Resolution unification method for variable-resolution image

Abstract

The invention belongs to the field of image processing, particularly relates to a variable-resolution image resolution unification method, and aims to solve the problems that visual quality and information integrity of an image are difficult to maintain at the same time, detail information is easy to lose, and the image utilization rate is reduced. The method comprises the following steps: cutting an initial image into a plurality of fragment images along the edge part, and ensuring that an overlapping region exists between the adjacent fragment images; the method comprises the following steps of: inputting high-resolution fragmented images into a super-resolution reconstruction model to obtain high-resolution fragmented images, carrying out geometric correction processing, correcting all the fragmented images into a unified coordinate system, carrying out weighted fusion processing on overlapped regions of the geometrically corrected fragmented images, and realizing seamless splicing with consistent hues based on a weight distribution principle of center distances of the fragmented images. And generating a unified resolution image. According to the method, detail information loss caused by global down-sampling / up-sampling in a traditional resampling method is avoided, and the problem of image blurring caused by single resampling operation is solved.

Description

Background Art

[0002] Variable-resolution images refer to images with an extremely wide imaging width, capable of capturing a large geographical area at once. The image coverage far exceeds that of conventional satellites and can cover thousands of kilometers or more. Variable-resolution images greatly improve the efficiency of data collection and are crucial for applications such as environmental monitoring, urban planning, and disaster response. Due to factors such as imaging methods, the Earth's curvature, and changes in the exterior orientation elements of sensors, large-width remote sensing images often exhibit deformation phenomena. This deformation results in a higher resolution at the center (sub-satellite point) of the image and a lower resolution at the edge part.

[0003] If a resampling method is simply adopted, downsampling the high-resolution area and upsampling the low-resolution area to achieve resolution uniformity, this method only considers the requirement of uniform resolution while ignoring the visual perception of the image. At the same time, it may also lead to the loss of detailed information, thereby reducing the utilization rate of the image. This resampling method is only applicable to ordinary satellite remote sensing images with relatively small differences in resolution for a single image.

[0004] Therefore, for the resolution uniformity of variable-resolution images, more refined image processing techniques need to be adopted to maintain the visual quality and information integrity of the images.

[0005] Based on this, the present invention proposes a method for unifying the resolution of variable-resolution images. Summary of the Invention

[0006] To solve the above problems in the prior art, namely, it is difficult to simultaneously maintain the visual quality and information integrity of the image, which easily leads to the loss of detailed information and a reduction in the utilization rate of the image, the present invention provides a method for unifying the resolution of variable-resolution images. The method includes the following steps: Step S1: Obtain the remote sensing image with variable resolution to be unified as the initial image. Starting from the center of the initial image, based on the change range of the resolution from the center to the edge, cut out multiple piecewise images along the edge part of the initial image, and ensure that there is an overlapping area between adjacent piecewise images; Step S2: Use the piecewise image corresponding to the low-resolution area as the input data and input it into the pre-constructed and trained super-resolution reconstruction model to obtain a high-resolution piecewise image with the same resolution as the piecewise image at the center; Step S3: Perform geometric correction processing on the piecewise images with unified resolution and correct all piecewise images into a unified coordinate system; Step S4: Perform weighted fusion processing on the overlapping areas of the piecewise images after geometric correction, and achieve seamless splicing with consistent tones based on the weight distribution principle of the distance from the center of the piecewise image to generate a unified-resolution image.

[0007] Further, a plurality of sliced images are cut out from the initial image along the edge part, and the method is as follows: taking the center of the initial image as the starting point, advancing the cutting towards the edge of the initial image, and keeping the cutting path consistent with the gradient direction of the resolution change.

[0008] Further, the size of the sliced image is dynamically adjusted according to the resolution change amplitude at its location; among them, the size of the sliced image in the central area is larger than that in the edge area.

