Color uniformity method, system and electronic equipment based on original remote sensing image

Abstract

The present invention provides a color leveling method, system, and electronic device based on original remote sensing images. The method comprises: geometrically correcting and resampling the original remote sensing image; performing preliminary color leveling on the resampled original remote sensing image, and then performing mosaic processing to generate a template image; dividing the original remote sensing image into blocks according to a preset size and overlap, and recording the starting point, width, and height information of each block image; calculating the longitude and latitude corresponding areas of the block images in the template image; calculating the mean and variance of the longitude and latitude corresponding areas in the block images and the template image, interpolating the mean and variance of each pixel based on the calculated mean and variance, and obtaining a mean map and variance map of the same size as the original image and the template image; and combining the interpolated mean map and variance map with a reference mean map and variance map to perform fine color leveling on the original remote sensing image pixel by pixel. The present invention achieves color leveling of original remote sensing images by utilizing computer technology.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more particularly to a color uniformity method, system and electronic equipment based on original remote sensing images. Background Art

[0002] Current satellite imagery 3D modeling primarily uses raw remote sensing imagery as input. Due to variations in time, weather, sensor quality, and terrain, raw images can exhibit uneven lighting and color distribution, hindering the capture of terrain and object features during 3D modeling. This results in low data quality and poor visual quality. Therefore, color stabilization of raw remote sensing imagery is crucial for improving the accuracy and efficiency of 3D modeling, enhancing model quality, and supporting subsequent analytical applications.

[0003] Existing image color uniformity methods are mainly based on digital orthophoto maps (DOM) and other product data; these product data have spatial reference information, while the original remote sensing images do not have spatial reference information, so such methods are difficult to process the original remote sensing images. Summary of the Invention

[0004] Based on the technical problems existing in the prior art, the present invention provides a color uniformity method, system and electronic equipment based on original remote sensing images. By adopting block calculation and using the RPC coefficient to convert the image pixel coordinates into geographic coordinates, the corresponding areas of the blocks in the reference template image are used as the color uniformity background to perform fine color uniformity processing on the original image, so as to solve the problem that the existing methods are difficult to perform color adjustment on the original remote sensing images.

[0005] According to a first aspect of the present invention, a color uniformity method based on an original remote sensing image is provided, comprising the following steps:

[0006] Step 1. Perform geometric correction on the original remote sensing image to obtain the corrected image;

[0007] Step 2. Resample the corrected image according to the target resolution;

[0008] Step 3. Perform preliminary color grading on the resampled image and mosaic the grading results to generate a template image.

[0009] Step 4. Divide the original remote sensing image into blocks according to the preset size and overlap, and record the starting point, width and height information of each block image;

[0010] Step 5. Calculate the latitude and longitude corresponding areas of the block image in the template image;

[0011] Step 6. Calculate the mean and variance of the corresponding latitude and longitude areas in the block image and the template image. Based on the calculated mean and variance, use the bilinear interpolation method to interpolate the mean and variance of each pixel, and obtain a mean map and variance map of the same size as the original remote sensing image. Apply the same operation to the template image to obtain a reference mean map and reference variance map of the same size as the original remote sensing image.

[0012] Step 7. Combine the interpolated mean map, variance map, and reference mean map, variance map to perform fine color grading on the original remote sensing image pixel by pixel.

[0013] On the basis of the above technical solution, the present invention can also make the following improvements.

[0014] Optionally, performing geometric correction on the original remote sensing image includes:

[0015] Vegetation enhancement is performed on each original remote sensing image, and the original remote sensing image is geometrically corrected using rational polynomial coefficients to obtain a corrected image. The corresponding corrected image coordinates are geographic coordinates.

[0016] Optionally, resampling the corrected image according to the target resolution includes:

[0017] The resolution of the corrected image is calculated to obtain the minimum resolution, which is multiplied by the coefficient N as the resampling target resolution. The corrected image is resampled to make the resolution of all corrected images consistent.

