within a preset time window, thereby realizing the gradual adjustment of the first exposure data.

[0192] It should be noted that each step adjustment can correspond to a preset number of frames, such as a single frame. The preset damping coefficient can be determined based on the frame rate of the image acquisition device and the acquisition scene in which the image acquisition device is located.

[0193] For example, the target gain coefficient can be determined using the following formula:

[0194] ;

[0195] in, It is the expected exposure data; This is the first data to be exposed; is the target gain coefficient.

[0196] For example, the following formula can be used to determine the current gain coefficient for each successive adjustment of exposure data:

[0197] ;

[0198] in, It is the preset damping coefficient; The target gain coefficient; This is the gain coefficient from the previous iteration; This is the current gain coefficient for the current iteration.

[0199] For example, for a vehicle-mounted camera with a frame rate of 30 FPS, the preset damping coefficient can first be set to the first coefficient (e.g., 0.2, meaning 80% of the old parameters and 20% of the new parameters). After accumulating a first preset number of adjusted image frames (e.g., 10), the preset damping coefficient can be adjusted to the second coefficient (e.g., 0.9, meaning the proportion of the old parameters decreases to 10%). Further, after accumulating a second preset number of adjusted image frames (e.g., 30), the preset damping coefficient can be set to the third coefficient (e.g., 1, meaning the proportion of the old parameters is ignored), thus gradually converging the new parameters to the target gain coefficient. For vehicle-mounted camera applications, especially in high-speed scenarios where dynamic changes are rapid, it is generally necessary to transition to the ideal brightness value within 5 frames.

[0200] In an optional embodiment, when allocating gain to different exposure parameters in the first exposure data based on the current gain data, the current gain data can be mapped to control parameters such as sensor (image sensor in image acquisition device) exposure time, sensor gain, and ISP gain. Exposure time can improve the signal-to-noise ratio of the image. A common strategy is to utilize the exposure time as much as possible within the constraints, then allocate it to the sensor gain, and finally allocate the remaining gain to the ISP digital gain.

[0201] It is worth noting that the control parameters described above need to take effect simultaneously in order for the image to achieve the expected exposure brightness. Furthermore, all parameters need to take effect within a specific time window, which is the time between the end of the previous frame and the start of the next frame. This time window is the sensor's vertical blanking window, which is relatively short, generally around 3 to 5 milliseconds.

[0202] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0203] Based on the same inventive concept, this application also provides an exposure data adjustment device for implementing the exposure data adjustment method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more exposure data adjustment device embodiments provided below can be found in the limitations of the exposure data adjustment method described above, and will not be repeated here.

[0204] In one exemplary embodiment, such as Figure 5 As shown, an exposure data adjustment device is provided, including: a first determining module 510, a second determining module 520, a third determining module 530, a data fusion module 540, and a data adjustment module 550. Among them,

[0205] The first determining module 510 is used to determine the histogram data and image quality data of the current image;

[0206] The second determining module 520 is used to determine the first exposure data of the current image based on the histogram data; and,

[0207] The third determining module 530 is used to determine the second exposure data of the current image based on the image quality data;

[0208] The data fusion module 540 is used to fuse the first exposure data and the second exposure data to obtain the desired exposure data;

[0209] The data adjustment module 550 is used to adjust the first exposure data based on the difference between the first exposure data and the desired exposure data.

[0210] In one embodiment, the first determining module 510 includes: a first acquiring unit, configured to acquire texture distribution features obtained by feature extraction of the image to be processed; wherein the image to be processed includes a current image and a reference image; and a first determining unit, configured to determine image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

[0211] In one embodiment, the first determining module 510 further includes: a first extraction unit for extracting target texture features of the image to be processed; and a second extraction unit for extracting distribution features of the target texture features of the image to be processed based on a multivariate Gaussian model to obtain texture distribution features of the image to be processed; wherein the multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0212] In one embodiment, the first extraction unit includes: a first extraction subunit for extracting a first texture feature of the image to be processed based on a generalized Gaussian distribution; and a second extraction subunit for extracting a second texture feature of the image to be processed in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature includes the first texture feature and / or the second texture feature.

[0213] In one embodiment, the first extraction unit further includes: a downsampling subunit for downsampling the image to be processed to obtain a derived image of the image to be processed; a third extraction subunit for extracting a third texture feature of the derived image based on a generalized Gaussian distribution; and a fourth extraction subunit for extracting a fourth texture feature of the derived image in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0214] In one embodiment, the first extraction unit includes: a first division subunit, configured to divide the image to be processed into at least one candidate image block; a first determination subunit, configured to determine the sharpness data of each candidate image block based on the distribution of different pixel values ​​in the candidate image block; a first selection subunit, configured to select a target image block from at least one candidate image block based on the sharpness data of each candidate image block; and a fifth extraction subunit, configured to extract the target texture features of the target image block as the target texture features of the image to be processed.

