Image processing methods, apparatus and computer-readable storage media

Abstract

This invention provides an image processing method, apparatus, and computer-readable storage medium. The image processing method according to the invention includes: acquiring an input image; dividing the input image into multiple regions; determining brightness information for different regions within the multiple regions of the input image; determining adjustment parameters for the brightness of a specific region based on the brightness information and brightness parameters of that specific region, wherein the specific region is one or more of the multiple regions, and the brightness parameters are associated with feature point detection parameters; and generating a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

Description

Technical Field

[0001] This invention relates to the field of image processing, and more particularly to an image processing method, apparatus, and computer-readable storage medium. Background Technology

[0002] Image matching methods in the field of image processing refer to the process of identifying corresponding points between two or more images using a specific matching algorithm. In implementing image matching methods, one or more feature points to be matched in each of the multiple images to be matched can be determined first by feature point identification. Then, image matching can be performed between the multiple images based on the determined feature points.

[0003] However, if the image to be matched has brightness issues when displayed, such as being too dark or overexposed, it is difficult to obtain enough feature points from the image to be matched, thus affecting the accuracy of feature point recognition and image matching.

[0004] Therefore, there is a need for an image processing method and apparatus that can effectively adjust image brightness and improve the accuracy of feature point recognition and image matching. Summary of the Invention

[0005] To address the aforementioned technical problems, according to one aspect of the present invention, an image processing method is provided, comprising: acquiring an input image; dividing the input image into multiple regions; determining brightness information of different regions within the multiple regions for different regions of the input image; determining an adjustment parameter for the brightness of a specific region based on the brightness information and brightness parameters of the specific region, wherein the specific region is one or more regions within the multiple regions, and the brightness parameters are associated with feature point detection parameters; and generating a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

[0006] According to another aspect of the present invention, an image processing apparatus is provided, comprising: an acquisition unit configured to acquire an input image; a segmentation unit configured to segment the input image into multiple regions; a determination unit configured to determine brightness information for different regions among the multiple regions of the input image; an adjustment unit configured to determine adjustment parameters for the brightness of a specific region based on the brightness information of the specific region and brightness parameters, wherein the specific region is one or more regions among the multiple regions, and the brightness parameters are associated with feature point detection parameters; and a generation unit configured to generate a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

[0007] According to another aspect of the present invention, an image processing apparatus is provided, comprising: a processor; and a memory storing computer program instructions, wherein, when the computer program instructions are executed by the processor, the processor performs the following steps: acquiring an input image; dividing the input image into multiple regions; determining brightness information for different regions among the multiple regions of the input image; determining an adjustment parameter for the brightness of a specific region based on the brightness information of the specific region and a brightness parameter, wherein the specific region is one or more regions among the multiple regions, and the brightness parameter is associated with a feature point detection parameter; and generating a brightness-corrected image based on the adjustment parameter, the brightness-corrected image being used for feature point matching.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, perform the following steps: acquiring an input image; dividing the input image into multiple regions; determining brightness information for different regions among the multiple regions of the input image; determining an adjustment parameter for the brightness of a specific region based on the brightness information and brightness parameters of the specific region, wherein the specific region is one or more regions among the multiple regions, and the brightness parameters are associated with feature point detection parameters; generating a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

[0009] According to the above-described image processing method, apparatus, and computer-readable storage medium of the present invention, the brightness of the input image can be adjusted and corrected in different regions based on brightness parameters related to feature point detection parameters, thereby improving the number and accuracy of feature point recognition for the input image and reducing feature point recognition errors.

[0010] Furthermore, according to the image processing method, apparatus, and computer-readable storage medium of the present invention, image matching processing can be performed after the above-described brightness correction processing on one or more input images, thereby reducing the mismatch rate between feature points and improving the accuracy of image matching. Attached Figure Description

[0011] The above and other objects, features, and advantages of the present invention will become clearer from the detailed description of the embodiments of the present invention in conjunction with the accompanying drawings.

[0012] Figure 1(a) shows an example of an input image under low brightness conditions according to an embodiment of the present invention; Figure 1(b) shows an example of an input image under high brightness conditions according to an embodiment of the present invention;

[0013] Figure 2The results of feature point recognition and image matching are shown between two input images, both of which are too dark.

[0014] Figure 3 A flowchart illustrating an image processing method according to an embodiment of the present invention is shown;

[0015] Figure 4 The results of clustering detected feature points in an input image according to an embodiment of the present invention are shown.

[0016] Figure 5 The result of merging various feature point groups of an input image according to an embodiment of the present invention is shown;

[0017] Figure 6 The results of feature point recognition and image matching between a left input image and a right image to be matched, both after brightness correction, are shown according to an embodiment of the present invention.

[0018] Figure 7 A block diagram of an image processing apparatus according to an embodiment of the present invention is shown;

[0019] Figure 8 A block diagram of an image processing apparatus according to another embodiment of the present invention is shown. Detailed Implementation

[0020] Image processing methods, apparatus, and computer-readable storage media according to embodiments of the present invention will now be described with reference to the accompanying drawings. In the drawings, the same reference numerals denote the same elements throughout. It should be understood that the embodiments described herein are merely illustrative and should not be construed as limiting the scope of the invention.

[0021] In image processing, if the acquired input image has brightness issues, it may be impossible to identify enough feature points, thus reducing the accuracy of image matching and affecting the user experience. Figure 1 shows examples of input images under different brightness levels. Figure 1(a) shows an example of an input image under excessively low brightness; Figure 1(b) shows an example of an input image under excessively high brightness. It is evident that in the examples of Figure 1(a) or Figure 1(b), it is difficult to obtain a sufficient number and accuracy of feature points through feature point detection, thereby affecting the accuracy of subsequent image matching between input images. For example, Figure 2 The results of feature point recognition and image matching are shown when both input images are too dark. Figure 2As shown, in low light conditions, the image matching process can only obtain a few pairs of matching feature points connected by line segments. Therefore, the small number of feature point pairs obtained will also affect the accuracy of the calculated motion matrix, such as the camera rotation and translation matrix, making it impossible to obtain accurate image matching results.