[0018] Optionally, the coefficient N is obtained by dividing the brightness mean of the minimum resolution image by the brightness variance of the minimum resolution image and then multiplying the result by a preset value.

[0019] Optionally, performing preliminary color grading on the resampled image and mosaicking the color grading result includes:

[0020] The resolution of all the corrected images is unified, the resampled images are preliminarily color-homogenized to reduce the color difference between all the resampled images, and the preliminarily color-homogenized images are mosaicked to generate a template image.

[0021] Optionally, the calculation of the latitude and longitude corresponding areas of the block image in the template image includes:

[0022] The rational polynomial coefficients of the original remote sensing image data are used to convert the starting point of each block image from pixel coordinates to geographic coordinates. According to the converted geographic coordinates, the corresponding area of ​​the block image on the template image is obtained.

[0023] Optionally, calculating the mean and variance of the areas corresponding to the longitude and latitude in the block image and the template image includes:

[0024] The pixel values ​​of the block image and the block reference image are counted by band respectively, and the mean and variance of each band are calculated based on the pixel values ​​to obtain the corresponding variance map and mean map.

[0025] Optionally, performing fine color grading on the original remote sensing image pixel by pixel includes:

[0026] Taking the template image as the reference target, the pixels of the original remote sensing image are traversed in different bands. The original remote sensing image is converted from pixel coordinates to geographic coordinates using rational polynomial coefficients. The corresponding position of each pixel coordinate in the original remote sensing image in the template image is obtained based on the geographic coordinates.

[0027] According to a second aspect of the present invention, there is provided a color uniformity system for original remote sensing images, comprising:

[0028] Image loading module, used to read and parse remote sensing data, and obtain basic information such as rational polynomial coefficients, image width and height, and image starting point;

[0029] The geometric correction module uses the obtained rational polynomial coefficients and publicly available elevation information to perform geometric correction on the image, so that the coordinates of the original remote sensing image are converted from pixel coordinates to geographic coordinates;

[0030] The vegetation enhancement module processes images including near-infrared and red bands to enhance the color of vegetation areas;

[0031] The resampling module resamples the resolution of the input remote sensing data to make the resolution of the input remote sensing data consistent;

[0032] The color grading module uses the input reference image or band reference data value to grade the original remote sensing data and output the graded result.

[0033] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to implement steps of a method for color uniformity of an original remote sensing image when executing a computer program stored in the memory.

[0034] Technical effects and advantages of the present invention:

[0035] The present invention discloses a color grading method, system, and electronic device based on original remote sensing images, which achieve color grading of original remote sensing images by utilizing computer technology. The color grading processing object is the original remote sensing image without spatial reference information. These remote sensing images have color aberration, inconsistent resolution, and are all pixel coordinate systems. The present invention performs vegetation enhancement on the original remote sensing image and corrects the rational polynomial coefficients to convert the image into a geographic coordinate system. Furthermore, to unify the resolution, the remote sensing image is resampled to the target resolution. To reduce image color aberration, the image is initially color graded at a resolution lower than that of the original image. After resampling, the image resolution and color aberration are smaller than those of the original image. Initial color grading utilizes a set reference variance and mean to greatly eliminate image color aberration. However, at this point, the remote sensing image is in a geographic coordinate system, making three-dimensional modeling unusable. Therefore, finally, using the initially color grading image as the color grading background, the original remote sensing image is color grading, block calculation, and variance and mean interpolation are performed on the image, greatly eliminating color aberration between images and ensuring a natural color transition between adjacent image blocks.

[0036] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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 any creative work.

