Remote sensing image processing method, device, electronic equipment and storage medium

Abstract

The present invention relates to a remote sensing image processing method, device, electronic device and storage medium, the method comprising: obtaining a first remote sensing image and a second remote sensing image, the first remote sensing image and the second remote sensing image being two images of the same geographical area taken at different time periods or at different angles; forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, the boundary size of the graphic array being no greater than the size of the first remote sensing image; based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image; distorting and transforming the second remote sensing image based on the multiple target image blocks, and superimposing the second remote sensing image with the first remote sensing image. The present invention can better handle the ghosting problem, reduce the amount of searching, and reduce the amount of calculation.

Description

Technical Field

[0001] The present invention relates to the field of geographic remote sensing technology, and in particular to a remote sensing image processing method, device, electronic equipment and storage medium. Background Art

[0002] Geographic remote sensing is a technology that obtains information about the earth's surface through remote sensing equipment such as satellites and aircraft. Image stitching is a commonly used technology in geographic remote sensing. Image stitching refers to stitching multiple local images into a larger image, or stitching multiple local remote sensing images into a panoramic image. Image stitching technology is widely used in the field of geographic remote sensing and can provide more comprehensive and detailed geographic information. The ghosting problem in image stitching is one of the common challenges, especially when stitching images from different time periods or different shooting angles. To reduce the ghosting problem, a panoramic stitching algorithm can be used, such as the SIFT (Scale-invariant feature transform) algorithm, which can better handle the ghosting area, but its computational complexity is large. Summary of the invention

[0003] Based on this, it is necessary to provide a remote sensing image processing method, device, electronic device and storage medium that can better process ghosting areas and has a small amount of calculation to address the above technical problems.

[0004] The present invention provides a remote sensing image processing method, the method comprising:

[0005] Acquire a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles;

[0006] Forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, wherein the boundary size of the graphic array is not greater than the size of the first remote sensing image;

[0007] Based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image;

[0008] The second remote sensing image is warped and transformed based on the multiple target image blocks, and is superimposed with the first remote sensing image.

[0009] In one embodiment, the acquiring of the first remote sensing image and the second remote sensing image includes:

[0010] Preprocessing the first remote sensing image and the second remote sensing image respectively, and making the similarity between the edge feature of the first remote sensing image and the edge feature of the second image greater than a first threshold;

[0011] The first remote sensing image and the second remote sensing image are simulated and superimposed, and the ghost ratio of the simulated superimposed image is made smaller than a second threshold value.

[0012] In one embodiment, the forming of the same graphic array on the first remote sensing image and the second remote sensing image respectively, and separating each graphic into a basic image block, comprises:

[0013] Drawing uniform square grids on the first remote sensing image and the second remote sensing image respectively;

[0014] Graphics of equal specifications are drawn at each intersection point of the square grid to form the graphic array, and the size of the graphics is smaller than the size of the square grid in the square grid.

[0015] In one embodiment, the step of searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image based on the multiple basic image blocks separated by the graphic array on the first remote sensing image comprises:

[0016] Using the positions of the graphics in the graphic arrays on the first remote sensing image and the second remote sensing image as references and the edges of each graphic on the second remote sensing image as search tracks, searching for target image blocks having the same image features as the basic image blocks separated by the corresponding graphics on the first remote sensing image according to a preset search radius;

[0017] In response to a failure in searching for the target image block, the size of the pattern in the pattern array is enlarged and the search is repeated.

[0018] In one of the embodiments, the step of searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image based on the multiple basic image blocks separated by the graphic array on the first remote sensing image further includes:

[0019] In response to the successful search for the target image block, calculating the offset of the target image block from the corresponding graphic position;

[0020] In response to the offset being less than a third threshold, the corresponding target image block, graphic position and offset are recorded.

[0021] In one embodiment, in response to the successful search for the target image block, calculating the offset of the target image block from the corresponding graphic position, and then further comprising:

[0022] In response to the offset being greater than a fourth threshold, the corresponding target image block is discarded.