[0022] To improve the accuracy of feature point recognition and image matching, embodiments of the present invention provide an image processing method, apparatus, and computer-readable storage medium. The following will refer to... Figure 3 An image processing method according to an embodiment of the present invention is described. The image processing method of the present invention can be applied to static images as well as video frames in a video that changes over time, and is not limited thereto. Figure 3 A flowchart of the image processing method 300 is shown.

[0023] like Figure 3 As shown, in step S301, the input image is acquired.

[0024] In this step, the input image can be a two-dimensional image acquired using an image acquisition device such as a camera or video camera, or a two-dimensional frame image captured from a video.

[0025] In step S302, the input image is divided into multiple regions.

[0026] In this step, the input image can be divided into multiple regions in different ways. For example, the input image can be divided into multiple regions based on the pixels in each row or column; another example is that the input image can be divided into multiple regions based on blocks of a specific size; yet another example is that the input image can be divided into multiple regions based on individual pixels. The above methods of region division for the input image are merely examples. In practical applications, any method of region division for the input image can be used, and there are no restrictions here.

[0027] In step S303, brightness information of different regions is determined for each of the plurality of regions of the input image.

[0028] In this step, corresponding brightness information can be determined for different regions within the multiple regions of the input image divided in step S302. When the input image is a color image, it can first be converted into a grayscale image, and the brightness information for different regions can be obtained based on the converted grayscale image. Optionally, the brightness information can be the grayscale value of a certain region's grayscale image, such as the total grayscale value of each pixel in that region's grayscale image, or the average or weighted average grayscale value of each pixel in the grayscale image; no limitation is made here. Optionally, the brightness information can also be the grayscale level corresponding to the grayscale value of a certain region's grayscale image. For example, the grayscale values ​​of each region in the converted grayscale image of the input image can be statistically analyzed (e.g., the total grayscale value of all pixels in that region, or the average or weighted average grayscale value of each pixel, etc.), normalized, and divided into multiple grayscale levels, so that the brightness information of each region can correspond to a specific grayscale level. Specifically, the grayscale values ​​of the aforementioned regions can be divided into 10 grayscale levels, namely 0.1, 0.2, 0.3...1, and then the brightness information of each region can be represented as a value of one of these grayscale levels. In one example, the grayscale levels can be divided according to the average grayscale value of each pixel in a certain region. For example, the brightness information of a region with an average grayscale value of 225-255 can be represented as 1, the brightness information of a region with an average grayscale value of 200-225 can be represented as 0.9, and so on... the brightness information of a region with an average grayscale value of 0-25 can be represented as 0.1.

[0029] Optionally, the brightness information can also be obtained by statistically analyzing the grayscale values ​​of each pixel by row or column, plotting a curve representing the sum of the grayscale values ​​for each row or column, and then using curve fitting (such as polynomial fitting) to obtain the grayscale values ​​on the fitted curve as the brightness information corresponding to each row or column. Furthermore, the grayscale values ​​on the fitted curve can be further normalized to obtain grayscale level values, which can then be used as the brightness information corresponding to each row or column.

[0030] Of course, the above method of determining the corresponding brightness information based on different regions is only an example. In practical applications, any way of expressing brightness information for different regions can be used, and there are no restrictions here.

[0031] In step S304, the brightness adjustment parameters of the specific region are determined based on the brightness information and brightness parameters of the specific region, wherein the specific region is one or more of the plurality of regions, and the brightness parameters are associated with the feature point detection parameters.

[0032] In this step, the brightness parameter can be obtained in various ways and can include different content and parameter values. In one example, the brightness parameter may include a first grayscale value associated with the feature point detection parameter. Specifically, the first grayscale value in the brightness parameter can be obtained as follows: construct an image dataset including multiple first reference images; for each first reference image in the image dataset, obtain multiple second reference images at different grayscale values; for each first reference image, perform feature point detection on the multiple second reference images at different grayscale values ​​respectively; based on the feature point detection results of the multiple second reference images, determine the grayscale value that meets the conditions of the preset feature point detection parameter among the different grayscale values ​​as the first grayscale value in the brightness parameter.

[0033] In one example, each first reference image in the image dataset can be divided into multiple second reference images at different grayscale values. For instance, each first reference image can be divided into second reference images at grayscale values ​​of 0, 25, 50, 100, 125, 150, 175, 200, 225, and 255. Then, feature points in each of the second reference images at each grayscale value are detected separately, thereby statistically calculating the feature point detection results for each second reference image at each grayscale value.

[0034] Optionally, the feature point detection result corresponding to each second reference image at each grayscale value can be the sum or average number of feature points in all second reference images at that grayscale value. Accordingly, the grayscale value that maximizes the sum or average number of feature points in all second reference images can be used as the first grayscale value in the brightness parameter. For example, the first grayscale value can be 150.

[0035] Alternatively, the feature point detection result corresponding to each second reference image at each grayscale value can also be the sum of the number of feature points in certain specific objects in all second reference images at that grayscale value, or the average number of feature points in certain specific objects. Accordingly, the grayscale value that maximizes the sum of the number of feature points in certain specific objects in all second reference images, or the average number of feature points in certain specific objects, can be used as the first grayscale value in the brightness parameter. For example, the first grayscale value can be 175.

[0036] In another example, the brightness parameter may include a first grayscale value associated with the feature point detection parameter. Specifically, the first grayscale value in the brightness parameter can be obtained as follows: construct an image dataset including multiple first reference images; for each first reference image in the image dataset, obtain multiple second reference images at different grayscale levels; for each first reference image, perform feature point detection on the multiple second reference images at different grayscale levels respectively; based on the feature point detection results of the multiple second reference images, determine the grayscale level that meets the conditions of the preset feature point detection parameter as the first grayscale value in the brightness parameter.

[0037] Similar to the calculation of grayscale values ​​described above, each first reference image in the image dataset can be divided into multiple second reference images at different grayscale levels. For example, each first reference image can be divided into second reference images at grayscale levels of 0, 0.1, 0.2, ..., 1. Then, feature points in each of the second reference images at each grayscale level are detected separately, thereby statistically calculating the feature point detection results for each second reference image at each grayscale level.