[0038] Figure 1 A schematic diagram of the process of creating a template image according to an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of an original remote sensing image provided by an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of an initial color-leveling result, i.e., a template image, provided by an embodiment of the present invention;

[0041] Figure 4 A corresponding area diagram of the block image in the reference template provided by an embodiment of the present invention;

[0042] Figure 5 A schematic diagram of bilinear interpolation provided by an embodiment of the present invention;

[0043] Figure 6A schematic diagram of a process for image color grading according to an embodiment of the present invention;

[0044] Figure 7 This is the final color uniformity result diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] It is understandable that, based on the defects in the background technology, the embodiment of the present invention proposes a color uniformity method based on the original remote sensing image. The process is referenced to Figure 1 , the method comprising:

[0047] Step 1: geometrically correct the original remote sensing image to obtain the corrected image;

[0048] It should be noted that the original remote sensing images used in the embodiment of the present invention are as follows: Figure 2 As shown in the figure, there are color differences in the original remote sensing images, and the resolution is inconsistent. It is visible to the naked eye, and the color difference is large, so it cannot be used for modeling.

[0049] Therefore, first of all, it is necessary to perform geometric correction on the original remote sensing image, including:

[0050] Vegetation enhancement is performed on each original remote sensing image. First, the Normalized Difference Vegetation Index (NDVI) is calculated using the brightness values ​​of the red and near-infrared bands. Different strategies are then used based on the NDVI values ​​to enhance the color of the vegetation area. The vegetation enhancement calculation formula is as follows:

[0051]

[0052]

[0053] in, is the brightness value of the red light band, is the brightness value in the near-infrared band, is the enhancement coefficient, which is set to 0.35 in this embodiment. is the brightness value of the green light band, is the brightness value of the enhanced green light band.

[0054] Then, the RPC coefficient is used to perform geometric correction on the original remote sensing image to obtain the corrected image. At this time, the coordinates of the corrected image are all geographic coordinates.

[0055] It should be noted that RPC coefficients (Rational Polynomial Coefficients) are polynomial parameters that describe the mapping relationship between image coordinates (rows and columns) and ground coordinates (longitude, latitude, and elevation). They are a core component of the Rational Function Model (RFM). Using RPC coefficients for correction is an extension of the linear polynomial model, using a nonlinear relationship to establish a correspondence between image pixel coordinates and the corresponding longitude and latitude. Image pixel coordinates are converted to geographic coordinates by combining pixel coordinates, elevation data, and parameters such as rotation, scaling, and perspective distortion included in the RPC model. The elevation data in this example comes from the publicly available DEM elevation data World_geoid_height_EGM96.img.

[0056] Step 2, resample the corrected image according to the target resolution;

[0057] The original remote sensing images have the problem of inconsistent resolution. If the images are directly mosaicked, there will be obvious visual differences between images of different resolutions. The fineness and detail richness of high-resolution images are usually higher than those of low-resolution images. Direct mosaicking will result in obvious boundaries, affecting the overall visual effect.

[0058] Therefore, the corrected image needs to be resampled, and the resampling includes:

[0059] The resolution of the corrected image is calculated to obtain the minimum resolution, which is multiplied by the coefficient N as the resampling target resolution. The corrected image is resampled to make the resolution of all corrected images consistent.

[0060] Furthermore, the rectified image is first analyzed to obtain the image resolution, and N times the minimum resolution is used as the resampling target resolution. For ease of description, the symbol R represents N times the minimum resolution, and all rectified images are resampled to resolution R. N is related to the information content of the remote sensing image, and the N value calculation formula is as follows:

[0061]

[0062] Wherein, m is a preset value. In this embodiment, the value of m is 5. The value represents the average brightness of the image with the minimum resolution. The value has the brightness variance of the minimum resolution image.

[0063] Perform preliminary color balancing on the resampled images to reduce the color difference between all resampled images. The calculation formula is as follows:

[0064]

[0065] in, Represents the pixel value after processing; They represent the variance of the (x, y) position of the resampled image in the corresponding position of the template image and the variance of the (x, y) position of the resampled image respectively; Respectively represent the mean of the resampled image (x, y) position in the corresponding position of the template image, the mean of the resampled image (x, y) position, Represent the brightness coefficient and variance expansion coefficient respectively.

