Remote sensing image space-time fusion color correction method based on virtual low-resolution reconstruction

Abstract

The invention provides a remote sensing image space-time fusion color correction method based on virtual low-resolution reconstruction, and the method comprises the steps: obtaining a to-be-reconstructed original remote sensing image, and determining a corresponding reference image according to the features of the original remote sensing image; performing virtual low-resolution image reconstruction by using the original remote sensing image and the reference image to obtain a virtual low-resolution image; and based on the virtual low-resolution image, performing color correction processing on the original remote sensing image by adopting a space-time fusion strategy to obtain a uniform color result image. According to the method, a weighted space-time filtering mechanism is introduced into color correction processing, a virtual low-resolution image is generated as auxiliary data, time correlation, spatial proximity and spectral similarity among the virtual low-resolution image, an original image and a reference bottom image element are comprehensively considered, spectral similar pixels of a central pixel in a filtering window are utilized to participate in result operation, and the color correction accuracy is improved. And generating a result image with the detail features of the original image and the spectral features of the reference image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction. Background Art

[0002] In remote sensing image processing, in order to meet the needs of large-area remote sensing analysis, multiple images need to be mosaicked to synthesize images covering a large area in practical applications. However, affected by the season, lighting, atmospheric conditions and ground coverage, the colors of the images obtained in a large area are usually uneven, which directly affects the interpretation and use of mosaicked images. Therefore, in order to obtain high-quality large-scale images with clear details and consistent colors, it is urgent to coordinate the color consistency between images before mosaicking, eliminate the color differences between different images, and provide guarantees for the accuracy of subsequent visual interpretation, production of digital orthophotos and other applications.

[0003] Existing color correction methods can be roughly divided into three categories according to different correction principles: color grading methods based on histogram matching, color grading methods based on statistical parameters, and color grading methods based on reference base maps. The principle of the method based on histogram matching is simple and easy to implement. The histogram of the original image is directly mapped to the specified shape according to certain rules to achieve color adjustment. When the overall color deviation of the image is not large and there is no sudden change in brightness distribution, the overall color tone between images can be coordinated; the color grading method based on statistical parameters believes that the statistical parameters representing the color tone and brightness between images with balanced color distribution in a certain area should also be similar. Therefore, statistical characteristic parameters such as mean and variance are used as a bridge to transform the statistical parameters of multiple images in the area so that the colors tend to be consistent; while the color grading method based on reference base maps does not consider whether there are overlapping areas between adjacent images. It directly selects low-resolution images that cover the survey area and have uniform colors from existing historical images as references, and uses the correspondence between the reference image and the original image to build a model to perform color grading on the original image to be processed. However, the color uniformity method based on histogram matching and statistical parameters has certain limitations. It is more effective in small areas with small color differences between images. Although the color uniformity processing based on the reference base map can effectively reduce error accumulation and human intervention, it is easy to cause the loss of local detail information and degradation of quality characteristics of the image when adjusting and correcting color differences with global statistical parameters or overall models. Therefore, how to better balance color balance and detail clarity in the color uniformity process is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction, which is used to solve the defects in the prior art.

[0005] In a first aspect, the present invention provides a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction, comprising: Acquire an original remote sensing image to be reconstructed, and determine a corresponding reference image according to the characteristics of the original remote sensing image; Reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; Based on the virtual low-resolution image, a spatiotemporal fusion strategy is adopted to perform color correction processing on the original remote sensing image to obtain a uniform color result image.

[0006] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, an original remote sensing image to be reconstructed is obtained, and a corresponding reference image is determined according to the characteristics of the original remote sensing image, including: Downloading a low-resolution image with a corresponding measurement area and time period as the reference image from an open source network platform; Acquire images from historical achievement data processed by a data production unit as the reference images; An image with uniform color is selected from land satellite remote sensing images or images with a preset large width and processed as the reference image.