[0023] In one embodiment, the warping and transforming the second remote sensing image based on the multiple target image blocks and superimposing the second remote sensing image with the first remote sensing image includes:

[0024] Generate an image offset table based on the recorded target image blocks, and the corresponding graphic positions and offsets;

[0025] According to the image offset table, the target image block on the second remote sensing image is distorted to the corresponding graphic position, and the images other than the target image block are naturally distorted along with the target image block;

[0026] The transformed image obtained by the distortion transformation is superimposed on the first remote sensing image.

[0027] The present invention also provides a remote sensing image processing device, the device comprising:

[0028] An acquisition module, used to acquire a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles;

[0029] A separation module, used to form the same graphic array on the first remote sensing image and the second remote sensing image respectively, and separate a basic image block from each graphic, wherein the boundary size of the graphic array is equivalent to the size of the first remote sensing image;

[0030] A search module, configured to search for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image, based on the multiple basic image blocks separated by the graphic array on the first remote sensing image;

[0031] The transformation module is used to distort and transform the second remote sensing image based on multiple target image blocks, and superimpose the second remote sensing image with the first remote sensing image.

[0032] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above-mentioned remote sensing image processing methods when executing the computer program.

[0033] The present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any of the remote sensing image processing methods described above.

[0034] The above remote sensing image processing method, device, electronic device and storage medium use a graphic array to separate basic image blocks, and each basic image block is evenly distributed. The searched target image blocks are evenly distributed, and the connection during distortion transformation is good, which can reduce the excessive deformation and distortion of the image caused by distortion transformation, avoid the ghost caused by distortion transformation is difficult to eliminate or new ghost is generated, and can better handle the ghost problem. At the same time, the image block separated by the graphic array is only a part of the entire remote sensing image, and an image block on one remote sensing image only searches for the target image block near the corresponding graphic of the graphic array on another remote sensing image, which greatly reduces the search amount and reduces the amount of calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to 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.

[0036] Figure 1 A flow chart of a remote sensing image processing method according to an embodiment of the present invention;

[0037] Figure 2 A flow chart of a remote sensing image processing method according to another embodiment of the present invention;

[0038] Figure 3 A flow chart of a remote sensing image processing method according to another embodiment of the present invention;

[0039] Figure 4 This is a flow chart of a remote sensing image processing method according to yet another embodiment of the present invention.

[0040] Figure 5 The figure is a schematic diagram of a remote sensing image processing device according to an embodiment of the present invention.

[0041] Figure 6 The figure is a diagram showing the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Geographic remote sensing is a technology that obtains information about the earth's surface through remote sensing equipment such as satellites and aircraft. Image stitching is a commonly used technology in geographic remote sensing. Image stitching refers to stitching multiple local images into a larger image, or stitching multiple local remote sensing images into a panoramic image. Image stitching technology is widely used in the field of geographic remote sensing and can provide more comprehensive and detailed geographic information. The ghosting problem in image stitching is one of the common challenges, especially when stitching images from different time periods or different shooting angles. The ghosting problem may occur at the boundary of the object, in areas with low texture richness, or when there is large movement in the stitching scene. To reduce the ghosting problem, a panoramic stitching algorithm, such as the SIFT (Scale-invariant feature transform) algorithm, can be used, which can better handle the ghosting area, but its computational complexity is large. In order to solve the ghosting problem in the stitching process of remote sensing images, a remote sensing image processing method, device, electronic device and storage medium are provided.

[0044] Combine the following Figure 1-Figure 6 The invention describes a remote sensing image processing method, device, electronic device and storage medium.

[0045] like Figure 1 As shown, in one embodiment, a remote sensing image processing method includes the following steps:

[0046] Step S110, obtaining a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles.

[0047] Images taken at different times will generally appear different due to the presence of moving objects or people in the scene. Two images taken at different angles will also have parallax. Therefore, in order to avoid ghosting after the two images are synthesized, processing is required before superposition.

