Brightness Equalization Adjustment Method, Device, Equipment and Storage Medium

Abstract

The present invention provides a brightness equalization adjustment method, device, equipment and storage medium, including: obtaining each overlapping area in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images of each camera; determining multiple brightness reference areas of each initial image based on each overlapping area; forming an area to be adjusted for each initial image according to the multiple brightness reference areas of each initial image; calculating the brightness gain of each camera according to the reference brightness values of the multiple brightness reference areas; and adjusting the brightness values of each area to be adjusted respectively according to the brightness gain of each camera to obtain a brightness adjustment result. By determining the brightness reference area and setting the area to be adjusted for the initial image, the present invention calculates the brightness gain of each camera based on the brightness value of the brightness reference area, and adjusts the brightness of the area to be adjusted based on the brightness gain, so that the brightness of the subsequent stitched display image is consistent, and the image stitching and fusion effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular, to a method, device, equipment and storage medium for adjusting brightness balance. Background Art

[0002] With the development of automotive technology, people's requirements for the convenience and safety of vehicle use are constantly increasing. Especially when parking or passing through narrow roads, environmental information around the vehicle is often required as a reference. The panoramic surround view system can provide a concise surround view image of the vehicle, enabling the driver to view the information around the vehicle from different perspectives inside the vehicle, which not only enhances the safety of the vehicle but also improves the driving experience of the driver.

[0003] Common panoramic surround view systems generally use four fisheye cameras installed at the front and rear of the vehicle body to obtain image information around the vehicle, and obtain corresponding four bird's-eye view images through fisheye image undistortion and perspective transformation. Finally, the four bird's-eye view images are stitched according to certain rules to obtain a surround view image. However, in the panoramic surround view system, since the input images come from different cameras and the internal parameters and the environments of each camera are different, there are differences in the brightness of the images collected by the four cameras, and obvious stitching boundaries will be formed during the stitching of the bird's-eye view images, greatly reducing the quality of the surround view image. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for adjusting brightness balance, aiming to solve the technical problem that due to the differences in the internal parameters and the environments of each camera, obvious stitching boundaries will be formed during image stitching, resulting in poor display effects of the stitched surround view image.

[0005] The present invention provides a method for adjusting brightness balance, including:

[0006] Obtaining each overlapping area in the surround view stitched image, where the surround view stitched image is formed by transforming the initial images collected by each camera at the same moment;

[0007] Based on each of the overlapping areas, determining a plurality of brightness reference areas in each of the initial images;

[0008] According to the plurality of brightness reference areas in each of the initial images, forming a region to be adjusted for each of the initial images;

[0009] Calculating the brightness gain of each camera according to the reference brightness values of the plurality of brightness reference areas in each of the initial images;

[0010] Adjusting the brightness values of each of the regions to be adjusted respectively according to the brightness gain of each camera to obtain a brightness adjustment result.

[0011] Optionally, according to a brightness balance adjustment method provided by the present invention, determining a plurality of brightness reference regions in each of the initial images based on each of the overlapping regions includes:

[0012] Performing pixel sampling on each of the overlapping regions to obtain a plurality of pixel sampling points within each of the overlapping regions;

[0013] Mapping the plurality of pixel sampling points within each of the overlapping regions to the corresponding initial images of each of the cameras to form a plurality of brightness reference regions in each of the initial images.

[0014] Optionally, according to a brightness balance adjustment method provided by the present invention, calculating the brightness gain of each camera based on the reference brightness values of the plurality of brightness reference regions in each of the initial images includes:

[0015] Based on the brightness values of each pixel sampling point in each of the brightness reference regions, respectively calculating the reference brightness value corresponding to each of the brightness reference regions;

[0016] Calculating a brightness average value according to the reference brightness values of each of the brightness reference regions;

[0017] Selecting a target standard region in each of the brightness reference regions based on the reference brightness values of each of the brightness reference regions and the brightness average value;

[0018] According to the reference brightness values of each of the brightness reference regions, respectively calculating the brightness difference corresponding to the brightness reference regions of adjacent cameras in each camera, and calculating the average brightness difference corresponding to each of the brightness differences;

[0019] Taking the target standard region as a reference, calculating the brightness gain of each of the cameras according to the average brightness difference and the brightness difference corresponding to the adjacent cameras.