[0038] Optionally, the feature point detection result corresponding to each second reference image at each gray level can be the sum or average number of feature points of all second reference images at that gray level. Accordingly, the value of the gray level that maximizes the sum or average number of feature points of all second reference images can be used as the value of the first gray level in the brightness parameters. For example, the value of the first gray level can be 0.6.

[0039] Alternatively, the feature point detection results for each second reference image at each grayscale level can also be the sum of the number of feature points in certain specific objects in all second reference images at that grayscale level, or the average number of feature points in certain specific objects. Accordingly, the grayscale level that maximizes the sum of the number of feature points in certain specific objects in all second reference images, or the average number of feature points in certain specific objects, can be used as the value of the first grayscale level in the brightness parameters. For example, the value of the first grayscale level can also be 0.7.

[0040] The above method for determining the first gray value or first gray level in the brightness parameter is only an example. In actual application, any statistical method for feature points of each second reference image in the image dataset can be used to obtain the first gray value or first gray level in the brightness parameter, and there are no restrictions here.

[0041] Optionally, in another example, the brightness parameter may further include adjustment parameters for determining the brightness of a specific region of the input image or its corresponding grayscale image. For example, if the grayscale value of the specific region is greater than the first grayscale value, a first adjustment parameter can be determined as the adjustment parameter; if the grayscale value of the specific region is less than the first grayscale value, a second adjustment parameter can be determined as the adjustment parameter. After determining the adjustment parameters to be used for each region, the brightness of the specific region can be adjusted according to the determined adjustment parameters. Specifically, after determining the first grayscale value, the corresponding regions can be adjusted using the first and second adjustment parameters in the brightness parameter. For example, when the first grayscale value is 150, and the grayscale value of the specific region is the average grayscale value of all pixels in that region, a first adjustment parameter σ1 can be determined as the adjustment parameter when the grayscale value of the specific region is greater than the first grayscale value; and a second adjustment parameter σ2 can be determined as the adjustment parameter when the grayscale value of the specific region is less than the first grayscale value.

[0042] Furthermore, in another example, if the grayscale value of the specific region is greater than the value of the first grayscale, a first adjustment parameter can be determined as the adjustment parameter; if the grayscale value of the specific region is less than the value of the first grayscale, a second adjustment parameter can be determined as the adjustment parameter. After determining the adjustment parameters to be used for each region, the brightness of the specific region can be adjusted according to the determined adjustment parameters. Specifically, after determining the value of the first grayscale, the corresponding regions can be adjusted using the first and second adjustment parameters in the brightness parameters respectively. For example, when the value of the first grayscale is N1 = 0.6, and the grayscale value of the specific region is the normalized grayscale value of each pixel in that region, the first adjustment parameter σ1 can be determined as the adjustment parameter when the grayscale value of the specific region (e.g., 0.7) is greater than the value of the first grayscale 0.6; and the second adjustment parameter σ2 can be determined as the adjustment parameter when the grayscale value of the specific region (e.g., 0.5) is less than the value of the first grayscale 0.6. Optionally, σ1 can be represented as (0.5-N1) / (lowestGrayLevel-N1); and σ2 can be represented as (0.7-N1) / (HighestGrayLevel-N1). Here, lowestGrayLevel can be the lowest gray level value across all regions of the entire input image, and highestGrayLevel can be the highest gray level value across all regions of the entire input image. During the adjustment process, the first adjustment parameter σ1 can be multiplied by the gray level value in its corresponding region, and the second adjustment parameter σ2 can be multiplied by the gray level value in its corresponding region. The adjusted gray level value is then restored to a gray value of 0-255 to obtain the adjusted brightness-corrected image. Furthermore, optionally, for regions where the first gray level value is equal to the first gray level value N1, brightness correction can be omitted, and their original gray level state can be preserved in the brightness-corrected image.

[0043] Of course, the above methods for adjusting the brightness parameters, including the first grayscale value / first grayscale level value, the second grayscale value / second grayscale level value, and the brightness of each region, are merely examples. In practical applications, any desired method for determining brightness parameters and adjusting region brightness can be used, and no limitation is made here. According to the brightness modification method described above in the embodiments of the present invention, the exposure state of the input image can be adjusted, and by increasing the brightness of underexposed areas and reducing the brightness of overexposed areas, the input image can display more image details, which is beneficial to the subsequent feature point detection and image matching processes.

[0044] In step S305, a brightness correction image is generated based on the adjustment parameters, and the brightness correction image is used for feature point matching.

[0045] In this step, a brightness correction image can be generated according to the adjustment parameters determined in step S304, and feature point detection can be performed on the generated brightness correction image to obtain at least one feature point; based on the obtained at least one feature point, feature point matching is performed with feature points in the image to be matched to obtain the image matching result.

[0046] Optionally, brightness correction can be applied only to the input image, while feature point detection and matching are performed separately for both the input image and the image to be matched without brightness correction. In this example, brightness correction of the input image yields more accurate feature point detection results, thus improving the accuracy of subsequent feature point matching.

[0047] Alternatively, while performing brightness correction on the input image in the embodiments of the present invention, a similar brightness correction process can also be performed on the image to be matched corresponding to the input image, so as to perform feature point detection and feature point matching on the input image and the brightness-corrected image to be matched respectively, so as to obtain a more accurate image matching result.

[0048] In one example, the results of image feature point detection can be further optimized to improve image matching quality. Optionally, the at least one feature point can be clustered to form at least one feature point group; the at least one feature point is then filtered based on the cluster center and cluster range of the clustered feature point group, and the filtered feature points are used for feature point matching. For example, based on the cluster center of each clustered feature point group, only feature points within a certain range around the cluster center can be retained for subsequent feature point matching. Figure 4 The following diagram illustrates the results of clustering detected feature points in an input image according to an embodiment of the present invention, such as... Figure 4 As shown, the detected feature points in the input image can be clustered into four groups of feature points indicated by boxes, and each group of feature points contains a cluster center and a cluster range covered by the box. Optionally, the cluster range can be... Figure 4 Feature points within a 0.5W1 range from the cluster center in each feature point group are retained for later feature point matching. Here, W1 can be the side length of the bounding box corresponding to that feature point group.