[0048] First, the images need to be processed before stacking. The first remote sensing image and the second remote sensing image need to be preprocessed respectively, and the similarity between the edge features of the first remote sensing image and the edge features of the second image should be greater than the first threshold. The two images are preliminarily processed, such as cropping, so that the size of the parts to be stacked is the same, and the similarity of the edge features (such as texture and color) of the two images is high. The first threshold can be set as a reference. The larger the first threshold, the higher the requirement for the similarity of the edge features of the two images.

[0049] The first remote sensing image and the second remote sensing image are simulated and superimposed, and the ghosting ratio of the simulated superimposed image is made less than the second threshold. The purpose of simulated superposition is mainly to verify the effect of the pre-processing of superposition and to determine whether the selected first remote sensing image and the second remote sensing image are superimposable. The two images to be superimposed have the same shooting scene and high similarity, and the only difference is the shooting angle or shooting time difference. If the two images are screened for the maximum similarity (the maximum value of the first threshold value that can be selected) during the pre-processing of superposition, and the ghosting ratio is still greater than the second threshold during the simulated superposition, it may be that the selected first remote sensing image and the second remote sensing image are not suitable and the difference is large. In other words, the first remote sensing image and the second remote sensing image are not superimposable and the image needs to be reselected.

[0050] Step S120, forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, and the boundary size of the graphic array is not greater than the size of the first remote sensing image.

[0051] The graphics in the graphic array can be square, circular, triangular, etc. The graphics in each graphic array have the same shape and size, and the spacing between the graphics is the same. The boundary of the graphic array is the boundary formed by connecting the outer edges of multiple graphics at the edge of the array. When setting the graphic array, the graphic array evenly separates the first remote sensing image and the second remote sensing image respectively. As an option, the boundary size of the graphic array is the same as the size of the first remote sensing image or the second remote sensing image. The graphic array is a rectangular array or a circular array.

[0052] Step S130 , based on the multiple basic image blocks separated by the pattern array on the first remote sensing image, search for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding patterns of the pattern array on the second image.

[0053] Among them, the image features are texture features and / or color features, including the roughness, direction, frequency, etc. of the texture in the graphics, as well as the color distribution and color information in the image. After the graphic array is separated for any one of the first remote sensing image and the second remote sensing image, each basic image block separated by the graphic theoretically has an image area (target image block) corresponding to its image feature in the other image, but the position is slightly changed. Therefore, two completely identical graphic arrays are formed on the two images, one of which is used to select the basic image block, and the other is used as a position reference for searching the target image block, which can quickly and accurately locate the target image block corresponding to the image feature of the selected basic image block, and because the multiple basic image blocks are only part of the entire remote sensing image, the search amount and the amount of calculation are also reduced.

[0054] Step S140: warping the second remote sensing image based on the multiple target image blocks and superimposing the second remote sensing image with the first remote sensing image.

[0055] Optionally, after searching for the corresponding target image block in the second remote sensing image according to each basic image block in the graphic array on the first remote sensing image, a position deviation can be obtained according to the positional relationship between the multiple target image blocks and the corresponding graphic array on the second remote sensing image, and the second remote sensing image is distorted and transformed according to the position deviation so that each target image block falls into the graphic in the corresponding graphic array, and finally the first remote sensing image and the second remote sensing image are superimposed, and the superimposed image is an image without ghosting. In addition, the graphics in the graphic array are evenly distributed, so that the separated basic image blocks are more evenly distributed, and the smoothness of each target image block in the second remote sensing image during the distortion transformation process is better when it is transformed to the corresponding graphic in the graphic array, which can reduce the excessive deformation and distortion of the image caused by the distortion transformation.

[0056] The remote sensing image processing method of this embodiment uses a graphic array to separate basic image blocks, and each basic image block is evenly distributed. The searched target image blocks are evenly distributed, and the connection during the distortion transformation is good, which can reduce the excessive deformation and distortion of the image caused by the distortion transformation, avoid the ghost caused by the distortion transformation is difficult to eliminate or new ghost is generated, and can better handle the ghost problem. At the same time, the image block separated by the graphic array is only a part of the entire remote sensing image, and an image block on one remote sensing image only searches for the target image block near the corresponding graphic of the graphic array on another remote sensing image, which greatly reduces the search amount and reduces the amount of calculation.