[0009] Further, the super-resolution reconstruction model includes a shallow feature extraction module, a deep feature extraction module, and a reconstruction module connected in sequence; The shallow feature extraction module extracts primary features through single-layer convolution operation; The deep feature extraction module is composed of a plurality of cascaded residual dense blocks, each residual dense block contains a plurality of cascaded residual dense attention modules, the residual dense attention module includes a plurality of sequentially connected convolutional layers and one spatial attention module, and adjacent residual dense attention modules are connected through layer normalization operation; The output of the spatial attention module is added to the input of the residual dense attention module through residual connection; The input of the deep feature extraction module is the primary feature output by the shallow feature extraction module, and the output of the deep feature extraction module is the deep feature; The reconstruction module fuses the primary feature and the deep feature, and after fusion, performs upsampling processing on the fused feature through the nearest neighbor interpolation method to generate the final high-resolution image.

[0010] Further, the execution process of the spatial attention module includes: Performing depth convolution and pointwise convolution on the input feature map in sequence to generate a spatial attention weight map; multiplying the spatial attention weight map with the input feature map channel by channel, and outputting the weighted feature map.

[0011] Further, in step S3, geometric correction processing is performed on the sliced images with unified resolution, and all sliced images are corrected to the same coordinate system, and the method is as follows: Step S31, constructing a rigorous imaging geometric model of the satellite remote sensing image; Step S32, based on each sliced image, judging whether the elevation value of the target point can be obtained. If so, jump to step S33, otherwise jump to step S34; Step S33, based on the rigorous imaging geometric model, given the sliced image coordinates, camera parameters, satellite orbit parameters, and the elevation value of the target point, obtaining the object plane coordinates of each target point in the sliced image through solving the model equation, as the corrected coordinates; Step S34: Using the local average elevation of the area covered by the sliced image as the initial value, calculate the initial longitude and latitude. Interpolate the elevation value corresponding to the initial longitude and latitude in the DEM data, and substitute it into the imaging geometric positioning model for iterative calculation to obtain the longitude, latitude, and elevation values of the sliced image, and then jump to step S33.

[0012] Furthermore, substitute it into the imaging geometric positioning model for iterative calculation until the results of two adjacent iterations are less than the preset threshold, and then obtain the longitude, latitude, and elevation values of the sliced image.

[0013] Furthermore, perform weighted fusion processing on the overlapping areas of the geometrically corrected sliced images. The method is as follows: Step S41: For any pixel P in the overlapping area, dynamically assign weights according to its distance from the centers of adjacent sliced images; Step S42: Calculate the pixel of point P based on the weight assignment: ; Among them, the two sliced images corresponding to the overlapping area where point P is located are respectively defined as image A and image B; is the pixel value of image A at the position of point P, is the pixel value of image B at the position of point P, is the weight of image A for the pixel of point P, is the weight of image B for the pixel of point P.

[0014] Furthermore, the weight , and its calculation method is: ; Among them, , are the distances from point P to the right edge and the lower edge of image A, , are the distances from point P to the left edge and the upper edge of image B.

[0015] Furthermore, the weight , and its calculation method is: ; Among them, , are the distances from point P to the right edge and the lower edge of image A, , are the distances from point P to the left edge and the upper edge of image B.

[0016] Advantages of the present invention: Resolution Adaptive Cropping Mechanism: By means of a radial cropping method starting from the center of the image and dynamically adjusting the patch size in combination with the resolution change range, it avoids the loss of detailed information caused by global downsampling / upsampling in traditional resampling methods, preserves the resolution distribution characteristics of the original image at the cropping stage, and provides a data basis for subsequent processing.

[0017] Region-based Super-resolution Reconstruction: Implement super-resolution processing for low-resolution edge patches in a targeted manner, and use a deep learning model to restore high-frequency texture details. While improving the resolution, it effectively maintains the visual quality of the image, overcoming the problem of image blurring caused by a single resampling operation.