[0066] When performing preliminary color grading on the resampled image, The value is 1. When processing the red light band, The values ​​are 54 and 95 respectively; when processing the green light band, The values ​​are 39 and 103 respectively; when processing the blue light band, The values ​​are 38, 95 respectively;

[0067] Step 3: Perform preliminary color grading on the resampled image and mosaic the grading results to generate a template image.

[0068] The performing preliminary color grading on the resampled image and mosaicking the color grading result includes:

[0069] The resolution of all images after correction is made consistent, and the resampled images are preliminarily color-homogenized to reduce the color difference between all resampled images. The preliminarily color-homogenized images are mosaicked to generate template images. At this time, the color difference of the template images is small and can be basically ignored.

[0070] It should be noted that the original remote sensing images of uniform resolution are mosaicked to obtain a low-resolution template image; the template image obtained in the embodiment is as follows: Figure 3 As shown, the template image has reduced color difference and lower resolution compared to the original image, and is used as a reference target for fine color uniformity. In this embodiment, the mosaic process uses the MULTI_BAND method of the third-party open source library OpenCV for mosaicking.

[0071] Step 4: Divide the original remote sensing image into blocks according to the preset size and overlap, and record the starting point, width and height information of each block image;

[0072] The original remote sensing image to be processed is divided into blocks according to preset sizes and overlaps to solve the problem of inconsistent overall tones and obvious local tones between adjacent images. For simplicity, the term "block image" is used to represent the image after the original remote sensing data is divided into blocks.

[0073] This example uses a 256x256 block size to divide the image into NxM sub-regions, recording the starting point coordinates, width, height, and other information of the sub-regions. To eliminate color differences between adjacent blocks, the image blocks are expanded by 100 pixels, resulting in an actual image block size of 356x356.

[0074] Step 5, calculate the corresponding latitude and longitude areas of the block image pixels in the template image;

[0075] The RPC coefficient of the original remote sensing image data is used to convert the starting point of each block image from pixel coordinates to geographic coordinates; since the template image is in a geographic coordinate system, the corresponding area of ​​the block image on the template image can be obtained according to the converted geographic coordinates. For the sake of simplicity, the block template image is used to represent the corresponding area of ​​the block image in the template image. Figure 4 , using the RPC coefficient, find the corresponding area in the template image for the block image.

[0076] Step 6: Calculate the mean and variance of the corresponding longitude and latitude areas in the block image and the template image. Based on the calculated mean and variance, use bilinear interpolation to interpolate the mean and variance of each pixel, and obtain a mean map and variance map of the same size as the original image. The same operation is performed on the template image to obtain a reference mean map and reference variance map of the same size as the original remote sensing image.

[0077] The calculation of the mean and variance of the latitude and longitude corresponding areas in the block image and the template image includes:

[0078] Count the pixel values ​​of the block image and the block reference image by band respectively. Based on these pixel values, calculate the mean and variance of each band to obtain the variance map and mean map of NxM size. Then use the bilinear interpolation method to interpolate the mean and variance of each pixel to obtain the mean map and variance map of the same size as the original image. The same operation is used for the block reference image to obtain the reference mean map and reference variance map of the same size as the template image. Figure 5 The figure shows a schematic diagram of bilinear interpolation. The bilinear interpolation method is used to obtain the mean map and variance map of the same size as the original image. The same operation is also performed on the block template image to calculate the mean and variance, and the bilinear interpolation method is used to obtain the reference mean map and reference variance map of the same size as the template image. The calculated mean and variance use an interpolation method that is not limited to bilinear interpolation.