[0057] like Figure 2 As shown, in one embodiment, forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and separating each graphic into a basic image block, includes the following steps:

[0058] Step S122: uniform square grids are drawn on the first remote sensing image and the second remote sensing image respectively.

[0059] Step S124, drawing graphics of the same specifications at each intersection point of the square grid to form a graphic array, wherein the size of the graphics is smaller than the size of the square grid in the square grid.

[0060] By drawing a square grid, the size of the formed graphic array and the graphic size are more closely matched to the remote sensing image, and the center of the graphic array is conveniently located at the center of the remote sensing graphic. At the same time, when the remote sensing image is distorted and transformed, the square grid also helps to observe the smoothness of the transformation, so that abnormal deformation can be handled in time.

[0061] like Figure 3As shown, in one embodiment, based on a plurality of basic image blocks separated by a pattern array on a first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding patterns of the pattern array on a second image respectively includes the following steps:

[0062] Step S132, using the graphic positions in the graphic arrays on the first remote sensing image and the second remote sensing image as references, using the edge of each graphic on the second remote sensing image as a search trajectory, and searching for target image blocks having the same image features as the basic image blocks separated by the corresponding graphics on the first remote sensing image according to a preset search radius.

[0063] Using the graphic arrays on the two remote sensing images as position references, a basic image block on the first remote sensing image is searched only at the corresponding graphic position in the graphic array on the second image. Multiple basic image blocks can be searched in parallel and synchronously to improve search efficiency.

[0064] Specifically, in the process of searching for the target image block based on the basic image block, in response to the successful search for the target image block, the offset of the target image block from the corresponding graphic position is calculated; in response to the offset being less than the third threshold, the corresponding target image block, graphic position and offset are recorded. In the scene of remote sensing graphics, the offset of static objects is generally small, and the offsets of different target image blocks are not much different. Optionally, the third threshold can be adjusted according to actual conditions so that 90% of the offsets are less than the third threshold.

[0065] In response to the offset being greater than a fourth threshold, the corresponding target image block is discarded. The fourth threshold is greater than the third threshold. In the scene of the remote sensing image, moving objects or people are also factors that cause ghosting. When the offset is too large, it is generally the moving objects or people that need to be distinguished from static objects, otherwise, deformation or distortion will occur during the distortion transformation. During the distortion transformation, the offset of the static object is mainly relied on, and the deviation of the moving object or person is discarded. Optionally, for the target image block whose offset is greater than the fourth threshold, the distortion transformation is abandoned, and it is also necessary to clarify to avoid the ghosting of the moving object or person when superimposed with the first remote sensing image.

[0066] Step S134, in response to a failure in searching the target image block, enlarging the size of the graphics in the graphics array and searching again.

[0067] When searching for a target image block, in order to reduce the amount of search, the graphic size in the initial graphic array is generally small, and the search radius is generally smaller than the graphic size. Therefore, a search failure may occur. The search is performed again by enlarging the graphic size until the search is successful.

[0068] like Figure 4As shown, in one embodiment, the second remote sensing image is distorted and transformed based on multiple target image blocks, and superimposed with the first remote sensing image, including the following steps:

[0069] Step S142: Generate an image offset table based on the recorded target image blocks, and the corresponding graphic positions and offsets.

[0070] The data in the image offset table is a set of offsets of all target image blocks whose offsets are less than a third threshold.

[0071] Step S144, according to the image offset table, the target image block on the second remote sensing image is distorted to the corresponding graphic position, and the images other than the target image block are naturally distorted along with the target image block.

[0072] Step S146: superimpose the transformed image obtained by the distortion transformation with the first remote sensing image.

[0073] It should be noted that the image on the second remote sensing image may also be used as a basic image block, and the first remote sensing image may be searched to obtain a target image block.

[0074] The remote sensing image processing device provided by the present invention is described below. The remote sensing image processing device described below and the remote sensing image processing method described above can be referred to each other.