[0018] Geometric Consistency Correction: Through a geometric correction algorithm based on the extraction of extreme values in the map coordinate system, it eliminates the image deformation caused by the earth's curvature and sensor distortion, ensures the spatial alignment accuracy of all patch images in a unified coordinate system, and provides a geometric basis for seamless stitching.

[0019] Intelligent Weight Fusion Technology: Based on the weight assignment principle of the distance from the center of the patch image, it realizes pixel-level smooth transition in the overlapping area, significantly reduces the visibility of the stitching seam, and at the same time maintains the tonal consistency of the full-frame image, avoiding the color jump problem caused by traditional stitching methods. Description of the Drawings

[0020] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objectives, and advantages of the present application will become more obvious: Figure 1 It is a schematic flowchart of a method for unifying the resolution of variable-resolution images according to the present invention; Figure 2 It is a schematic diagram of the weighted fusion process in a method for unifying the resolution of variable-resolution images according to the present invention. Detailed Embodiment

[0021] The following further details the present application in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention and are not a limitation to the invention. Additionally, it should be noted that for the sake of description, only parts related to the invention are shown in the drawings.

[0022] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The following will detail the present application with reference to the drawings and embodiments.

[0023] The present invention provides a method for unifying the resolution of variable-resolution images, which includes the following steps: Step S1: Obtain the remotely sensed image with variable resolution to be unified as the initial image. Starting from the center of the initial image, based on the variation amplitude of the resolution from the center to the edge, cut out multiple patch images along the edge of the initial image, and ensure that there is an overlapping area between adjacent patch images. Step S2: Use the patch image corresponding to the low-resolution area as the input data and input it into the pre-constructed and trained super-resolution reconstruction model to obtain a high-resolution patch image with the same resolution as the patch image at the center. Step S3: Perform geometric correction on the patch images with unified resolution and correct all patch images into a unified coordinate system. Step S4: Perform weighted fusion on the overlapping areas of the geometrically corrected patch images, and achieve seamless stitching with consistent tone based on the weight distribution principle of the distance from the center of the patch image to generate an image with unified resolution.

[0024] For a clearer description of a method for unifying the resolution of variable-resolution images according to the present invention, the following is combined with Figure 1 Expand and detail each step in the embodiments of the present invention.

[0025] A method for unifying the resolution of variable-resolution images according to the first embodiment of the present invention includes steps S1 - S4, and each step is described in detail as follows: Step S1: Obtain the remotely sensed image with variable resolution to be unified as the initial image. Starting from the center of the initial image, based on the variation amplitude of the resolution from the center to the edge, cut out multiple patch images along the edge of the initial image, and ensure that there is an overlapping area between adjacent patch images. Specifically, the method of cutting out multiple patch images along the edge of the initial image is as follows: Starting from the center of the initial image, push forward the cutting towards the edge of the initial image, and the cutting path is consistent with the direction of the resolution change gradient.

[0026] The size of the patch image is dynamically adjusted according to the variation amplitude of the resolution at its location; among them, the size of the patch image in the central area is larger than that in the edge area. Specifically, the size cutting method is as follows: ; ; Among them, k represents the spatial resolution of the pixel point at the edge of the cut image (close to the center position of the entire variable-resolution remotely sensed image). If the spatial resolution of this point is not an integer multiple, it is rounded to an integer by the rounding method; W and H respectively represent the width and height of the cut image in the variable-resolution remotely sensed image when the resolution is fixed at 1 meter. 、 respectively represent the actual width and height of the cropped image.

[0027] In this embodiment, various existing open-source software is used to crop a variable-resolution image. When cropping, it is necessary to crop according to the resolution. That is, for a variable-resolution image, the spatial resolution decreases from 1m to 4m in sequence from the middle to the edge. Therefore, when cropping, attention should be paid to the resolution of the original image so that the resolutions on both sides of the cropped piecewise image are as close as possible. Since the resolution of the variable-resolution image changes in an exponential curve from the center to the edge, this means that in the area close to the center of the image, the change in spatial resolution is relatively slow. Therefore, the size of the image cropped from this area is relatively large.