[0020] Optionally, according to a brightness balance adjustment method provided by the present invention, selecting a target standard region in each of the brightness reference regions based on the reference brightness value corresponding to each of the brightness reference regions and the brightness average value includes:

[0021] Adding the reference brightness values corresponding to the plurality of brightness reference regions in any one of the initial images to obtain the added brightness value of the any one of the initial images;

[0022] Calculating the difference between the added brightness value of the any one of the initial images and the brightness average value, and taking the brightness reference region with the smallest difference as the target standard region of the any one of the initial images.

[0023] Optionally, according to a brightness balance adjustment method provided by the present invention, taking the target standard area as a reference, and calculating the brightness gains of each camera according to the average brightness difference and the brightness differences corresponding to adjacent cameras, includes:

[0024] Set the brightness gain corresponding to the camera to which the target standard area belongs to zero, and calculate the brightness gains of each target camera according to the average brightness difference and the brightness differences corresponding to adjacent cameras, where each of the target cameras is each camera except the camera to which the target standard area belongs.

[0025] Optionally, according to a brightness balance adjustment method provided by the present invention, forming the area to be adjusted for each of the initial images according to a plurality of brightness reference areas in each of the initial images, includes:

[0026] For any one of the initial images: Based on a plurality of brightness reference areas of the initial image, calculate an outer envelope box area including the plurality of brightness reference areas;

[0027] Extend the matrix area downward until it is flush with the lower edge of the initial image to form the area to be adjusted for each of the initial images.

[0028] Optionally, according to a brightness balance adjustment method provided by the present invention, adjusting the brightness values of each of the areas to be adjusted according to the brightness gains of each camera to obtain a brightness adjustment result, includes:

[0029] Perform pixel superposition processing on the brightness gains of each camera and the brightness values of the areas to be adjusted corresponding to each camera respectively to obtain the brightness adjustment result.

[0030] The present invention also provides a brightness balance adjustment device, including:

[0031] An acquisition module, configured to acquire each overlapping area in the panoramic stitching image, where the panoramic stitching image is formed by transforming initial images collected by each camera at the same moment;

[0032] A determination module, configured to determine a plurality of brightness reference areas in each initial image based on each of the overlapping areas;

[0033] A formation module, configured to form the area to be adjusted for each of the initial images according to a plurality of brightness reference areas in each of the initial images;

[0034] A calculation module, configured to calculate the brightness gains of each camera according to the reference brightness values of a plurality of brightness reference areas in each of the initial images;

[0035] The adjustment module is used to adjust the brightness value of each of the to-be-adjusted areas according to the brightness gain of each of the cameras to obtain a brightness adjustment result.

[0036] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned brightness balance adjustment methods is implemented.

[0037] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the brightness balance adjustment method described in any one of the above is implemented.

[0038] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the brightness balance adjustment method described above is implemented.

[0039] The brightness balance adjustment method, device, equipment and storage medium provided by the present invention determine multiple brightness reference areas in the initial images of each camera by looking at the overlapping areas between adjacent cameras in the stitched image, so as to calculate the brightness gain corresponding to each initial image according to the brightness of the brightness reference area, and also provide an area to be adjusted for each of the initial images, so as to adjust the brightness value of the area to be adjusted according to the brightness gain, thereby improving the stitching and fusion effect of the panoramic image. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of the brightness balance adjustment method provided by the present invention;

[0042] Figure 2 is a schematic diagram of performing pixel sampling in an overlapping area in a surround stitching image provided by the present invention;

[0043] Figure 3 is a structural schematic diagram of the area to be adjusted in the initial image provided by the present invention;

[0044] Figure 4 It is a structural schematic diagram of the brightness balance adjustment device provided by the present invention;

[0045] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. Detailed implementation manners

[0046] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] The terms used in one or more embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present invention. The singular forms "a", "the" and "said" used in one or more embodiments of the present invention are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present invention refers to and includes any or all possible combinations of one or more of the associated listed items.

[0048] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of the present invention to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present invention, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0049] The following will be combined with Figures 1 - 3 to describe in detail the exemplary implementation manners of the present invention.