[0007] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, the virtual low-resolution image is reconstructed using the original remote sensing image and the reference image to obtain a virtual low-resolution image, comprising: Respectively determining the mean and variance in the normal distribution of the original remote sensing image, and determining the mean and variance in the normal distribution of the reference image; Based on the mean and variance in the normal distribution of the original remote sensing image and the mean and variance in the normal distribution of the reference image, a histogram mapping relationship between the grayscale value of the original remote sensing image and the grayscale value of the reference image is established; The virtual low-resolution image is obtained by performing color matching using the histogram mapping relationship between the grayscale value of the original remote sensing image and the grayscale value of the reference image.

[0008] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, the virtual low-resolution image is reconstructed using the original remote sensing image and the reference image to obtain a virtual low-resolution image, and the method also includes: Respectively determining the local mean and variance in the normal distribution of the original remote sensing image, and determining the local mean and variance in the normal distribution of the reference image; The gray value of the reference image is determined, and the virtual low-resolution image is obtained by using the local mean and variance in the normal distribution of the original remote sensing image, the local mean and variance in the normal distribution of the reference image, and the gray value of the reference image.

[0009] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, the virtual low-resolution image is reconstructed using the original remote sensing image and the reference image to obtain a virtual low-resolution image, and the method also includes: Extracting background information of the reference image and detail information of the original remote sensing image; The background information and the detail information are superimposed, and when coloring, a simulated background image is used to replace the background information to obtain a color-matched replacement image; The virtual low-resolution image is obtained by taking the mean value of the uniform color replacement image as the center and combining the stretching coefficient to compensate for brightness loss.

[0010] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, based on the virtual low-resolution image, a spatiotemporal fusion strategy is used to perform color correction processing on the original remote sensing image to obtain a uniform color result image, including: Determining any candidate pixel as a similar pixel in the original remote sensing image based on a preset screening condition; Based on the similar pixels, calculating the spectral difference measure, the phase difference measure and the spatial difference measure between the original remote sensing image, the reference image and the virtual low-resolution image; The spectral difference metric, the phase difference metric and the spatial difference metric are processed by weighted spatiotemporal filtering color correction to output the uniform color result image.

[0011] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, any candidate pixel is determined as a similar pixel in the original remote sensing image based on a preset screening condition, including: The threshold for selecting spectrally similar pixels is determined by the mean square error of high-resolution images and the estimated number of ground object categories. The central pixel is determined according to the size of the local moving window, and the similar pixel is obtained when the absolute value of the difference between any candidate pixel in the original remote sensing image and the central pixel is less than the threshold value for screening spectrally similar pixels.

[0012] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, based on the similar pixels, the spectral difference measurement, the phase difference measurement and the spatial difference measurement between the original remote sensing image, the reference image and the virtual low-resolution image are calculated, including: Calculating the gray value difference between the original remote sensing image and the virtual low-resolution image at the same time to obtain the spectral difference measurement; Calculating the gray value difference between the reference image and the virtual low-resolution image at different times to obtain the phase difference measurement; A specific constant is determined, and a spatial distance between the candidate pixel and the central pixel is calculated in a local moving window based on the specific constant to obtain the spatial difference metric.

[0013] According to a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction provided by the present invention, the spectral difference metric, the phase difference metric and the spatial difference metric are processed by weighted spatiotemporal filtering color correction to output the uniform color result image, including: Calculating a weight function based on the spectral difference metric, the phase difference metric, and the spatial difference metric; The uniform color result image is calculated based on the weight function and the grayscale values ​​of the original remote sensing image, the reference image and the virtual low-resolution image at different times.