[0028] On the contrary, as we gradually approach the edge of the image, the change speed of the spatial resolution accelerates. Correspondingly, the size of the image cropped from these areas will be relatively small. This characteristic of resolution change requires that when processing variable-resolution images, appropriate cropping should be performed according to different resolution areas to ensure that the resolutions of all piecewise images after subsequent super-resolution reconstruction are consistent. At the same time, a certain overlapping area should be designed during cropping to facilitate the splicing and fusion of subsequent images.

[0029] Step S2: Use the piecewise image corresponding to the low-resolution area as input data and input it into a pre-constructed and trained super-resolution reconstruction model to obtain a high-resolution piecewise image with the same resolution as the central piecewise image; The super-resolution reconstruction model includes a shallow feature extraction module, a deep feature extraction module, and a reconstruction module connected in sequence; The shallow feature extraction module extracts primary features through single-layer convolution operations; it can efficiently extract preliminary feature information from the input image and lay a foundation for subsequent feature processing and reconstruction tasks; The deep feature extraction module is composed of multiple cascaded residual dense blocks. Each residual dense block contains multiple cascaded residual dense attention modules. The residual dense attention module includes multiple sequentially connected convolutional layers and 1 spatial attention module, and adjacent residual dense attention modules are connected through layer normalization operations; The output of the spatial attention module is added to the input of the residual dense attention module through a residual connection; The input of the deep feature extraction module is the primary feature output by the shallow feature extraction module, and the output of the deep feature extraction module is the deep feature; The reconstruction module fuses the primary feature and the deep feature, and after fusion, performs upsampling processing on the fused feature through the nearest neighbor interpolation method to generate the final high-resolution image.

[0030] Specifically, in this embodiment, the deep feature extraction module is composed of 10 cascaded residual dense blocks. Each residual dense block contains 3 cascaded residual dense attention modules. The residual dense attention module includes 4 sequentially connected convolutional layers and 1 spatial attention module, and adjacent residual dense attention modules are connected through layer normalization operations; In this embodiment, the batch normalization (BN) layer in the traditional DenseBlock is removed because the BN layer often introduces artifacts, thus affecting the quality of the reconstructed image. Instead, layer normalization (LN) is introduced between two residual dense attention modules to reduce the computational complexity of the model and improve the training speed. In this way, while retaining the powerful feature extraction ability of the residual dense block, the RDAB further optimizes the performance of the model. In addition, the residual dense block (RDB) originally composed of 5 convolutional layers is improved to be composed of 4 convolutional layers and 1 spatial attention module. Each convolutional layer uses a 3×3 convolutional kernel, with a stride of 1 and a padding of 1, and is followed by a ReLU activation function after each layer.

[0031] The spatial attention module is mainly implemented based on depthwise separable convolution, which is composed of depthwise convolution (DWConv) and pointwise convolution (PWConv). First, the depthwise convolution performs convolution operations on each channel independently, retaining rich local features; subsequently, the pointwise convolution combines the features of all channels into the output feature map. This design not only reduces the computational complexity but also improves the overall performance of the network, making the model more efficient and stable when processing inputs of different resolutions: The execution process of the spatial attention module includes: The number of channels is doubled through 1×1 convolution and the features are divided into two parts. One part serves as the gating feature, which is processed by 7×7 depthwise separable convolution to capture large-range spatial information; the other part serves as the main feature. The main feature is multiplied by the processed gating feature to achieve feature modulation. Finally, the number of feature channels is compressed back to the original size through 1×1 convolution.

[0032] The depthwise convolution and pointwise convolution are sequentially performed on the input feature map to generate the spatial attention weight map; the spatial attention weight map is multiplied by the input feature map channel by channel to output the weighted feature map : ; wherein, is the depthwise convolution, It is point-by-point convolution, A is the gated feature, and B is the main feature.