[0049] Furthermore, in one example, the at least one feature point can be clustered to form multiple feature point groups; the multiple feature point groups are merged according to their cluster centers and cluster ranges, and at least one feature point group is selected from the merged feature point groups for feature point matching. Optionally, in Figure 4Among the four feature point groups shown, feature point groups can be merged based on the cluster centers and cluster ranges of each feature point group. For example, two feature points whose cluster centers are less than 0.5W2 apart can be combined into one feature point group, where W2 can be the image width of the input image. Figure 5 The result of merging various feature point groups of an input image according to an embodiment of the present invention is shown. For example... Figure 5 As shown, it can be seen that Figure 4 The four feature point groups can be merged into two feature point groups for later feature point matching.

[0050] The filtering and merging operations for feature points / groups described above can be performed individually or simultaneously. When filtering and merging feature points / groups simultaneously, feature points can be filtered first, followed by merging feature point groups; alternatively, feature point groups can be merged first, followed by filtering feature points. There are no restrictions on this approach. Furthermore, the specific operational methods and parameter selections for filtering and merging feature points / groups are also not limited and can be modified according to the needs of the actual application. After completing the above filtering / merging operations, all obtained feature points can be used in the subsequent feature point matching process, or only the feature point group with the most feature points can be selected for the subsequent feature point matching process. There are no restrictions on this approach either.

[0051] Figure 6 The results of feature point recognition and image matching between the left input image and the right image to be matched, both after brightness correction, are shown. Figure 6 As shown, after brightness correction, the result can be the same as... Figure 2 Compared to the significantly increased number of matching feature point pairs connected by line segments, the accuracy of feature point detection and image matching results is significantly improved, the false matching rate is reduced, and the image matching effect is enhanced.

[0052] According to the above-described image processing method of the present invention, the brightness of the input image can be adjusted and corrected in different regions based on the brightness parameters related to the feature point detection parameters, thereby improving the number and accuracy of feature point recognition for the input image and reducing feature point recognition errors.

[0053] Furthermore, the image processing method according to embodiments of the present invention can perform image matching processing after performing the above-mentioned brightness correction processing on one or more input images, thereby reducing the mismatch rate between feature points and improving the accuracy of image matching.

[0054] Below, refer to Figure 7 The image processing apparatus according to embodiments of the present invention will be described. Figure 7A block diagram of an image processing apparatus 700 according to an embodiment of the present invention is shown. Figure 7 As shown, the image processing apparatus 700 includes an acquisition unit 710, a division unit 720, a determination unit 730, an adjustment unit 740, and a generation unit 750. Besides these units, the image processing apparatus 700 may also include other components; however, since these components are not relevant to the content of this embodiment, their illustrations and descriptions are omitted here. Furthermore, since the specific details of the operations performed by the image processing apparatus 700 according to this embodiment are the same as those referred to above... Figure 3 The details described are the same, so repeated descriptions of the same details are omitted here to avoid repetition.

[0055] Figure 7 The image processing apparatus 700 in the image processing apparatus 700 is configured to acquire an input image.

[0056] Specifically, the input image acquired by the acquisition unit 710 can be a two-dimensional image acquired using an image acquisition device such as a camera or video camera, or a two-dimensional frame image captured from a video.

[0057] The segmentation unit 720 is configured to divide the input image into multiple regions.

[0058] Optionally, the segmentation unit 720 can divide the input image into multiple regions in different ways. For example, the input image can be divided into multiple regions based on the pixels in each row or column; another example is that the input image can be divided into multiple regions based on blocks of a specific size; yet another example is that the input image can be divided into multiple regions based on pixels. The above methods of region segmentation for the input image are merely examples. In practical applications, any method of region segmentation for the input image can be used, and there are no restrictions here.

[0059] The determining unit 730 is configured to determine the brightness information of different regions among the plurality of regions of the input image.

[0060] The determining unit 730 can determine corresponding brightness information for different regions within the multiple regions of the input image divided by the dividing unit 720. When the input image is a color image, the determining unit 730 can first convert the color input image into a grayscale image and obtain the brightness information for different regions based on the converted grayscale image. Optionally, the brightness information can be the grayscale value of a certain region's grayscale image, such as the total grayscale value of each pixel in the grayscale image of that region, or the average grayscale value or weighted average grayscale value of each pixel in the grayscale image, without limitation. Optionally, the brightness information can also be the grayscale level corresponding to the grayscale value of a certain region's grayscale image. For example, the grayscale values ​​of each region in the converted grayscale image of the input image can be statistically analyzed (e.g., the total grayscale value of all pixels in that region, or the average grayscale value, weighted average grayscale value, etc. for each pixel), normalized, and divided into multiple grayscale levels, so that the brightness information of each region can correspond to a specific grayscale level. Specifically, the grayscale values ​​of the aforementioned regions can be divided into 10 grayscale levels, namely 0.1, 0.2, 0.3...1, and then the brightness information of each region can be represented as a value of one of these grayscale levels. In one example, the grayscale levels can be divided according to the average grayscale value of each pixel in a certain region. For example, the brightness information of a region with an average grayscale value of 225-255 can be represented as 1, the brightness information of a region with an average grayscale value of 200-225 can be represented as 0.9, and so on... the brightness information of a region with an average grayscale value of 0-25 can be represented as 0.1.

[0061] Optionally, the brightness information can also be obtained by statistically analyzing the grayscale values ​​of each pixel by row or column, plotting a curve representing the sum of the grayscale values ​​for each row or column, and then using curve fitting (such as polynomial fitting) to obtain the grayscale values ​​on the fitted curve as the brightness information corresponding to each row or column. Furthermore, the grayscale values ​​on the fitted curve can be further normalized to obtain grayscale level values, which can then be used as the brightness information corresponding to each row or column.

[0062] Of course, the above method of determining the corresponding brightness information based on different regions is only an example. In practical applications, any way of expressing brightness information for different regions can be used, and there are no restrictions here.