[0075] like Figure 5 As shown, in one embodiment, a remote sensing image processing device includes an acquisition module 510, a separation module 520, a search module 530 and a transformation module 540.

[0076] The acquisition module 510 is used to acquire a first remote sensing image and a second remote sensing image, where the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles.

[0077] The separation module 520 is used to form the same graphic array on the first remote sensing image and the second remote sensing image respectively, and separate each graphic into a basic image block, and the boundary size of the graphic array is not greater than the size of the first remote sensing image.

[0078] The search module 530 is used to search for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image based on the multiple basic image blocks separated by the graphic array on the first remote sensing image.

[0079] The transformation module 540 is used to distort and transform the second remote sensing image based on the multiple target image blocks, and superimpose the second remote sensing image with the first remote sensing image.

[0080] Figure 6An example of a physical structure diagram of an electronic device is shown. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a remote sensing image processing method is implemented, and the method includes:

[0081] Acquire a first remote sensing image and a second remote sensing image, where the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles;

[0082] forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, and the boundary size of the graphic array is not greater than the size of the first remote sensing image;

[0083] Based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image;

[0084] The second remote sensing image is warped and transformed based on the multiple target image blocks, and is superimposed with the first remote sensing image.

[0085] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the electronic device to which the scheme of the present invention is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0086] On the other hand, the present invention also provides a computer storage medium storing a computer program, which implements a remote sensing image processing method when the computer program is executed by a processor, the method comprising:

[0087] Acquire a first remote sensing image and a second remote sensing image, where the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles;

[0088] forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, and the boundary size of the graphic array is not greater than the size of the first remote sensing image;

[0089] Based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image;

[0090] The second remote sensing image is warped and transformed based on the multiple target image blocks, and is superimposed with the first remote sensing image.

[0091] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, a remote sensing image processing method is implemented, the method comprising:

[0092] Acquire a first remote sensing image and a second remote sensing image, where the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles;

[0093] forming the same graphic array on the first remote sensing image and the second remote sensing image respectively, and making each graphic separate a basic image block, and the boundary size of the graphic array is not greater than the size of the first remote sensing image;

[0094] Based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image;

[0095] The second remote sensing image is warped and transformed based on the multiple target image blocks, and is superimposed with the first remote sensing image.

[0096] The above remote sensing image processing method, device, electronic device and storage medium use a graphic array to separate basic image blocks, and each basic image block is evenly distributed. The searched target image blocks are evenly distributed, and the connection during distortion transformation is good, which can reduce the excessive deformation and distortion of the image caused by distortion transformation, avoid the difficulty in eliminating ghost images or generating new ghost images caused by distortion transformation, and can better handle the ghost image problem. At the same time, the image blocks separated by the graphic array are only part of the entire remote sensing image, and an image block on one remote sensing image only searches for the target image block near the corresponding graphic of the graphic array on another remote sensing image, which greatly reduces the search amount and reduces the amount of calculation.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0098] By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A remote sensing image processing method, characterized in that: The method comprises: Acquire a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles; The same graphic array is formed on the first remote sensing image and the second remote sensing image respectively, and each graphic is separated into a basic image block, the boundary size of the graphic array is not larger than the size of the first remote sensing image, wherein uniform square grids are drawn on the first remote sensing image and the second remote sensing image respectively; graphics of the same specifications are drawn at each intersection point of the square grid respectively to form the graphic array, the size of the graphics is smaller than the size of the square grid in the square grid, the graphics in each graphic array are of the same shape and size, and the spacing between the graphics is the same; Based on the multiple basic image blocks separated by the graphic array on the first remote sensing image, searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near the corresponding graphics of the graphic array on the second image; The second remote sensing image is distorted and transformed based on the multiple target image blocks, and superimposed with the first remote sensing image, wherein a position deviation is obtained according to the positional relationship between the multiple target image blocks and the corresponding graphic array on the second remote sensing image, and the second remote sensing image is distorted and transformed according to the position deviation so that each target image block falls into a graphic in the corresponding graphic array, and then the first remote sensing image and the second remote sensing image are superimposed; The warping and transforming the second remote sensing image based on the multiple target image blocks and superimposing the second remote sensing image with the first remote sensing image includes: Generate an image offset table based on the recorded target image blocks, and the corresponding graphic positions and offsets; According to the image offset table, the target image block on the second remote sensing image is distorted to the corresponding graphic position, and the images other than the target image block are naturally distorted along with the target image block; The transformed image obtained by the distortion transformation is superimposed on the first remote sensing image.