[0033] Among them, the magnification ratio of the upsampling layer is dynamically determined by the resolution difference between the edge region and the central region to ensure that the output image resolution is consistent with the spatial resolution at the sub-satellite point.

[0034] Step S3: Perform geometric correction on the segmented images with unified resolution, and correct all segmented images into a unified coordinate system: Step S31: Construct a rigorous imaging geometric model for satellite remote sensing images; Specifically, the satellite remote sensing image uses the rigorous imaging geometric model to calculate the object space position of the image point, and its geometric positioning model: ; In the formula, is the ground point coordinate, represents the position of the projection center measured by GPS at the imaging moment, which is a scale factor, represents the transformation matrix from the satellite body coordinate system to the J2000 coordinate system, represents the transformation matrix from the J2000 coordinate system to the WGS84 coordinate system, represents the transformation matrix from the sensor coordinate system to the satellite body coordinate system, is the coordinate of the object space vector in the sensor coordinate system, is the projection center offset vector, is the focal plane distortion, is the focal length of the camera x , y is the coordinate of the image point on the sensor imaging plane After the pixel coordinates (I, J) of the target point in the segmented image are obtained, the scan line number is determined from the pixel coordinates, and the imaging moment is obtained according to the auxiliary data. Further, the position and attitude at the imaging moment of the scan line are obtained by the satellite position and attitude interpolation method.

[0035] Step S32: Based on each segmented image, determine whether the elevation value of the target point can be obtained. If so, jump to step S33; otherwise, jump to step S34; Step S33: Based on the rigorous imaging geometric model, given the segmented image coordinates, camera parameters, satellite orbit parameters, and the elevation value of the target point, the object space plane coordinates of each target point in the segmented image are obtained by solving the model equation as the corrected coordinates ; Step S34: Using the local average elevation of the area covered by the fragmented image as the initial value, calculate the initial longitude and latitude. Interpolate the elevation value corresponding to the initial longitude and latitude in the DEM data, and substitute it into the imaging geometric positioning model for iterative calculation until the results of two adjacent iterations are less than the preset threshold, then obtain the longitude, latitude, and elevation values of the fragmented image. , and jump to step S33.

[0036] After forward and inverse coordinate transformation and gray resampling, all images are corrected to a unified coordinate system. The prerequisite for splicing is to correct the images to a unified coordinate system, and then ensure that the contrast of the spliced images is consistent, the tones are similar, and there are no obvious seams. Therefore, the operation of step S4 is performed.

[0037] Step S4: Perform weighted fusion processing on the overlapping areas of the geometrically corrected fragmented images, and achieve seamless splicing with consistent tones based on the weight distribution principle of the distance from the center of the fragmented images, and generate an image with a unified resolution.

[0038] Since all variable-resolution images are derived from the same parent variable-resolution image, the color differences between slices are relatively small. In the splicing process, this solution uses the method of weighted summation to process the overlapping areas to ensure the coherence of tones. Specifically, for any pixel point in the overlapping area, the weight distribution principle is: the closer to the center point of an image, the higher the weight of this image at this pixel point; conversely, the image farther away is given a lower weight. Through this weighted fusion technology, the tones of the spliced image are finally consistent.

[0039] Refer to Figure 2 Example, if you want to determine the pixel value at the position of point P, first determine that the rectangular frame of the spliced image is composed of the right edge and the lower edge of image A, and the left edge and the upper edge of image B. It is known that the distance from point P to the right edge of image A is , and the distance from the upper edge is ; the distance from the left edge of image B is , and the distance from the upper edge is .

[0040] Specifically, the method of performing weighted fusion processing on the overlapping areas of the geometrically corrected fragmented images is as follows: Step S41: For any pixel point P in the overlapping area, dynamically allocate weights according to its distance from the centers of adjacent fragmented images; Step S42: Calculate the pixel of point P based on the weight distribution: ; Among them, the two fragmented images corresponding to the overlapping area where point P is located are respectively defined as image A and image B; is the pixel value of image A at the position of point P, is the pixel value of Image B at position P, is the weight of Image A for the pixel at point P, is the weight of Image B for the pixel at point P.