[0050] Figure 1 is a schematic flowchart of the brightness equalization adjustment method provided by the present invention. As Figure 1 shown, the brightness equalization adjustment method includes:[[]]

[0051] Step 11, obtaining each overlapping area in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images collected by each camera at the same moment;

[0052] It should be noted that the cameras are pre-installed on the vehicle, and there is no limit to the number of cameras. For the convenience of description and to improve the efficiency of calculation, four cameras are taken as an example in the embodiments of the invention. Preferably, a camera is installed respectively in front of, behind, on the left and on the right of the vehicle to form a front camera, a rear camera, a left camera and a right camera. Each camera is a fisheye camera. The images captured by the four cameras can cover the area around the vehicle body, and there is an overlapping area between the images taken by adjacent cameras. Furthermore, the initial image taken by the fisheye camera is an image in YUV format, so that when adjusting the brightness, the Y component of the initial image can be directly adjusted.

[0053] Specifically, the initial images captured by each camera at the same time are first obtained, and then each initial image is distorted and perspective transformed to obtain the bird's-eye view corresponding to each initial image, and then each bird's-eye view is stitched together to obtain the surround stitching image. Since there are overlapping areas between the images taken by adjacent cameras, the surround stitching image formed by stitching also has overlapping areas. In this embodiment, the overlapping area corresponding to the front camera and the left camera can be recorded as V FL , the overlapping area corresponding to the front camera and the right camera is recorded as V FR , the overlapping area corresponding to the rear camera and the left camera is recorded as V BL , and the overlapping area corresponding to the rear camera and the right camera is recorded as V BR .

[0054] Step 12, determining a plurality of brightness reference areas in each of the initial images based on each of the overlapping areas;

[0055] Specifically, the following steps are performed for each overlapping area in the surround stitching image: pixel sampling is performed in the overlapping area to obtain a number of pixel sampling points in the overlapping area, and then based on the intrinsic parameters and extrinsic parameters of each camera, the number of pixel sampling points in the overlapping area are mapped to the initial image of the camera corresponding to the overlapping area to form a brightness reference area in the initial image.

[0056] Understandably, due to V FL Indicates the overlapping area corresponding to the front camera and the left camera, and then in V FL The area is sampled to obtain multiple pixel sampling points, and then the pixel sampling points are mapped to the initial image of the front camera to form a brightness reference area I FL , and the initial image mapped to the left camera to form the brightness reference area I LF , and so on, V FR The pixel sampling points of the area are mapped to the initial image of the front camera to form a brightness reference area I FR , and V FRThe pixel sampling points in the area are mapped to the initial image of the right camera to form the luminance reference area I RF , V BL The pixel sampling points in the area are mapped to the initial image of the rear camera to form the luminance reference area I BL , and V BL The pixel sampling points in the area are mapped to the initial image of the left camera to form the luminance reference area I LB , V BR The pixel sampling points in the area are mapped to the initial image of the rear camera to form the luminance reference area I BR , and V BR The pixel sampling points in the area are mapped to the initial image of the right camera to form the luminance reference area I RB , such that two luminance reference areas are formed on the initial image of each camera.

[0057] Step 13, according to the multiple luminance reference areas in each of the initial images, form the area to be adjusted for each of the initial images;

[0058] Specifically, for each of the initial images, the following steps are performed:

[0059] According to the multiple luminance reference areas in the initial image, form an outer envelope box area including all the luminance reference areas. Preferably, the outer envelope box area is a matrix area, wherein the border of the matrix area is parallel to the upper, lower, left, and right edges of the initial image. Further, extend the matrix area downward until it is flush with the lower edge of the initial image to obtain the area to be adjusted for the initial image.

[0060] As Figure 3 shown, Figure 3 is a schematic structural diagram of the area to be adjusted in the initial image provided by the present invention. The front fisheye image represents the initial image captured by the front camera, and B F represents the outer envelope box area on the initial image of the front camera, and I F represents the area to be adjusted on the initial image of the front camera, B R and I R respectively represent the outer envelope box area and the area to be adjusted on the initial image of the right camera, B B and I B respectively represent the outer envelope box area and the area to be adjusted on the initial image of the rear camera, B L and I F respectively represent the outer envelope box area and the area to be adjusted on the initial image of the left camera.