[0215] In one embodiment, the third determining module 530 includes: a second determining unit, configured to determine second exposure data of the current image based on a target mapping function and image quality data; wherein the target mapping function is generated in the following manner: determining reference exposure data of a reference image acquired under preset quality acquisition requirements, and reference image quality of the reference image; and performing polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0216] In one embodiment, the third determining module 530 further includes: a second acquisition unit, configured to acquire the acquisition environment type of the current image; and a second selection unit, configured to select a candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; wherein the acquisition environment types of the reference images corresponding to different candidate mapping functions are different when they are generated.

[0217] Each module in the aforementioned exposure data adjustment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0218] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an exposure data adjustment method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0219] In one alternative embodiment, the computer device may be a vehicle rearview mirror.

[0220] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0221] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0222] Determine the histogram data and image quality data of the current image;

[0223] Based on the histogram data, determine the first exposure data for the current image; and,

[0224] Based on the image quality data, determine the second exposure data for the current image;

[0225] The first exposure data and the second exposure data are merged to obtain the desired exposure data;

[0226] The first exposure data is adjusted based on the difference between the first exposure data and the expected exposure data.

[0227] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining texture distribution features obtained by feature extraction of the image to be processed; wherein the image to be processed includes a current image and a reference image; and determining image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

[0228] In one embodiment, when the processor executes the computer program, it further performs the following steps: extracting target texture features of the image to be processed; extracting distribution features of the target texture features of the image to be processed based on a multivariate Gaussian model to obtain texture distribution features of the image to be processed; wherein the multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0229] In one embodiment, when the processor executes the computer program, it further performs the following steps: extracting a first texture feature of the image to be processed based on a generalized Gaussian distribution; and extracting a second texture feature of the image to be processed in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature includes the first texture feature and / or the second texture feature.

[0230] In one embodiment, when the processor executes the computer program, it further performs the following steps: downsampling the image to be processed to obtain a derived image of the image to be processed; extracting a third texture feature of the derived image based on a generalized Gaussian distribution; and extracting a fourth texture feature of the derived image in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0231] In one embodiment, when the processor executes the computer program, it further performs the following steps: dividing the image to be processed into at least one candidate image block; for each candidate image block, determining the sharpness data of the candidate image block according to the distribution of different pixel values ​​in the candidate image block; selecting a target image block from at least one candidate image block according to the sharpness data of each candidate image block; and extracting the target texture features of the target image block as the target texture features of the image to be processed.

[0232] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the second exposure data of the current image based on the target mapping function and the image quality data; wherein the target mapping function is generated in the following manner: determining the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; and performing polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0233] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining the acquisition environment type of the current image; selecting a candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; wherein, the acquisition environment types of the reference images corresponding to different candidate mapping functions are different when they are generated.

[0234] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0235] Determine the histogram data and image quality data of the current image;

[0236] Based on the histogram data, determine the first exposure data for the current image; and,

[0237] Based on the image quality data, determine the second exposure data for the current image;

[0238] The first exposure data and the second exposure data are merged to obtain the desired exposure data;

[0239] The first exposure data is adjusted based on the difference between the first exposure data and the expected exposure data.

[0240] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining texture distribution features obtained by feature extraction of the image to be processed; wherein the image to be processed includes a current image and a reference image; and determining image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

[0241] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: extracting target texture features of the image to be processed; extracting distribution features of the target texture features of the image to be processed based on a multivariate Gaussian model to obtain texture distribution features of the image to be processed; wherein the multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0242] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: extracting a first texture feature of the image to be processed based on a generalized Gaussian distribution; and extracting a second texture feature of the image to be processed in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature includes the first texture feature and / or the second texture feature.

[0243] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: downsampling the image to be processed to obtain a derived image of the image to be processed; extracting a third texture feature of the derived image based on a generalized Gaussian distribution; and extracting a fourth texture feature of the derived image in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0244] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: dividing the image to be processed into at least one candidate image block; for each candidate image block, determining the sharpness data of the candidate image block according to the distribution of different pixel values ​​in the candidate image block; selecting a target image block from at least one candidate image block according to the sharpness data of each candidate image block; and extracting the target texture features of the target image block as the target texture features of the image to be processed.

[0245] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the second exposure data of the current image based on the target mapping function and the image quality data; wherein the target mapping function is generated in the following manner: determining the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; and performing polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0246] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the acquisition environment type of the current image; selecting a candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; wherein, the acquisition environment types of the reference images corresponding to different candidate mapping functions are different when they are generated.

[0247] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0248] Determine the histogram data and image quality data of the current image;

[0249] Based on the histogram data, determine the first exposure data for the current image; and,

[0250] Based on the image quality data, determine the second exposure data for the current image;

[0251] The first exposure data and the second exposure data are merged to obtain the desired exposure data;

[0252] The first exposure data is adjusted based on the difference between the first exposure data and the expected exposure data.