[0014] In a second aspect, the present invention further provides a remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction, comprising: An acquisition module is used to acquire an original remote sensing image to be reconstructed and determine a corresponding reference image according to the characteristics of the original remote sensing image; A reconstruction module, used to reconstruct a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; The correction module is used to perform color correction processing on the original remote sensing image based on the virtual low-resolution image by adopting a spatiotemporal fusion strategy to obtain a uniform color result image.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) The remote sensing image spatiotemporal fusion algorithm framework is introduced into the color correction process. The present invention proposes to use the spectral information of the original image to reconstruct the reference base map before color correction to obtain a virtual low-resolution image as auxiliary data. The image has a similar color distribution to the original image and a similar texture feature to the reference base map, which meets the requirements of the fusion algorithm for existing images. (2) The weighted spatiotemporal filtering is used to realize color correction processing. The method proposed in the present invention fully considers the temporal correlation, spatial proximity and spectral similarity of adjacent pixels between images, and uses a local filtering window to select spectrally similar pixels of the target pixel to reconstruct a uniform color image, so that the resulting image maintains the same color as the reference background. Figure 1While maintaining consistent color distribution, it can retain the detail features of the high-resolution original image to the greatest extent, and can effectively overcome the shortcomings of existing methods in considering image details and the relationship between pixels. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a schematic diagram of the process of remote sensing image spatiotemporal fusion color correction based on virtual low-resolution reconstruction provided by the present invention; Figure 2 It is a principle diagram of remote sensing image spatiotemporal fusion color correction based on virtual low-resolution reconstruction provided by the present invention; Figure 3 It is a structural schematic diagram of a remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0019] In view of the problems existing in the prior art, the present invention proposes a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction, introduces a weighted spatiotemporal filtering mechanism in the color correction process, generates a virtual low-resolution image as auxiliary data, and comprehensively considers the temporal correlation, spatial proximity and spectral similarity between the virtual low-resolution image and the original image and the reference base image elements, utilizes the spectrally similar pixels of the central pixel in the filtering window to participate in the result calculation, and generates a result image with both the detail characteristics of the original image and the spectral characteristics of the reference image.

[0020] Figure 1 FIG. 1 is a flow chart of remote sensing image spatiotemporal fusion color correction based on virtual low-resolution reconstruction provided by an embodiment of the present invention. Figure 1 As shown, including: Step 100: obtaining an original remote sensing image to be reconstructed, and determining a corresponding reference image according to the characteristics of the original remote sensing image; Step 200: reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; Step 300: Based on the virtual low-resolution image, a spatiotemporal fusion strategy is used to perform color correction processing on the original remote sensing image to obtain a uniform color result image.

[0021] Specifically, in an embodiment of the present invention, firstly, in order to fuse the spatiotemporal information of images with different resolutions, it is proposed to reconstruct a reference image using the spectral information of the original image, and obtain a virtual low-resolution image as auxiliary data before correction; secondly, in order to retain the detail information to the maximum extent, a weighted spatiotemporal filtering mechanism is introduced to highlight and quantify the temporal correlation, spatial proximity and spectral similarity among the reconstructed image, the original image and the reference image, so that they participate in the calculation of the correction result, and generate a result image with the detail characteristics of the original image and the spectral characteristics of the reference image.

[0022] Combination Figure 2 To illustrate the technical solution of the present invention.

[0023] The first step is to select the corresponding reference image based on the image characteristics.

[0024] Currently, the amount of remote sensing image data is large and the sources are wide-ranging. It is usually necessary to obtain a reference base map with uniform color and easy to process for color uniformity. That is, historical results data with good color consistency and no seams can be used as a reference base map.

[0025] There are several main ways to obtain a reference base map. First, you can download low-resolution images of the corresponding survey area and time period from open source network platforms, such as Google Maps, Tiandi Maps, and Baidu Maps. Second, you can obtain images from historical data that have been processed by data production units as reference base maps. Third, you can select images with uniform colors from land satellite remote sensing images or images with larger widths and process them as reference base maps.

[0026] It is understandable that the spectral characteristics of different remote sensing images covering the same area should be the same, so the geographical location is one of the factors that need to be considered when selecting the reference base map, that is, select an image that covers the same area as the original reference image. Secondly, complex surface coverage usually changes in different seasons. When selecting a reference base map, the imaging season should be close to the original image to ensure that the coverage type and distribution of objects in the same area are similar. In addition, since the ultimate goal of color grading is to obtain an image with uniform color and rich details, the balance of the color distribution of the image is an important criterion that must be considered. Therefore, the reference base map selected before the remote sensing image based on the reference base map should have the characteristics of uniform color, covering the same survey area as the original image, similar imaging time, and small changes in objects.