2. The remote sensing image processing method according to claim 1, characterized in that: The acquiring of the first remote sensing image and the second remote sensing image comprises: Preprocessing the first remote sensing image and the second remote sensing image respectively, and making the similarity between the edge feature of the first remote sensing image and the edge feature of the second image greater than a first threshold; The first remote sensing image and the second remote sensing image are simulated and superimposed, and the ghost ratio of the simulated superimposed image is made smaller than a second threshold value.

3. The remote sensing image processing method according to claim 1, characterized in that: The method of searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image based on the multiple basic image blocks separated by the graphic array on the first remote sensing image comprises: Using the positions of the graphics in the graphic arrays on the first remote sensing image and the second remote sensing image as references and the edges of each graphic on the second remote sensing image as search tracks, searching for target image blocks having the same image features as the basic image blocks separated by the corresponding graphics on the first remote sensing image according to a preset search radius; In response to a failure in searching for the target image block, the size of the pattern in the pattern array is enlarged and the search is repeated.

4. The remote sensing image processing method according to claim 3, characterized in that: The method of searching for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image based on the multiple basic image blocks separated by the graphic array on the first remote sensing image also includes: In response to the successful search for the target image block, calculating the offset of the target image block from the corresponding graphic position; In response to the offset being less than a third threshold, the corresponding target image block, graphic position and offset are recorded.

5. The remote sensing image processing method according to claim 4, characterized in that: In response to the successful search for the target image block, calculating the offset of the target image block from the corresponding graphic position, and then further comprising: In response to the offset being greater than a fourth threshold, the corresponding target image block is discarded.

6. A remote sensing image processing device, characterized in that: The device comprises: An acquisition module, used to acquire a first remote sensing image and a second remote sensing image, wherein the first remote sensing image and the second remote sensing image are two images of the same geographical area taken at different time periods or at different angles; A separation module is used to form the same graphic array on the first remote sensing image and the second remote sensing image respectively, and to separate a basic image block from each graphic, wherein the boundary size of the graphic array is not greater than the size of the first remote sensing image, wherein uniform square grids are drawn on the first remote sensing image and the second remote sensing image respectively; graphics of equal specifications are drawn at each intersection of the square grids to form the graphic array, wherein the size of the graphics is smaller than the size of the square grid in the square grid, and the graphics in each graphic array have the same shape and size, and the spacing between the graphics is the same; A search module, configured to search for target image blocks having the same image features as the basic image blocks on the first remote sensing image near corresponding graphics of the graphic array on the second image, based on the multiple basic image blocks separated by the graphic array on the first remote sensing image; a transformation module, configured to distort and transform the second remote sensing image based on the plurality of target image blocks, and to superimpose the second remote sensing image with the first remote sensing image, wherein a position deviation is obtained according to a positional relationship between the plurality of target image blocks and a corresponding graphic array on the second remote sensing image, and the second remote sensing image is distorted and transformed according to the position deviation so that each target image block falls into a graphic in the corresponding graphic array, and then the first remote sensing image and the second remote sensing image are superimposed; The warping and transforming the second remote sensing image based on the multiple target image blocks and superimposing the second remote sensing image with the first remote sensing image includes: Generate an image offset table based on the recorded target image blocks, and the corresponding graphic positions and offsets; According to the image offset table, the target image block on the second remote sensing image is distorted to the corresponding graphic position, and the images other than the target image block are naturally distorted along with the target image block; The transformed image obtained by the distortion transformation is superimposed on the first remote sensing image.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the remote sensing image processing method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the remote sensing image processing method according to any one of claims 1 to 5 is implemented.

Images