[0253] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining texture distribution features obtained by feature extraction of the image to be processed; wherein the image to be processed includes a current image and a reference image; and determining image quality data of the current image based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

[0254] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: extracting target texture features of the image to be processed; extracting distribution features of the target texture features of the image to be processed based on a multivariate Gaussian model to obtain texture distribution features of the image to be processed; wherein the multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

[0255] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: extracting a first texture feature of the image to be processed based on a generalized Gaussian distribution; and extracting a second texture feature of the image to be processed in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature includes the first texture feature and / or the second texture feature.

[0256] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: downsampling the image to be processed to obtain a derived image of the image to be processed; extracting a third texture feature of the derived image based on a generalized Gaussian distribution; and extracting a fourth texture feature of the derived image in at least one pixel extension direction based on an asymmetric generalized Gaussian distribution; wherein the target texture feature further includes the third texture feature and / or the fourth texture feature.

[0257] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: dividing the image to be processed into at least one candidate image block; for each candidate image block, determining the sharpness data of the candidate image block according to the distribution of different pixel values ​​in the candidate image block; selecting a target image block from at least one candidate image block according to the sharpness data of each candidate image block; and extracting the target texture features of the target image block as the target texture features of the image to be processed.

[0258] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the second exposure data of the current image based on the target mapping function and the image quality data; wherein the target mapping function is generated in the following manner: determining the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; and performing polynomial fitting based on the reference exposure data and corresponding reference image quality of at least two reference images to obtain the target mapping function.

[0259] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the acquisition environment type of the current image; selecting a candidate mapping function corresponding to the acquisition environment type from at least one candidate mapping function as the target mapping function; wherein, the acquisition environment types of the reference images corresponding to different candidate mapping functions are different when they are generated.

[0260] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0261] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0262] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0263] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for adjusting exposure data, characterized in that, include: Determine the histogram data and image quality data of the current image; Based on the histogram data, determine the first exposure data of the current image; as well as, Based on the image quality data, determine the second exposure data of the current image; The first exposure data and the second exposure data are fused to obtain the desired exposure data; The first exposure data is adjusted based on the difference between the first exposure data and the desired exposure data.

2. The method according to claim 1, characterized in that, Determine the image quality data for the current image, including: The texture distribution features obtained by feature extraction of the image to be processed are acquired; wherein the image to be processed includes the current image and the reference image; The image quality data of the current image is determined based on the difference between the texture distribution features of the current image and the texture distribution features of the reference image.

3. The method according to claim 2, characterized in that, The texture distribution features of the image to be processed are determined using the following method: Extract the target texture features of the image to be processed; Based on the multivariate Gaussian model, the distribution features of the target texture features of the image to be processed are extracted to obtain the texture distribution features of the image to be processed. The multivariate Gaussian model is obtained by fitting the target texture features extracted from at least one sample image.

4. The method according to claim 3, characterized in that, The extraction of target texture features from the image to be processed includes: Based on a generalized Gaussian distribution, the first texture feature of the image to be processed is extracted; and... Based on the asymmetric generalized Gaussian distribution, the second texture feature of the image to be processed is extracted in at least one pixel extension direction. The target texture features include the first texture feature and / or the second texture feature.

5. The method according to claim 4, characterized in that, The method further includes: The image to be processed is downsampled to obtain a derived image of the image to be processed; Based on the generalized Gaussian distribution, the third texture feature of the derived image is extracted; and, Based on the asymmetric generalized Gaussian distribution, the fourth texture feature of the derived image is extracted in at least one pixel extension direction; The target texture feature further includes the third texture feature and / or the fourth texture feature.

6. The method according to claim 3, characterized in that, The extraction of target texture features from the image to be processed includes: The image to be processed is divided into at least one candidate image block; For each candidate image block, the sharpness data of the candidate image block is determined based on the distribution of different pixel values ​​in the candidate image block; Based on the sharpness data of each candidate image block, a target image block is selected from the at least one candidate image block; Extract the target texture features of the target image block and use them as the target texture features of the image to be processed.

7. The method according to any one of claims 1-6, characterized in that, Determining the second exposure data of the current image based on the image quality data includes: Based on the target mapping function and the image quality data, the second exposure data of the current image is determined; The target mapping function is generated in the following manner: Determine the reference exposure data of the reference image acquired under the preset quality acquisition requirements, and the reference image quality of the reference image; The target mapping function is obtained by performing polynomial fitting based on reference exposure data and corresponding reference image quality from at least two reference images.

8. The method according to claim 7, characterized in that, The method further includes: Obtain the acquisition environment type of the current image; From at least one candidate mapping function, select the candidate mapping function corresponding to the acquisition environment type as the target mapping function; Among them, the acquisition environment type of the reference image is different when different candidate mapping functions are generated.

9. An exposure data adjustment device, characterized in that, include: The first determining module is used to determine the histogram data and image quality data of the current image; The second determining module is used to determine the first exposure data of the current image based on the histogram data; as well as, The third determining module is used to determine the second exposure data of the current image based on the image quality data; The data fusion module is used to fuse the first exposure data and the second exposure data to obtain the desired exposure data; The data adjustment module is used to adjust the first exposure data based on the difference between the first exposure data and the desired exposure data.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-8.

Images