[0027] In the second step, after obtaining the corresponding reference image, the reference image and the original image are used to reconstruct a virtual low-resolution image.

[0028] In fact, the reconstruction process of virtual low-resolution images is to transfer information between the original image and the reference background according to certain matching rules, so that the reconstructed image is superimposed with the same color distribution as the original image while maintaining the original texture of the reference background. Combined with the characteristics of virtual low-resolution images, the color information of the original image is extracted and matched to the reference background. Methods based on histogram matching, statistical feature parameter matching, and linear transformation can be used. First, the cumulative histogram, mean, variance and other parameters of the original known image need to be counted and recorded, and then a mapping relationship between the two is established to achieve color matching, and finally a color distribution and reference background similar to the original image are generated. Figure 1 The virtual low-resolution images with consistent texture features are generated, and their quality is analyzed and evaluated. The qualified images are used as auxiliary data for constructing uniform color models in subsequent processing.

[0029] (1) The reconstruction method based on histogram matching is based on the original image to be uniformly colored. The histogram of the standard reference background The histogram of is matched to obtain Consistent histogram distribution, the two have good color consistency. Assume It conforms to the normal distribution ( , ), It conforms to the normal distribution ( , ), then:

[0030] So we can get:

[0031] According to the above formula, a mapping relationship between the grayscale value of the original image and the grayscale value of the reference base map is established to perform color matching to obtain a virtual low-resolution image. .

[0032] (2) The reconstruction method based on statistical feature parameter matching uses parameters that characterize the grayscale distribution and discreteness of the image, such as mean, variance and other statistical parameters, to establish the color relationship between the image to be processed and the reference standard to achieve a uniform color effect. Among them, Wallis filtering is one of the most commonly used methods. The conversion relationship can be expressed as:

[0033] and are the grayscale values ​​of the uniform color reference base map and the reconstructed virtual low-resolution image, and Respectively represent the local mean and variance of the original image to be uniformly colored, and Respectively represent uniform color reference background The local mean and variance of .

[0034] (3) The linear transformation reconstruction method uses the linear correlation between the overlapping areas of the images to match and interpolate them into the rest of the original image dataset. It regards the image 𝐹 as the image detail information Overlay with background image 𝐵:

[0035] Use simulated background images when balancing colors Replace the background in the original image:

[0036] Then with The mean Generate a spectral reconstruction image to compensate for brightness loss :

[0037] in, and is the stretch coefficient.

[0038] The third step is to obtain the reconstructed virtual low-resolution image and use the spatiotemporal fusion strategy to perform color correction on the original image.

[0039] (1) Find similar pixels to the central pixel in the original image.

[0040] Without considering the influence of geometric registration and atmospheric correction errors between images, there is correlation between pixels of multi-source images in the same area, and high-resolution homogeneous pixels in the area can be calculated using adjacent low-resolution spectrally similar pixels. In order to ensure the use of correct information about adjacent pixels, only pixel data with the same spectral type as the original image to be processed and without cloud and fog obstruction can be used in the calculation. The present invention defines pixels with a grayscale value difference within the neighborhood that is less than a specific threshold as similar pixels, and reconstructs the image by selecting neighboring pixels similar to the central pixel in the image through a local moving window. It is worth noting that a window that is too large will introduce redundant mixed pixels, so the window size can be set to an appropriate value according to the characteristics of the areas covered by different images. Similar pixels are generally determined according to the following formula:

[0041] in, is the size of the local moving window, and its value is determined according to the complexity of the image objects in the study area and experimental experience; ( , )and( , ) are candidate pixels and central pixels respectively, and the constant To select the threshold value of spectrally similar pixels, the mean square error of the high-resolution image can be and the estimated number of feature categories Determine, that is .

[0042] (2) Quantify the spectral, temporal, and spatial differences between the original image, the reference image, and the low-resolution reconstructed image.