[0061] Step 14, according to the reference luminance values of the multiple luminance reference areas in each of the initial images, calculate the luminance gain of each camera;

[0062] Specifically, following the example of step 12 above, the average brightness of each pixel sampling point within the brightness reference regions I FL , I FR , I RF , I RB , I BL , I BR , I LF , I LB is solved respectively, that is, the mean value of the Y channel of each pixel sampling point in the YUV image, and the average brightness corresponding to I FL , I FR , I RF , I RB , I BL , I BR , I LF , I LB is used as the reference brightness value Y FL , Y FR , Y RF , Y RB , Y BR , Y BL , Y LB , Y LF of the brightness reference region. Then, based on the reference brightness values of each brightness reference region, a target standard region is selected in each of the brightness reference regions. According to the reference brightness values of each brightness reference region, the brightness differences corresponding to the brightness reference regions of adjacent cameras in each camera are calculated respectively, and the average brightness difference corresponding to each of the brightness differences is calculated. Thus, based on the target standard region, according to the average brightness difference and the brightness differences corresponding to the adjacent cameras, the brightness gains of each camera are calculated.

[0063] Step 15: According to the brightness gains of each camera, the brightness values of each region to be adjusted are adjusted respectively to obtain a brightness adjustment result.

[0064] Specifically, the brightness gains corresponding to each camera are respectively subjected to pixel superposition processing with the brightness values of the regions to be adjusted corresponding to the camera, to obtain the brightness adjustment result of the initial image corresponding to each camera, that is: the brightness gain is superimposed on the Y channel component of the region to be adjusted in the YUV image.

[0065] It can be understood that the brightness value of the brightness equalization transformation region I F is superimposed with the brightness gain add F , the brightness value of I R is superimposed with the brightness gain add R , the brightness value of I B is superimposed with the brightness gain add B , the brightness value of I L is superimposed with the brightness gain addL 。

[0066] In the embodiment of the present invention, through the above solution, it is realized to determine multiple brightness reference regions in the initial images of each path of cameras by overlapping regions between adjacent cameras in the panoramic stitching image, calculate the brightness gain corresponding to each initial image according to the brightness of the brightness reference regions, and set regions to be adjusted in each of the initial images, so as to adjust the brightness value of the regions to be adjusted according to the brightness gain, thereby improving the stitching and fusion effect of the panoramic panoramic image.

[0067] In one embodiment, the above step 12: determining multiple brightness reference regions in each of the initial images based on each of the overlapping regions includes:

[0068] Step 121, performing pixel sampling on each of the overlapping regions to obtain a plurality of pixel sampling points in each of the overlapping regions;

[0069] Step 122, mapping the plurality of pixel sampling points in each of the overlapping regions to the initial images corresponding to each path of cameras respectively to form multiple brightness reference regions in each of the initial images.

[0070] Preferably, the acquisition method of the pixel sampling points can be performed according to a matrix sampling area, such as Figure 2 shown, Figure 2 is a schematic diagram of pixel sampling in the overlapping region in the panoramic stitching image provided by the present invention. Continuing with the example of the above step 12, pixel point sampling is respectively performed in the overlapping regions V FL , V FR , V BL and V BR to obtain n pixel sampling points V FL corresponding to the overlapping region V 1-n , n pixel sampling points V FR corresponding to the overlapping region V 2-n , n pixel sampling points V BL corresponding to the overlapping region V 3-n , n pixel sampling points V BR corresponding to the overlapping region V 4-n . Furthermore, map V 1-n to the initial image of the front camera to form the brightness reference region I FL , and map it to the initial image of the left camera to form the brightness reference region I LF . And so on. Finally, there are brightness reference regions I FL and I FR in the initial image of the front camera, and there are brightness reference regions I RF and I RB in the initial image of the right camera., the initial image of the rear camera has a brightness reference region I BL and I BR , the initial image of the left camera has a brightness reference region I LF and I LB .

[0071] In the embodiment of the present invention, through the above solution, by collecting pixel points in each overlapping region of the panoramic stitching image and mapping the pixel sampling points to the initial images of each camera path, a brightness reference region is formed, laying a foundation for calculating the brightness gain of each camera path based on the brightness values of the brightness reference regions in the subsequent stage.