[0079] When calculating the variance and mean, this embodiment ignores pixels whose pixel values ​​in all bands are 0. Each original image is divided into NxM block images according to the blocking strategy, and a mean and variance can be calculated for each block image. Based on this, an NxM size mean map and variance map can be obtained for each image. The mean map and variance map are interpolated using the bilinear interpolation method, and the interpolated mean map and interpolated variance map of the same size as the original image are obtained using the bilinear interpolation method. The block reference image is also operated using the same principle to obtain the interpolated reference mean map and interpolated reference variance map of the same size as the template image.

[0080] Step 7: Combine the interpolated mean map, variance map, and reference mean map, variance map to perform fine color grading on the original remote sensing image pixel by pixel.

[0081] The process of using template images to even out the color of original remote sensing images is as follows: Figure 6 As shown in the figure, the template image is used as the reference target, and the pixels of the original remote sensing image are traversed in different bands. The RPC coefficient is used to convert its coordinates from pixel coordinates to geographic coordinates. According to this principle, the coordinates of each pixel in the original remote sensing image are converted from pixel coordinates to geographic coordinates. Find the corresponding position in the template image , the original remote sensing image and the interpolated mean map and interpolated variance map are in one-to-one correspondence. The value of the position is , variance map after interpolation The value of the position is , the template image corresponds to the reference mean map after interpolation and the reference variance map after interpolation. The value of the position is , reference variance map after interpolation The value of the position is , process the original image according to the calculation formula in Step 3. The values ​​are 0.75 and 0.6 respectively. Finally, the computer program written in C++ development language is used to automatically perform color uniformity processing on the original remote sensing image. The final color uniformity result is shown in Figure 7 shown.

[0082] In summary, an embodiment of the present invention provides a method for color grading of original remote sensing images. The method utilizes RPC (Rational Polynomial Coefficients) coefficients to convert image pixel coordinates into geographic coordinates, uses a template image derived from the original remote sensing image as a color grading background, and performs fine color grading on the original remote sensing image to solve the problem that existing methods are difficult to perform color grading on original remote sensing images.

[0083] According to a second aspect of the present invention, the present invention provides a color uniformity system based on original remote sensing images, comprising:

[0084] Image loading module, used to read and parse remote sensing data in common formats, and obtain basic information such as RPC information, image width and height, and image starting point;

[0085] The geometric correction module uses the obtained RPC coefficients and publicly available elevation information to perform geometric correction on the image, so that the coordinates of the original remote sensing image are converted from pixel coordinates to geographic coordinates;

[0086] The vegetation enhancement module processes images that include both near-infrared and red bands to enhance the color of vegetation areas.

[0087] The resampling module resamples the resolution of the input remote sensing data to make the resolution of the input remote sensing data consistent;

[0088] The color grading module uses the input reference image or band reference data value to grade the original remote sensing data and output the graded result.

[0089] It can be understood that the color equalization system based on original remote sensing images provided by the present invention corresponds to the color equalization method based on original remote sensing images provided in the aforementioned embodiments. The relevant technical features of the color equalization system based on original remote sensing images can refer to the relevant technical features of the color equalization method based on original remote sensing images, and will not be repeated here.

[0090] According to a third aspect of the present invention, an embodiment of the present invention provides an electronic device, which may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may invoke logic instructions in the memory to execute the steps of the aforementioned method for color-leveling a template image and an original remote sensing image.

[0091] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or 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 media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0092] On the other hand, the present invention also provides a computer program product, which 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 perform the implementation steps of the above-mentioned color uniformity method based on original remote sensing images.

[0093] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the implementation steps of the above-mentioned color uniformity method based on original remote sensing images.