[0043] Reconstructed virtual image As with the original image The corresponding low-resolution images at the same time have a reflectivity difference between the high-resolution and low-resolution images at that time, and a low-resolution reference base map at another time. There are differences between low-resolution images caused by different imaging times. Taking into account the complex surface cover types and changing environmental impacts, the present invention, based on the reconstructed image, combines the remote sensing image spatiotemporal fusion algorithm to quantify the spectral, temporal and spatial differences between images, so as to reduce the errors caused by external conditions and achieve the purpose of considering the color differences between ground object categories.

[0044] The spectral difference between the original image to be homogenized and the virtual low-resolution image is expressed as :

[0045] The temporal difference between the reference base map and the virtual low-resolution image is expressed as :

[0046] , Indicates different moments of the image.

[0047] The spatial distance between the candidate pixel and the central pixel in the moving window is , the calculation formula is as follows:

[0048] in, is a specific constant, and the relative distance in the moving window changes from 1 to , The smaller the value, the larger the dynamic range. , and The smaller the value, the smaller the difference between the neighboring pixels and the central pixel.

[0049] (3) Use weighted filtering to achieve color correction processing.

[0050] In order to apply the quantized spatiotemporal spectrum difference to the uniform color processing, the present invention introduces a weight function To participate in uniform color fusion, the weight function is determined by the spectral difference, phase difference and spatial difference between the original image and the virtual low-resolution image and the reference base map. It comprehensively measures the importance of similar pixels adjacent to the target pixel to its spectral information, and finally traverses the entire image to generate a uniform color result image.

[0051] Comprehensive quantified spatiotemporal spectrum differences, weight function Normalization can be expressed as:

[0052] Represents the total number of similar pixels; Combining the above formula, the calculation formula for the central pixel after local window filtering is:

[0053] , Indicates different moments of the image.

[0054] like Figure 2As shown in the figure, the remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction is divided into two main parts: virtual low-resolution image reconstruction and spatiotemporal fusion color correction based on weighted spatiotemporal filtering. In order to combine high-resolution detail features with low-resolution spectral features and effectively utilize the relationship between adjacent pixels, the method proposed in the present invention generates a virtual low-resolution reconstructed image as auxiliary data, introduces a weighted spatiotemporal filtering mechanism in the processing process, and considers the temporal correlation, spatial proximity and spectral similarity between the pixels of the original image or the reference image, and uses the spectrally similar pixels of the central element of the filtering window to participate in the result calculation, and finally generates a result image with both the detail features of the original image and the spectral features of the reference image.

[0055] The remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction provided by the present invention is described below. The remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction described below and the remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction described above can be referenced to each other.

[0056] Figure 3 is a structural diagram of a remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: an acquisition module 31, a reconstruction module 32 and a correction module 33, wherein: The acquisition module 31 is used to acquire the original remote sensing image to be reconstructed, and determine the corresponding reference image according to the characteristics of the original remote sensing image; the reconstruction module 32 is used to reconstruct a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; the correction module 33 is used to perform color correction processing on the original remote sensing image based on the virtual low-resolution image using a time-space fusion strategy to obtain a uniform color result image.

[0057] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction, the method comprising: obtaining an original remote sensing image to be reconstructed, determining a corresponding reference image according to the characteristics of the original remote sensing image; reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; and based on the virtual low-resolution image, performing color correction processing on the original remote sensing image using a spatiotemporal fusion strategy to obtain a uniform color result image.

[0058] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0059] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0060] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0061] 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 embodiments of the present invention.

Claims

1. A remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction, characterized in that: include: Acquire an original remote sensing image to be reconstructed, and determine a corresponding reference image according to the characteristics of the original remote sensing image; Reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; Based on the virtual low-resolution image, a spatiotemporal fusion strategy is adopted to perform color correction processing on the original remote sensing image to obtain a uniform color result image.

2. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 1 is characterized in that: Acquiring an original remote sensing image to be reconstructed, and determining a corresponding reference image according to the characteristics of the original remote sensing image, including: Downloading a low-resolution image with a corresponding measurement area and time period as the reference image from an open source network platform; Acquire images from historical achievement data processed by a data production unit as the reference images; An image with uniform color is selected from land satellite remote sensing images or images with a preset large width and processed as the reference image.

3. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 1 is characterized in that: Reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image includes: Respectively determining the mean and variance in the normal distribution of the original remote sensing image, and determining the mean and variance in the normal distribution of the reference image; Based on the mean and variance in the normal distribution of the original remote sensing image and the mean and variance in the normal distribution of the reference image, a histogram mapping relationship between the grayscale value of the original remote sensing image and the grayscale value of the reference image is established; The virtual low-resolution image is obtained by performing color matching using the histogram mapping relationship between the grayscale value of the original remote sensing image and the grayscale value of the reference image.

4. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 1 is characterized in that: Reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image also includes: Respectively determining the local mean and variance in the normal distribution of the original remote sensing image, and determining the local mean and variance in the normal distribution of the reference image; The gray value of the reference image is determined, and the virtual low-resolution image is obtained by using the local mean and variance in the normal distribution of the original remote sensing image, the local mean and variance in the normal distribution of the reference image, and the gray value of the reference image.

5. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 1 is characterized in that: Reconstructing a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image also includes: Extracting background information of the reference image and detail information of the original remote sensing image; The background information and the detail information are superimposed, and when coloring, a simulated background image is used to replace the background information to obtain a color-matched replacement image; The virtual low-resolution image is obtained by taking the mean value of the uniform color replacement image as the center and combining the stretching coefficient to compensate for brightness loss.

6. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 1 is characterized in that: Based on the virtual low-resolution image, the original remote sensing image is color corrected by using a spatiotemporal fusion strategy to obtain a uniform color result image, including: Determining any candidate pixel as a similar pixel in the original remote sensing image based on a preset screening condition; Based on the similar pixels, calculating the spectral difference measure, the phase difference measure and the spatial difference measure between the original remote sensing image, the reference image and the virtual low-resolution image; The spectral difference metric, the phase difference metric and the spatial difference metric are processed by weighted spatiotemporal filtering color correction to output the uniform color result image.

7. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 6 is characterized in that: Determining any candidate pixel as a similar pixel in the original remote sensing image based on a preset screening condition includes: The threshold for selecting spectrally similar pixels is determined by the mean square error of high-resolution images and the estimated number of ground object categories. The central pixel is determined according to the size of the local moving window, and the similar pixel is obtained when the absolute value of the difference between any candidate pixel in the original remote sensing image and the central pixel is less than the threshold value for screening spectrally similar pixels.

8. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 7 is characterized in that: Based on the similar pixels, calculating the spectral difference measure, the phase difference measure and the spatial difference measure between the original remote sensing image, the reference image and the virtual low-resolution image, including: Calculating the gray value difference between the original remote sensing image and the virtual low-resolution image at the same time to obtain the spectral difference measurement; Calculating the gray value difference between the reference image and the virtual low-resolution image at different times to obtain the phase difference measurement; A specific constant is determined, and a spatial distance between the candidate pixel and the central pixel is calculated in a local moving window based on the specific constant to obtain the spatial difference metric.

9. The remote sensing image spatiotemporal fusion color correction method based on virtual low-resolution reconstruction according to claim 8, characterized in that: The method uses weighted spatiotemporal filtering color correction to process the spectral difference metric, the phase difference metric, and the spatial difference metric, and outputs the uniform color result image, including: Calculating a weight function based on the spectral difference metric, the phase difference metric, and the spatial difference metric; The uniform color result image is calculated based on the weight function and the grayscale values ​​of the original remote sensing image, the reference image and the virtual low-resolution image at different times.

10. A remote sensing image spatiotemporal fusion color correction system based on virtual low-resolution reconstruction, characterized in that: include: An acquisition module is used to acquire an original remote sensing image to be reconstructed and determine a corresponding reference image according to the characteristics of the original remote sensing image; A reconstruction module, used to reconstruct a virtual low-resolution image using the original remote sensing image and the reference image to obtain a virtual low-resolution image; The correction module is used to perform color correction processing on the original remote sensing image based on the virtual low-resolution image by adopting a spatiotemporal fusion strategy to obtain a uniform color result image.

Images