[0072] In one embodiment, the above step 13: calculating the brightness gain of each camera path according to the reference brightness values of multiple brightness reference regions in each of the initial images includes:

[0073] Step 131, respectively calculating the reference brightness value corresponding to each brightness reference region based on the brightness values of each pixel sampling point in each brightness reference region;

[0074] Step 132, calculating the average brightness value according to the reference brightness values of each brightness reference region;

[0075] Step 133, selecting a target standard region in each brightness reference region based on the reference brightness value of each brightness reference region and the average brightness value;

[0076] The above step 133 includes:

[0077] Step 1331, adding the reference brightness values corresponding to multiple brightness reference regions in any one initial image to obtain the added brightness value of the any one initial image;

[0078] Step 1332, calculating the difference between the added brightness value of the any one initial image and the average brightness value, and taking the brightness reference region with the smallest difference as the target standard region of the any one initial image.

[0079] Step 134, respectively calculating the brightness difference corresponding to the brightness reference regions of adjacent cameras in each camera path according to the reference brightness values of each brightness reference region, and calculating the average brightness difference corresponding to each brightness difference;

[0080] Step 135, taking the target standard region as a reference, calculating the brightness gain of each camera path according to the average brightness difference and the brightness difference corresponding to the adjacent cameras.

[0081] The above step 135 includes:

[0082] Step 1351, set the brightness gain corresponding to the camera to which the target standard region belongs to zero, and calculate the brightness gains of each target camera according to the average brightness difference and the brightness differences corresponding to the adjacent cameras, where each of the target cameras is each camera except the camera to which the target standard region belongs

[0083] Specifically, calculate the average brightness between each pixel sampling point in the brightness reference regions I FL 、I FR 、I RF 、I RB 、I BL 、I BR 、I LF and I LB respectively. Then, take the average brightness between each pixel sampling point in each brightness reference region as the reference brightness value corresponding to the brightness reference region. In this embodiment, the reference brightness value of I FL can be denoted as Y FL 、the reference brightness value of I FR is denoted as Y FR 、the reference brightness value of I RF is denoted as Y RF 、the reference brightness value of I RB is denoted as Y RB 、the reference brightness value of I BL is denoted as Y BL 、the reference brightness value of I BR is denoted as Y BR 、the reference brightness value of I LF is denoted as Y LF and the reference brightness value of I LB is denoted as Y LB . Further, calculate the average brightness value according to the reference brightness values of each of the brightness reference regions, that is: the average brightness value Y mean =(Y FL +Y FR +Y RF +Y RB +Y BR +Y BL +Y LB +Y LF ) / 8. Then, for the initial image of each camera: add the reference brightness values corresponding to the multiple brightness reference regions in the initial image to obtain the added brightness value corresponding to the initial image. Further, calculate the difference between the added brightness value corresponding to the initial image and the average brightness value, and take the brightness reference region with the smallest difference as the target standard region according to the differences corresponding to each initial image. The difference calculation formula for each initial image is as follows:

[0084] Y F-mean=(Y FL +Y FR ) / 2 - Y mean

[0085] Y R-mea =(Y RF +Y RB ) / 2 - Y mean

[0086] Y B-mean =(Y BL +Y BR ) / 2 - Y mean

[0087] Y L-mea =(Y LF +Y LB ) / 2 - Y mean

[0088] Among them, Y F-mea represents the difference corresponding to the initial image of the front camera, Y R-mea represents the difference corresponding to the initial image of the right camera, Y B-mean represents the difference corresponding to the initial image of the rear camera, Y L-mea represents the difference corresponding to the initial image of the left camera.

[0089] Furthermore, calculate the brightness differences corresponding to the brightness reference regions of adjacent cameras in each camera respectively, and the calculation method is as follows:

[0090] d0 = Y FR - Y RF

[0091] d1 = Y RB - Y BR

[0092] d2 = Y BL - Y LB

[0093] d3 = Y LF - Y FL

[0094] Among them, d0 represents the brightness difference between the front camera and the right camera, d1 represents the brightness difference between the right camera and the rear camera, d3 represents the brightness difference between the rear camera and the left camera, and d4 represents the brightness difference between the left camera and the front camera. Furthermore, based on each brightness difference, calculate the brightness average value, and the brightness average value dmean = (d1 + d2 + d3 + d4) / 4.