[0094] Professionals will appreciate that, in conjunction with the embodiments disclosed in the materials of this application, it is possible to implement them using electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of functionality in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not exceed the scope of the present invention. The steps of the methods or algorithms described in the embodiments disclosed in this application can be implemented directly using hardware, software modules executed by a processor, or a combination of the two. The software module can be placed in a random access memory, a memory, a read-only memory, an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0095] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A color uniformity method based on original remote sensing images, characterized in that: The following steps are involved: Step 1. Perform geometric correction on the original remote sensing image, including: enhancing vegetation on the original remote sensing image, calculating the normalized vegetation coefficient using the brightness values ​​of the red band and the brightness values ​​of the near-infrared band, and then using different strategies to enhance the color of the vegetation area based on the value of the normalized vegetation coefficient. The original remote sensing image is geometrically corrected using rational polynomial coefficients to obtain the corrected image. The corresponding coordinates of the corrected image are geographic coordinates. Step 2. Resample the corrected image according to the target resolution; Step 3. Perform preliminary color grading on the resampled image and mosaic the grading results to generate a template image. Step 4. Divide the original remote sensing image into blocks according to the preset size and overlap, and record the starting point, width and height information of each block image; Step 5. Calculate the latitude and longitude corresponding areas of the block image in the template image; this includes: using the rational polynomial coefficients of the original remote sensing image data to convert the starting point of each block image from pixel coordinates to geographic coordinates, and obtaining the corresponding area of ​​the block image on the template image based on the converted geographic coordinates; Step 6. Calculate the mean and variance of the corresponding latitude and longitude areas in the block image and the template image, including: counting the pixel values ​​of the block image and the block reference image by band, and calculating the mean and variance of each band based on the pixel values ​​to obtain corresponding variance maps and mean maps; Based on the calculated mean and variance, the bilinear interpolation method is used to interpolate the mean and variance of each pixel, and obtain the mean map and variance map of the same size as the original remote sensing image. The same operation is performed on the template image to obtain the reference mean map and reference variance map of the same size as the original remote sensing image. Step 7. Combine the interpolated mean map, variance map, and reference mean map, variance map to perform fine color grading on the original remote sensing image pixel by pixel, including: using the template image as a reference target, traversing the pixels of the original remote sensing image in different bands, using rational polynomial coefficients to convert the original remote sensing image from pixel coordinates to geographic coordinates, and obtaining the corresponding position of each pixel coordinate in the original remote sensing image in the template image based on the geographic coordinates.

2. The color uniformity method based on original remote sensing images according to claim 1, characterized in that: The resampling of the corrected image according to the target resolution includes: The resolution of the corrected image is calculated to obtain the minimum resolution, which is multiplied by the coefficient N as the resampling target resolution. The corrected image is resampled to make the resolution of all corrected images consistent.

3. The color uniformity method based on original remote sensing images according to claim 2, characterized in that: The coefficient N is obtained by dividing the brightness mean of the minimum resolution image by the brightness variance of the minimum resolution image and then multiplying by a preset value.

4. The color uniformity method based on original remote sensing images according to claim 1, characterized in that: The performing preliminary color grading on the resampled image and mosaicking the color grading result includes: The resolution of all the corrected images is unified, the resampled images are preliminarily color-homogenized to reduce the color difference between all the resampled images, and the preliminarily color-homogenized images are mosaicked to generate a template image.

5. A color leveling system based on original remote sensing images, used in the color leveling method based on original remote sensing images according to any one of claims 1 to 4, characterized in that: The system comprises: Image loading module, used to read and parse remote sensing data, and obtain basic information such as rational polynomial coefficients, image width and height, and image starting point; The geometric correction module uses the obtained rational polynomial coefficients and publicly available elevation information to perform geometric correction on the image, so that the coordinates of the original remote sensing image are converted from pixel coordinates to geographic coordinates; The vegetation enhancement module processes images including near-infrared and red bands to enhance the color of vegetation areas; The resampling module resamples the resolution of the input remote sensing data to make the resolution of the input remote sensing data consistent; The color grading module uses the input reference image or band reference data value to grade the original remote sensing data and output the graded result.

6. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the processor is used to implement a color uniformity method based on original remote sensing images as claimed in any one of claims 1 to 4 when executing a computer program stored in the memory.

Images