[0041] The weights and weights , and their calculation method is: ； ; wherein, 、 are the distances from point P to the right and lower edges of Image A, 、 are the distances from point P to the left and upper edges of Image B.

[0042] After super-resolution reconstruction, geometric correction, and image mosaicking, a variable-resolution image with the same resolution as the sub-satellite point resolution can be obtained.

[0043] Although the steps are described in the above order in the above embodiments, those skilled in the art can understand that in order to achieve the effects of this embodiment, different steps do not have to be executed in such an order, and they can be executed simultaneously (in parallel) or in a reversed order, and these simple changes are within the protection scope of the present invention.

[0044] A variable-resolution image resolution unification system according to the second embodiment of the present invention is based on a variable-resolution image resolution unification method according to the first embodiment. The system includes: An image cropping module configured to obtain a remote sensing image with a variable resolution to be unified as an initial image, and starting from the center of the initial image, based on the change range of the resolution from the center to the edge, crop out multiple piece images along the edge part of the initial image, and ensure that there is an overlapping area between adjacent piece images; A resolution unification module configured to use the piece image corresponding to the low-resolution area as input data and input it into a pre-constructed and trained super-resolution reconstruction model to obtain a high-resolution piece image with the same resolution as the piece image at the center; A coordinate unification module configured to perform geometric correction processing on the piece images after resolution unification and correct all piece images into a unified coordinate system; A stitching module configured to perform weighted fusion processing on the overlapping regions of the geometrically corrected fragmented images, and achieve seamless stitching with consistent tone based on the weight assignment principle of the distances from the centers of the fragmented images, so as to generate an image with a unified resolution. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes and related explanations of the above-described system can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0045] It should be noted that the variable-resolution image resolution unification system provided in the above embodiment is only illustrated by dividing the above function modules. In practical applications, the above functions can be assigned to different function modules according to needs, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further split into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only used to distinguish each module or step, and are not regarded as an improper limitation of the present invention.

[0046] An electronic device according to the third embodiment of the present invention includes: At least one processor; and A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned variable-resolution image resolution unification method.

[0047] A computer-readable storage medium according to the fourth embodiment of the present invention, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned variable-resolution image resolution unification method.

[0048] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes and related explanations of the above-described storage device and processing device can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0049] Those skilled in the art should be able to realize that the modules and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. The programs corresponding to the software modules and method steps can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the technical field. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0050] The terms "first", "second", etc. are used to distinguish similar objects, rather than to describe or represent a specific order or sequence.

[0051] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, so that a process, method, article, or device / equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent in these processes, methods, articles, or devices / equipment.

[0052] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for unifying the resolution of variable-resolution images, characterized in that: The method comprises the following steps: Step S1, obtaining a remote sensing image to be uniformly changed in resolution as an initial image, taking the center of the initial image as a starting point, and based on the resolution change range from the center to the edge, cutting the initial image along the edge portion into a plurality of slice images, and ensuring that there are overlapping areas between adjacent slice images; Step S2, taking the slice image corresponding to the low-resolution area as input data and inputting it into a pre-built and trained super-resolution reconstruction model to obtain a high-resolution slice image with the same resolution as the slice image at the center; Step S3, performing geometric correction processing on the tile images with unified resolution, and correcting all the tile images to a unified coordinate system; Step S4, weighted fusion processing is performed on the overlapping areas of the geometrically corrected tile images, and seamless stitching with consistent tones is achieved based on the weight distribution principle of the center distance of the tile images to generate a uniform resolution image.

2. The method for unifying the resolution of variable-resolution images according to claim 1, characterized in that: The initial image is cut out along the edge portion to obtain a plurality of fragmented images, wherein the method is as follows: starting from the center of the initial image, the cutting is advanced toward the edge of the initial image, and the cutting path is consistent with the direction of the resolution change gradient.