[0095] Further, set the brightness gain corresponding to the camera to which the target standard area belongs to zero. For each camera other than the camera to which the target standard area belongs, calculate the brightness gain of each target camera according to the average brightness difference and the brightness difference corresponding to the adjacent camera. For example, if the camera to which the target standard area belongs is the front camera, the brightness gain of the front camera is add F = 0, the brightness gain of the right camera is add R = d0 - d mean The brightness gain of the rear camera is add B = (d0 + d1 - 2 * d mean ), and the brightness gain of the left camera is add L = (d0 + d1 + d2 - 3 * d mean ).

[0096] Through the above solution in the embodiments of the present invention, that is: based on the brightness values of each pixel sampling point in each of the brightness reference areas, calculate the reference brightness value corresponding to each of the brightness reference areas respectively; calculate the average brightness value according to the reference brightness values of each of the brightness reference areas; select the target standard area in each of the brightness reference areas based on the reference brightness values of each of the brightness reference areas and the average brightness value; calculate the brightness difference corresponding to the brightness reference area of the adjacent camera in each path camera respectively according to the reference brightness values of each of the brightness reference areas, and calculate the average brightness difference corresponding to each of the brightness differences; taking the target standard area as a reference, calculate the brightness gain of each of the path cameras according to the average brightness difference and the brightness difference corresponding to the adjacent camera. The reference brightness value corresponding to each of the brightness reference areas is realized, the target standard area is determined, and taking the target standard area as a reference, the brightness gain of each of the path cameras is calculated. The brightness gain calculation algorithm is simple, so as to perform adjustment based on the brightness gain to improve the stitching and fusion effect of the panoramic surround view image.

[0097] The brightness balance adjustment device provided by the present invention is described below. The brightness balance adjustment device described below can be correspondingly referred to the brightness balance adjustment method described above.

[0098] Figure 4 is a schematic structural diagram of the brightness balance adjustment device provided by the present invention. As Figure 4 shown, a brightness balance adjustment device in an embodiment of the present invention, the device includes:

[0099] An acquisition module 41, configured to acquire each overlapping area in the surround view stitching image, and the surround view stitching image is formed by transforming the initial images collected by each path camera at the same moment;

[0100] A determination module 42, configured to determine a plurality of luminance reference regions in each of the initial images based on each of the overlapping regions;

[0101] A formation module 43, configured to form a region to be adjusted for each of the initial images according to the plurality of luminance reference regions in each of the initial images;

[0102] A calculation module 44, configured to calculate the luminance gain of each camera according to the reference luminance values of the plurality of luminance reference regions in each of the initial images;

[0103] An adjustment module 45, configured to adjust the luminance values of each of the regions to be adjusted respectively according to the luminance gain of each camera to obtain a luminance adjustment result.

[0104] The determination module 42 is further configured to:

[0105] Perform pixel sampling on each of the overlapping regions to obtain a plurality of pixel sampling points within each of the overlapping regions;

[0106] Map the plurality of pixel sampling points within each of the overlapping regions to the corresponding initial images of each camera respectively to form a plurality of luminance reference regions in each of the initial images.

[0107] The calculation module 44 is further configured to:

[0108] Calculate the reference luminance value corresponding to each of the luminance reference regions respectively based on the luminance values of each pixel sampling point in each of the luminance reference regions;

[0109] Calculate a luminance average value according to the reference luminance values of each of the luminance reference regions;

[0110] Select a target standard region from each of the luminance reference regions based on the reference luminance value of each of the luminance reference regions and the luminance average value;

[0111] Calculate the luminance difference corresponding to the luminance reference regions of adjacent cameras in each camera respectively according to the reference luminance values of each of the luminance reference regions, and calculate the average luminance difference corresponding to each of the luminance differences;

[0112] Based on the target standard region, calculate the luminance gain of each camera according to the average luminance difference and the luminance difference corresponding to the adjacent cameras.

[0113] The calculation module 44 is further configured to:

[0114] Add up the reference luminance values corresponding to the plurality of luminance reference regions in any one of the initial images to obtain the added luminance value of the any one initial image;

[0115] Calculate the difference between the added brightness value of any one of the initial images and the average brightness value, and use the brightness reference area with the smallest difference as the target standard area of any one of the initial images.

[0116] The calculation module 44 is further configured to:

[0117] Set the brightness gain corresponding to the camera to which the target standard area belongs to zero, and calculate the brightness gains of each target camera according to the average brightness difference and the brightness differences corresponding to the adjacent cameras, where each of the target cameras is each camera other than the camera to which the target standard area belongs.