[0063] The adjustment unit 740 is configured to determine the adjustment parameters of the brightness of the specific region based on the brightness information and brightness parameters of the specific region, wherein the specific region is one or more of the plurality of regions, and the brightness parameters are associated with feature point detection parameters.

[0064] Optionally, the brightness parameter can be obtained in various ways and can include different content and parameter values. In one example, the brightness parameter may include a first grayscale value associated with the feature point detection parameter. Specifically, the first grayscale value in the brightness parameter can be obtained as follows: construct an image dataset including multiple first reference images; for each first reference image in the image dataset, obtain multiple second reference images at different grayscale values; for each first reference image, perform feature point detection on the multiple second reference images at different grayscale values ​​respectively; based on the feature point detection results of the multiple second reference images, determine the grayscale value that meets the conditions of the preset feature point detection parameter as the first grayscale value in the brightness parameter.

[0065] In one example, the adjustment unit 740 can divide each first reference image in the image dataset into multiple second reference images at multiple different grayscale values. For example, each first reference image can be divided into second reference images at grayscale values ​​of 0, 25, 50, 100, 125, 150, 175, 200, 225, and 255. Then, feature points in each of the second reference images at each of the above grayscale values ​​are detected separately, thereby statistically calculating the feature point detection results corresponding to each of the second reference images at each grayscale value.

[0066] Optionally, the feature point detection result corresponding to each second reference image under each gray value counted by the adjustment unit 740 can be the sum or average number of feature points of all second reference images under that gray value. Accordingly, the gray value that maximizes the sum or average number of feature points of all second reference images can be used as the first gray value in the brightness parameter. For example, the first gray value can be 150.

[0067] Alternatively, the feature point detection result corresponding to each second reference image at each gray value calculated by the adjustment unit 740 can also be the sum of the number of feature points in certain specific objects in all second reference images at that gray value, or the average number of feature points in certain specific objects. Accordingly, the gray value that maximizes the sum of the number of feature points in certain specific objects in all second reference images, or the average number of feature points in certain specific objects, can be used as the first gray value in the brightness parameter. For example, the first gray value can be 175.

[0068] In another example, the brightness parameter may include a first grayscale value associated with the feature point detection parameter. Specifically, the first grayscale value in the brightness parameter can be obtained as follows: construct an image dataset including multiple first reference images; for each first reference image in the image dataset, obtain multiple second reference images at different grayscale levels; for each first reference image, perform feature point detection on the multiple second reference images at different grayscale levels respectively; based on the feature point detection results of the multiple second reference images, determine the grayscale level that meets the conditions of the preset feature point detection parameter as the first grayscale value in the brightness parameter.

[0069] Similar to the calculation of grayscale values ​​described above, the adjustment unit 740 can divide each first reference image in the image dataset into multiple second reference images at multiple different grayscale levels. For example, each first reference image can be divided into second reference images at grayscale levels of 0, 0.1, 0.2...1. Then, feature points in each of the second reference images at each grayscale level are detected separately, thereby statistically calculating the feature point detection results corresponding to each of the second reference images at each grayscale level.

[0070] Optionally, the feature point detection results corresponding to each second reference image at each gray level, as calculated by the adjustment unit 740, can be the sum or average number of feature points of all second reference images at that gray level. Accordingly, the value of the gray level that maximizes the sum or average number of feature points of all second reference images can be used as the value of the first gray level in the brightness parameters. For example, the value of the first gray level can be 0.6.

[0071] Alternatively, the feature point detection results corresponding to each second reference image at each gray level, as calculated by the adjustment unit 740, can also be the sum of the number of feature points in certain specific objects in all second reference images at that gray level, or the average number of feature points in certain specific objects. Accordingly, the value of the gray level that maximizes the sum of the number of feature points in certain specific objects in all second reference images, or the average number of feature points in certain specific objects, can be used as the value of the first gray level in the brightness parameters. For example, the value of the first gray level can also be 0.7.

[0072] The above method for determining the first gray value or first gray level in the brightness parameter is only an example. In actual application, any statistical method for feature points of each second reference image in the image dataset can be used to obtain the first gray value or first gray level in the brightness parameter, and there are no restrictions here.

[0073] Optionally, in another example, the brightness parameter may further include adjustment parameters for determining the brightness of a specific region of the input image or its corresponding grayscale image. For example, if the grayscale value of the specific region is greater than the first grayscale value, a first adjustment parameter can be determined as the adjustment parameter; if the grayscale value of the specific region is less than the first grayscale value, a second adjustment parameter can be determined as the adjustment parameter. After determining the adjustment parameters to be used for each region, the brightness of the specific region can be adjusted according to the determined adjustment parameters. Specifically, after determining the first grayscale value, the corresponding regions can be adjusted using the first and second adjustment parameters in the brightness parameter. For example, when the first grayscale value is 150, and the grayscale value of the specific region is the average grayscale value of all pixels in that region, a first adjustment parameter σ1 can be determined as the adjustment parameter when the grayscale value of the specific region is greater than the first grayscale value; and a second adjustment parameter σ2 can be determined as the adjustment parameter when the grayscale value of the specific region is less than the first grayscale value.

[0074] Furthermore, in another example, if the grayscale value of the specific region is greater than the value of the first grayscale, a first adjustment parameter can be determined as the adjustment parameter; if the grayscale value of the specific region is less than the value of the first grayscale, a second adjustment parameter can be determined as the adjustment parameter. After determining the adjustment parameters to be used for each region, the brightness of the specific region can be adjusted according to the determined adjustment parameters. Specifically, after determining the value of the first grayscale, the corresponding regions can be adjusted using the first and second adjustment parameters in the brightness parameters respectively. For example, when the value of the first grayscale is N1 = 0.6, and the grayscale value of the specific region is the normalized grayscale value of each pixel in that region, the first adjustment parameter σ1 can be determined as the adjustment parameter when the grayscale value of the specific region (e.g., 0.7) is greater than the value of the first grayscale 0.6; and the second adjustment parameter σ2 can be determined as the adjustment parameter when the grayscale value of the specific region (e.g., 0.5) is less than the value of the first grayscale 0.6. Optionally, σ1 can be represented as (0.5-N1) / (lowestGrayLevel-N1); and σ2 can be represented as (0.7-N1) / (HighestGrayLevel-N1). Here, lowestGrayLevel can be the lowest gray level value across all regions of the entire input image, and highestGrayLevel can be the highest gray level value across all regions of the entire input image. During the adjustment process, the first adjustment parameter σ1 can be multiplied by the gray level value in its corresponding region, and the second adjustment parameter σ2 can be multiplied by the gray level value in its corresponding region. The adjusted gray level value is then restored to a gray value of 0-255 to obtain the adjusted brightness-corrected image. Furthermore, optionally, for regions where the first gray level value is equal to the first gray level value N1, brightness correction can be omitted, and their original gray level state can be preserved in the brightness-corrected image.