3. The method for unifying the resolution of variable-resolution images according to claim 1, characterized in that: The size of the slice image is dynamically adjusted according to the resolution change range of the location; wherein the size of the slice image in the central area is larger than the size of the slice image in the edge area.

4. The method for unifying the resolution of variable-resolution images according to claim 1, characterized in that: The super-resolution reconstruction model includes a shallow feature extraction module, a deep feature extraction module and a reconstruction module connected in sequence; The shallow feature extraction module extracts primary features through a single-layer convolution operation; The deep feature extraction module is composed of a plurality of residual dense blocks connected in series, each residual dense block contains a plurality of cascaded residual dense attention modules, the residual dense attention module includes a plurality of convolutional layers connected in sequence and a spatial attention module, and adjacent residual dense attention modules are connected through a layer normalization operation; The output of the spatial attention module is added to the input of the residual dense attention module through a residual connection; The input of the deep feature extraction module is the primary feature output by the shallow feature extraction module, and the output of the deep feature extraction module is the deep feature; The reconstruction module fuses the primary features and the deep features, and after fusion, upsamples the fused features using a nearest neighbor interpolation method to generate a final high-resolution image.

5. The method for unifying the resolution of variable-resolution images according to claim 4, characterized in that: The execution process of the spatial attention module includes: The input feature map is sequentially subjected to depth convolution and point-by-point convolution to generate a spatial attention weight map; the spatial attention weight map is multiplied channel by channel with the input feature map, and a weighted feature map is output.

6. The method for unifying the resolution of variable-resolution images according to claim 1, characterized in that: In step S3, geometric correction is performed on the tile images with unified resolution to correct all tile images to a unified coordinate system. The method is as follows: Step S31, constructing a rigorous imaging geometry model of the satellite remote sensing image; Step S32, based on each slice image, determine whether the elevation value of the target point can be obtained, if yes, jump to step S33, otherwise jump to step S34; Step S33, based on the rigorous imaging geometry model, given the slice image coordinates, camera parameters, satellite orbit parameters and target point elevation values, the object plane coordinates of each target point in the slice image are obtained by solving the model equation as the corrected coordinates; Step S34, using the local average elevation of the area covered by the slice image as the initial value, calculate the initial longitude and latitude, interpolate the elevation values ​​corresponding to the initial longitude and latitude in the DEM data, and substitute them into the imaging geometry positioning model for iterative calculation to obtain the longitude and latitude and elevation values ​​of the slice image, and jump to step S33.

7. The method for unifying the resolution of variable-resolution images according to claim 6, characterized in that: Substitute the imaging geometric positioning model for iterative calculation until the results of two adjacent iterations are less than the preset threshold, and then obtain the longitude, latitude and elevation values ​​of the segmented image.

8. The method for unifying the resolution of variable-resolution images according to claim 1, characterized in that: The overlapping areas of the geometrically corrected tiled images are weighted fused using the following method: Step S41, for a pixel at any point P in the overlapping area, dynamically assign a weight according to its distance from the center of the adjacent slice image; Step S42, calculate the pixels of point P based on weight distribution: ； The two slice images corresponding to the overlapping area where point P is located are defined as image A and image B respectively; is the pixel value of image A at point P, is the pixel value of image B at point P, is the weight of image A for point P pixel, is the weight of image B for the pixel at point P.

9. The method for unifying the resolution of variable-resolution images according to claim 8, characterized in that: The weight , which is calculated as: ； in, , is the distance from point P to the right and bottom edges of image A, , is the distance from point P to the left and top edges of image B.

10. The method for unifying the resolution of variable-resolution images according to claim 8, characterized in that: The weight , which is calculated as: ； in, , is the distance from point P to the right and bottom edges of image A, , is the distance from point P to the left and top edges of image B.

Images