[0118] The forming module 43 is further configured to:

[0119] For any one of the initial images: Based on the multiple brightness reference areas of the initial image, calculate the circumscribed bounding box area including the multiple brightness reference areas;

[0120] Extend the matrix area downward to be flush with the lower edge of the initial image to form the area to be adjusted for each of the initial images.

[0121] The adjustment module 45 is further configured to:

[0122] Perform pixel superposition processing on the brightness gains of each camera path and the brightness values of the areas to be adjusted corresponding to each camera path to obtain the brightness adjustment result.

[0123] It should be noted here that the above device provided by the embodiments of the present invention can implement all the method steps implemented by the above method embodiments and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0124] Figure 5It is a schematic structural diagram of an electronic device provided by the present invention. The electronic device may include: a processor 510, a memory 520, a communications interface 530, and a communication bus 540. Among them, the processor 510, the memory 520, and the communication interface 530 complete communication with each other through the communication bus 540. The processor 510 can call the logical instructions in the memory 520 to execute a brightness equalization adjustment method, which includes: obtaining each overlapping region in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images collected by each camera at the same moment; based on each of the overlapping regions, determining a plurality of brightness reference regions in each of the initial images; according to the plurality of brightness reference regions in each of the initial images, forming a region to be adjusted in each of the initial images; calculating the brightness gains of each camera according to the reference brightness values of the plurality of brightness reference regions in each of the initial images; and adjusting the brightness values of each of the regions to be adjusted respectively according to the brightness gains of each camera to obtain a brightness adjustment result.

[0125] In addition, when the logical instructions in the above-mentioned memory 520 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0126] In another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the brightness balance adjustment method provided by the above-mentioned various methods. The method includes: obtaining each overlapping region in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images collected by each camera at the same moment; based on each of the overlapping regions, determining a plurality of brightness reference regions in each of the initial images; according to the plurality of brightness reference regions in each of the initial images, forming a region to be adjusted in each of the initial images; calculating the brightness gain of each camera according to the reference brightness values of the plurality of brightness reference regions in each of the initial images; and adjusting the brightness values of each of the regions to be adjusted respectively according to the brightness gains of each camera to obtain a brightness adjustment result.

[0127] On the other hand, the present invention further provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the brightness balance adjustment method provided by the above-mentioned various methods. The method includes: obtaining each overlapping region in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images collected by each camera at the same moment; based on each of the overlapping regions, determining a plurality of brightness reference regions in each of the initial images; according to the plurality of brightness reference regions in each of the initial images, forming a region to be adjusted in each of the initial images; calculating the brightness gain of each camera according to the reference brightness values of the plurality of brightness reference regions in each of the initial images; and adjusting the brightness values of each of the regions to be adjusted respectively according to the brightness gains of each camera to obtain a brightness adjustment result.

[0128] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0129] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A brightness equalization adjustment method, characterized in that, Including: Obtain each overlapping region in the panoramic stitching image, where the panoramic stitching image is formed by transforming the initial images collected by each camera at the same moment; Based on each of the overlapping regions, determine a plurality of luminance reference regions in each of the initial images; According to the plurality of luminance reference regions in each of the initial images, form a region to be adjusted for each of the initial images; Calculate the luminance gain of each camera according to the reference luminance values of the plurality of luminance reference regions in each of the initial images; According to the luminance gain of each camera, adjust the luminance value of each region to be adjusted respectively to obtain a luminance adjustment result; The determining a plurality of luminance reference regions in each of the initial images based on each of the overlapping regions includes: Perform pixel sampling on each of the overlapping regions to obtain a plurality of pixel sampling points in each of the overlapping regions; Map the plurality of pixel sampling points in each of the overlapping regions to the corresponding initial images of each camera respectively to form a plurality of luminance reference regions in each of the initial images; The calculating the luminance gain of each camera according to the reference luminance values of the plurality of luminance reference regions in each of the initial images includes: Based on the luminance values of each pixel sampling point in each of the luminance reference regions, calculate the reference luminance value corresponding to each of the luminance reference regions respectively; Calculate the average luminance value according to the reference luminance values of each of the luminance reference regions; Based on the reference luminance value of each of the luminance reference regions and the average luminance value, select a target standard region in each of the luminance reference regions; According to the reference luminance values of each of the luminance reference regions, calculate the luminance difference corresponding to the luminance reference regions of adjacent cameras in each camera respectively, and calculate the average luminance difference corresponding to each of the luminance differences; Taking the target standard region as a reference, calculate the luminance gain of each camera according to the average luminance difference and the luminance difference corresponding to the adjacent cameras; The selecting a target standard region in each of the luminance reference regions based on the reference luminance value of each of the luminance reference regions and the average luminance value includes: Add up the reference luminance values corresponding to the plurality of luminance reference regions in any one initial image to obtain the added luminance value of the any one initial image; Calculate the difference between the added luminance value of the any one initial image and the average luminance value, and use the luminance reference region with the smallest difference as the target standard region of the any one initial image.