[0075] Of course, the above methods for adjusting the brightness parameters, including the first grayscale value / first grayscale level value, the second grayscale value / second grayscale level value, and the brightness of each region, are merely examples. In practical applications, any desired method for determining brightness parameters and adjusting region brightness can be used, and no limitation is made here. According to the brightness modification method described above in the embodiments of the present invention, the exposure state of the input image can be adjusted, and by increasing the brightness of underexposed areas and reducing the brightness of overexposed areas, the input image can display more image details, which is beneficial to the subsequent feature point detection and image matching processes.

[0076] The generation unit 750 is configured to generate a brightness-corrected image based on adjusted parameters, the brightness-corrected image being used for feature point matching.

[0077] The generation unit 750 can generate a brightness correction image according to the adjustment parameters determined by the adjustment unit 740, and perform feature point detection based on the generated brightness correction image to obtain at least one feature point; based on the obtained at least one feature point, feature point matching is performed with feature points in the image to be matched to obtain an image matching result.

[0078] Optionally, the generation unit 750 may perform brightness correction only on the input image, while performing feature point detection and feature point matching separately on the image to be matched without brightness correction. In this example, brightness correction on the input image yields more accurate feature point detection results, thereby improving the accuracy of subsequent feature point matching.

[0079] Alternatively, the generation unit 750 may perform a similar brightness correction process on the input image in the embodiment of the present invention while performing brightness correction on the image to be matched corresponding to the input image, thereby performing feature point detection and feature point matching on the input image and the brightness-corrected image to be matched respectively, so as to obtain a more accurate image matching result.

[0080] In one example, the generation unit 750 can further optimize the results of image feature point detection to further improve image matching quality. Optionally, the at least one feature point can be clustered to form at least one feature point group; the at least one feature point is then filtered based on the cluster center and cluster range of the clustered feature point group, and the filtered feature points are used for feature point matching. For example, based on the cluster center of each clustered feature point group, only feature points within a certain range around the cluster center can be retained for subsequent feature point matching. Figure 4 The following diagram illustrates the results of clustering detected feature points in an input image according to an embodiment of the present invention, such as... Figure 4 As shown, the detected feature points in the input image can be clustered into four groups of feature points indicated by boxes, and each group of feature points contains a cluster center and a cluster range covered by the box. Optionally, the cluster range can be... Figure 4 Feature points within a 0.5W1 range from the cluster center in each feature point group are retained for later feature point matching. Here, W1 can be the side length of the bounding box corresponding to that feature point group.

[0081] Furthermore, in one example, the generation unit 750 can also cluster the at least one feature point to form multiple feature point groups; merge the multiple feature point groups according to the cluster centers and cluster ranges of the clustered feature point groups, and select at least one feature point group from the merged feature point groups for feature point matching. Optionally, in Figure 4Among the four feature point groups shown, feature point groups can be merged based on the cluster centers and cluster ranges of each feature point group. For example, two feature points whose cluster centers are less than 0.5W2 apart can be combined into one feature point group, where W2 can be the image width of the input image. Figure 5 The result of merging various feature point groups of an input image according to an embodiment of the present invention is shown. For example... Figure 5 As shown, it can be seen that Figure 4 The four feature point groups can be merged into two feature point groups for later feature point matching.

[0082] The filtering and merging operations for feature points / groups described above can be performed individually or simultaneously. When filtering and merging feature points / groups simultaneously, feature points can be filtered first, followed by merging feature point groups; alternatively, feature point groups can be merged first, followed by filtering feature points. There are no restrictions on this approach. Furthermore, the specific operational methods and parameter selections for filtering and merging feature points / groups are also not limited and can be modified according to the needs of the actual application. After completing the above filtering / merging operations, all obtained feature points can be used in the subsequent feature point matching process, or only the feature point group with the most feature points can be selected for the subsequent feature point matching process. There are no restrictions on this approach either.

[0083] Figure 6 The results of feature point recognition and image matching between the left input image and the right image to be matched, both after brightness correction, are shown. Figure 6 As shown, after brightness correction, the result can be the same as... Figure 2 Compared to the significantly increased number of matching feature point pairs connected by line segments, the accuracy of feature point detection and image matching results is significantly improved, the false matching rate is reduced, and the image matching effect is enhanced.

[0084] According to the above-described image processing apparatus of the present invention, the brightness of the input image can be adjusted and corrected by region based on the brightness parameters related to the feature point detection parameters, thereby improving the number and accuracy of feature point recognition for the input image and reducing feature point recognition errors.

[0085] Furthermore, the image processing apparatus according to embodiments of the present invention can perform image matching processing after performing the above-described brightness correction processing on one or more input images, thereby reducing the mismatch rate between feature points and improving the accuracy of image matching.

[0086] Below, refer to Figure 8 The image processing apparatus according to embodiments of the present invention will be described. Figure 8A block diagram of an image processing apparatus 800 according to an embodiment of the present invention is shown. Figure 8 As shown, the device 800 can be a computer or a server.

[0087] like Figure 8 As shown, the image processing apparatus 800 includes one or more processors 810 and a memory 820. In addition, the image processing apparatus 800 may also include input devices, output devices (not shown), etc., and these components can be interconnected via a bus system and / or other forms of connection mechanisms. It should be noted that... Figure 8 The components and structures of the image processing apparatus 800 shown are merely exemplary and not limiting; the image processing apparatus 800 may also have other components and structures as needed.