2. The brightness equalization adjustment method according to claim 1, characterized in that The calculating the luminance gain of each camera according to the average luminance difference and the luminance difference corresponding to the adjacent cameras taking the target standard region as a reference includes: Set the luminance gain corresponding to the camera to which the target standard region belongs to zero, and calculate the luminance gain of each target camera according to the average luminance difference and the luminance difference corresponding to the adjacent cameras, where each of the target cameras is each camera except the camera to which the target standard region belongs.

3. The brightness balance adjustment method according to claim 1, wherein The forming a region to be adjusted for each of the initial images according to the plurality of luminance reference regions in each of the initial images includes: For any initial image: Based on multiple luminance reference regions of the initial image, an enclosing box region including the multiple luminance reference regions is calculated; the enclosing box region is a matrix region; The matrix region is extended downward to be flush with the lower edge of the initial image to form a region to be adjusted for each initial image.

4. The brightness equalization adjustment method according to claim 1, wherein Adjusting the luminance values of each region to be adjusted according to the luminance gains of each camera to obtain a luminance adjustment result includes: Performing pixel superposition processing on the luminance gains of each camera and the luminance values of the regions to be adjusted corresponding to each camera respectively to obtain the luminance adjustment result.

5. A brightness equalization adjustment device, characterized in that, It includes: An acquisition module for acquiring each overlapping region in the panoramic stitching image, where the panoramic stitching image is formed by transforming initial images collected by each camera at the same moment; A determination module for determining multiple luminance reference regions in each initial image based on each overlapping region; A formation module for forming a region to be adjusted for each initial image according to the multiple luminance reference regions in each initial image; A calculation module for calculating the luminance gains of each camera according to the reference luminance values of the multiple luminance reference regions in each initial image; An adjustment module for adjusting the luminance values of each region to be adjusted according to the luminance gains of each camera to obtain a luminance adjustment result; Determining multiple luminance reference regions in each initial image based on each overlapping region includes: Performing pixel sampling on each overlapping region to obtain several pixel sampling points in each overlapping region; Mapping the several pixel sampling points in each overlapping region to the initial image corresponding to each camera respectively to form multiple luminance reference regions in each initial image; Calculating the luminance gains of each camera according to the reference luminance values of the multiple luminance reference regions in each initial image includes: Based on the luminance values of each pixel sampling point in each luminance reference region, calculating the reference luminance value corresponding to each luminance reference region respectively; Calculating a luminance average value according to the reference luminance values of each luminance reference region; Selecting a target standard region in each luminance reference region based on the reference luminance value of each luminance reference region and the luminance average value; Calculating the luminance difference corresponding to the luminance reference regions of adjacent cameras in each camera respectively according to the reference luminance values of each luminance reference region, and calculating the average luminance difference corresponding to each luminance difference; Taking the target standard region as a reference, calculating the luminance gains of each camera according to the average luminance difference and the luminance difference corresponding to the adjacent cameras; Selecting a target standard region in each luminance reference region based on the reference luminance value of each luminance reference region and the luminance average value includes: Adding the reference luminance values corresponding to the multiple luminance reference regions in any initial image to obtain the added luminance value of the any initial image; Calculate the difference between the added brightness value of any one of the initial images and the average brightness value, and use the brightness reference area with the smallest difference as the target standard area of any one of the initial images.

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the program, it implements the brightness equalization adjustment method according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the brightness equalization adjustment method according to any one of claims 1 to 4.

Images