[0088] The processor 810 may be a central processing unit (CPU) or other processing unit with data processing and / or instruction execution capabilities, and may utilize computer program instructions stored in the memory 820 to perform desired functions, including: acquiring an input image; dividing the input image into multiple regions; determining brightness information for different regions within the multiple regions of the input image; determining adjustment parameters for the brightness of a specific region based on the brightness information and brightness parameters of that specific region, wherein the specific region is one or more of the multiple regions, and the brightness parameters are associated with feature point detection parameters; and generating a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

[0089] The memory 820 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 810 may execute the program instructions to implement the functions of the image processing apparatus of the embodiments of the present invention described above, and / or other desired functions, and / or to execute the image processing method according to the embodiments of the present invention. Various application programs and various data may also be stored in the computer-readable storage medium.

[0090] The following describes a computer-readable storage medium according to embodiments of the present invention, having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, perform the following steps: acquiring an input image; dividing the input image into multiple regions; determining brightness information for different regions within the multiple regions of the input image; determining an adjustment parameter for the brightness of a specific region based on the brightness information and brightness parameters of that specific region, wherein the specific region is one or more regions within the multiple regions, and the brightness parameters are associated with feature point detection parameters; generating a brightness-corrected image based on the adjustment parameters, the brightness-corrected image being used for feature point matching.

[0091] Of course, the specific embodiments described above are merely examples and not limitations. Those skilled in the art can combine and integrate some steps and devices from the various embodiments described separately above to achieve the effects of the present invention. Such combined and integrated embodiments are also included in the present invention, but will not be described one by one here.

[0092] Note that the advantages, benefits, and effects mentioned in this invention are merely examples and not limitations, and should not be considered as essential features of every embodiment of the invention. Furthermore, the specific details described above are for illustrative and illustrative purposes only, and are not intended to limit the invention. These details do not limit the invention from being implemented solely by employing these specific details.

[0093] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0094] The flowcharts and method descriptions in this invention are merely illustrative examples and are not intended to require or imply that the steps of the various embodiments must be performed in the given order. As those skilled in the art will recognize, the steps in the above embodiments can be performed in any order. Words such as "then," "next," etc., are not intended to limit the order of steps; these words are only used to guide the reader through the description of these methods. Furthermore, any reference to a singular element, such as the use of the articles "a," "one," or "the," is not to be construed as limiting that element to the singular.

[0095] Furthermore, the steps and apparatus in the various embodiments herein are not limited to any one embodiment. In fact, new embodiments can be conceived by combining relevant steps and apparatus in the various embodiments herein with the concepts of the present invention, and these new embodiments are also included within the scope of the present invention.

[0096] Each operation described above can be performed by any suitable means capable of performing the corresponding function. Such means may include various hardware and / or software components and / or modules, including but not limited to circuits, application-specific integrated circuits (ASICs), or processors.

[0097] The various exemplified logic blocks, modules, and circuits described herein can be implemented or performed using a general-purpose processor, digital signal processor (DSP), ASIC, field-programmable gate array (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but alternatively, it may be any commercially available processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0098] The steps of the methods or algorithms described in this invention can be directly embedded in hardware, in a software module executed by a processor, or a combination of both. The software module can reside in any form of tangible storage medium. Some examples of usable storage media include random access memory (RAM), read-only memory (ROM), flash memory, EPROM, EEPROM, registers, hard disks, removable disks, CD-ROMs, etc. The storage medium can be coupled to the processor so that the processor can read information from and write information to the storage medium. Alternatively, the storage medium can be integral with the processor. The software module can be a single instruction or many instructions, and can be distributed across several different code segments, different programs, and across multiple storage media.

[0099] The method of this invention includes one or more actions for implementing the method. The methods and / or actions may be interchanged without departing from the scope of the claims. In other words, unless a specific order of actions is specified, the order and / or use of specific actions may be modified without departing from the scope of the claims.

[0100] The described functionality can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality can be stored as one or more instructions on a tangible computer-readable medium. The storage medium can be any available tangible medium that can be accessed by a computer. By way of example, and not limitation, such a computer-readable medium can include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other tangible medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. As used herein, a disc includes a compact disc (CD), a laser disc, an optical disc, a digital universal disc (DVD), a floppy disk, and a Blu-ray disc.

[0101] Therefore, a computer program product can perform the operations described herein. For example, such a computer program product can be a computer-readable tangible medium having instructions tangibly stored (and / or encoded) thereon, which can be executed by one or more processors to perform the operations described herein. The computer program product may include packaging materials.

[0102] Software or instructions can also be transmitted via a transmission medium. For example, software can be transmitted from a website, server, or other remote source using transmission media such as coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, or microwave.

[0103] Furthermore, modules and / or other suitable means for carrying out the methods and techniques described herein can be downloaded and / or obtained by user terminals and / or base stations as appropriate. For example, such a device can be coupled to a server to facilitate the transmission of means for carrying out the methods described herein. Alternatively, the various methods described herein can be provided via storage components (e.g., RAM, ROM, physical storage media such as CDs or floppy disks) so that user terminals and / or base stations can obtain the various methods when coupled to the device or when providing storage components to the device. Furthermore, any other suitable techniques for providing the methods and techniques described herein to the device can be utilized.

[0104] Other examples and implementations are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Features implementing the functions can also be physically located in various places, including being distributed so that parts of the functions are implemented at different physical locations. Moreover, as used herein, including as used in the claims, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the described examples are preferred or better than other examples.

[0105] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims is not limited to the specific aspects of the processes, machines, manufacturing processes, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufacturing processes, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufacturing processes, events, means, methods, or actions within their scope.

[0106] The above description of aspects of the invention is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features of the invention herein.

[0107] The above description has been given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of the invention to the forms described herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for image processing, comprising: obtaining an input image; dividing the input image into a plurality of regions; determining luminance information of different regions of the plurality of regions of the input image respectively; determining an adjustment parameter of luminance of a specific region based on the luminance information of the specific region and a luminance parameter, wherein the specific region is one or more regions of the plurality of regions, and the luminance parameter comprises a first parameter value associated with a feature point detection parameter; generating a luminance correction image based on the adjustment parameter, wherein the luminance correction image is used for feature point matching; and obtaining the first parameter value comprises: constructing an image data set comprising a plurality of first reference images; obtaining a plurality of second reference images under different parameter values for each first reference image in the image data set; performing feature point detection on the plurality of second reference images under the different parameter values respectively for each first reference image; and determining a parameter value that meets a preset condition of a feature point detection parameter from the different parameter values as the first parameter value according to the feature point detection results of the plurality of second reference images. The first parameter value is a first gray value, and determining the luminance information of different regions of the plurality of regions of the input image respectively comprises: obtaining a gray image according to the input image; and obtaining a gray value of a different region of the gray image as the luminance information of the different region. The obtaining of the first parameter value comprises: obtaining a plurality of second reference images under different gray values for each first reference image in the image data set; performing feature point detection on the plurality of second reference images under the different gray values respectively for each first reference image; and determining a gray value that meets a preset condition of a feature point detection parameter from the different gray values as the first gray value in the luminance parameter according to the feature point detection results of the plurality of second reference images. The determination of the adjustment parameter of luminance of the specific region based on the luminance information of the specific region and the luminance parameter comprises: if the gray value of the specific region is greater than the first gray value, determining a first adjustment parameter as the adjustment parameter; if the gray value of the specific region is less than the first gray value, determining a second adjustment parameter as the adjustment parameter; and adjusting the luminance of the specific region according to the determined adjustment parameter. 5.The method of claim 1, further comprising: performing feature point detection according to the generated luminance correction image to obtain at least one feature point; and performing feature point matching with feature points in a to-be-matched image according to the obtained at least one feature point to obtain an image matching result. The performing of feature point matching with feature points in a to-be-matched image according to the obtained at least one feature point comprises: clustering the at least one feature point to form at least one feature point group; and screening the at least one feature point according to a cluster center and a cluster range of the at least one feature point group after clustering, and using the screened feature points for feature point matching. ​ ​ ​ ​ ​ ​ 2. The method of claim 1, wherein, ​ ​ ​ 3. The method of claim 2, wherein, ​ ​ ​ ​ 4. The method of claim 3, wherein, ​ ​ ​ ​ ​ ​ ​ 6. The method of claim 5, wherein, ​ ​ ​ 7. The method of claim 5, wherein, According to the obtained at least one feature point, the feature point matching with feature points in a to-be-matched image comprises: clustering the at least one feature point to form a plurality of feature point groups; merging the plurality of feature point groups according to cluster centers and cluster ranges of the plurality of feature point groups, and selecting at least one feature point group from the feature point groups obtained after the merging for feature point matching. 8.An image processing apparatus, comprising: an acquisition unit configured to acquire an input image; a division unit configured to divide the input image into a plurality of regions; a determination unit configured to determine luminance information of different regions among the plurality of regions of the input image respectively for the different regions; an adjustment unit configured to determine an adjustment parameter of luminance of a specific region based on the luminance information of the specific region and a luminance parameter, wherein the specific region is one or more regions among the plurality of regions, and the luminance parameter comprises a first parameter value associated with a feature point detection parameter; a generation unit configured to generate a luminance correction image based on the adjustment parameter, wherein the luminance correction image is used for feature point matching; and in order to acquire the first parameter value, the adjustment unit is further configured to: construct an image data set comprising a plurality of first reference images; for each first reference image in the image data set, acquire a plurality of second reference images under different parameter values; for each first reference image, perform feature point detection on the plurality of second reference images under the different parameter values respectively; determine, according to the plurality of second reference image feature point detection results, a parameter value in the different parameter values that meets a preset feature point detection parameter condition as the first parameter value. 9.An image processing apparatus, comprising: a processor; and a memory having computer program instructions stored therein, wherein when the computer program instructions are run by the processor, the image processing apparatus performs the following steps: acquiring an input image; dividing the input image into a plurality of regions; determining luminance information of different regions among the plurality of regions of the input image respectively for the different regions; determining an adjustment parameter of luminance of a specific region based on the luminance information of the specific region and a luminance parameter, wherein the specific region is one or more regions among the plurality of regions, and the luminance parameter comprises a first parameter value associated with a feature point detection parameter; generating a luminance correction image based on the adjustment parameter, wherein the luminance correction image is used for feature point matching; and in order to acquire the first parameter value, when the computer program instructions are run by the processor, the image processing apparatus further performs the following steps: constructing an image data set comprising a plurality of first reference images; for each first reference image in the image data set, acquiring a plurality of second reference images under different parameter values; for each first reference image, performing feature point detection on the plurality of second reference images under the different parameter values respectively; determining, according to the plurality of second reference image feature point detection results, a parameter value in the different parameter values that meets a preset feature point detection parameter condition as the first parameter value. According to the multiple second reference image feature point detection results, a parameter value of the different parameter values that meets a preset condition of a feature point detection parameter is determined as the first parameter value.

10. A computer readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions, when executed by a processor, implement the following steps: obtaining an input image; dividing the input image into multiple regions; determining luminance information of different regions of the multiple regions of the input image respectively; determining an adjustment parameter of luminance of a specific region based on the luminance information of the specific region and a luminance parameter, wherein the specific region is one or more regions of the multiple regions, and the luminance parameter comprises a first parameter value associated with a feature point detection parameter; generating a luminance correction image based on the adjustment parameter, wherein the luminance correction image is used for feature point matching; and In order to obtain the first parameter value, the computer program instructions, when executed by a processor, further implement the following steps: constructing an image data set comprising multiple first reference images; for each first reference image in the image data set, obtaining multiple second reference images under different parameter values; for each first reference image, performing feature point detection on the multiple second reference images under the different parameter values respectively; According to the multiple second reference image feature point detection results, a parameter value of the different parameter values that meets a preset condition of a feature point detection parameter is determined as the first parameter value.

Images