Remote Sensing Image Enhancement Method and System Based on Visual Analysis

Abstract

The present invention relates to the field of image enhancement technology, and particularly to a remote sensing image enhancement method and system based on visual analysis. The method first obtains multiple preliminary connected components of the remote sensing image through a connected component algorithm; then, based on the color, texture condition, area, and the shortest distance between all edge pixel points within each preliminary connected component, multiple connected components of the remote sensing image are obtained. By calculating the local feature index of the connected components, evaluating the possibility of merging, clustering and dividing the surface feature regions, determining the side length of the pixel window and the weights of neighboring pixels, finally, the remote sensing image is enhanced according to the weights. The remote sensing image enhancement method provided by the present invention effectively enhances the quality of the remote sensing image, improves the recognition accuracy of surface features, effectively removes noise while maintaining important details, and the filtering result can more accurately conform to the actual features of the image, retaining both key information and improving the processing efficiency and visual effect.

Description

Technical Field

[0001] The present invention relates to the technical field of image enhancement, and in particular to a remote sensing image enhancement method and system based on visual analysis. Background Art

[0002] Remote sensing images play an irreplaceable role in providing information about the earth's surface. They are widely used in scientific research, resource management, and environmental monitoring. However, due to various limitations, the spatial and temporal resolutions of remote sensing images are not high, which restricts the scope of application of remote sensing images. In order to observe the objects of interest more clearly, enhancement processing becomes a necessary step. Gaussian filtering is a classic image processing technique that is widely used in the enhancement and analysis of remote sensing images. Gaussian filtering effectively removes random noise in the image by smoothing the image using a Gaussian function, while retaining edges and important features as much as possible.

[0003] In the prior art, the traditional implementation of Gaussian filtering usually fixes the window size and calculates the weight of each pixel in the window according to the Gaussian distribution. However, this method may not be flexible and efficient when processing images with different textures and details. For example, using a larger window on the edge or in areas with rich details will produce too much smoothing effect, resulting in blurred edges and loss of details; while using a smaller window in a large area of ​​uniform smooth areas will increase the amount of calculation, resulting in unnecessary over-enhancement, which will make the filtering result inconsistent with the actual characteristics of the image. Summary of the invention

[0004] In order to solve the technical problem that the remote sensing image processing in the prior art is not flexible and efficient enough, the purpose of the present invention is to provide a remote sensing image enhancement method based on visual analysis. The technical solution adopted is as follows:

[0005] In a first aspect, a remote sensing image enhancement method based on visual analysis is provided, the method comprising:

[0006] Step S1: obtaining multiple preliminary connected domains of the remote sensing image through a connected domain algorithm;

[0007] Step S2: obtaining multiple connected domains of the remote sensing image according to the color, texture, area, and the shortest distance between all edge pixels in each preliminary connected domain;

[0008] Step S3: clustering all connected domains, and each obtained cluster represents a surface feature area;

[0009] Step S4: Obtain the window side length of a pixel point according to the position of the pixel point in the surface feature area where the pixel point is located, the grayscale variance in the connected domain where the pixel point is located, and the difference in local feature indexes of the connected domains on both sides of the pixel point;

[0010] Step S5: Obtain the weights of each neighboring pixel within the window of each pixel based on the grayscale and gradient of each pixel and other neighboring pixels within its window.

[0011] Step S6: Perform enhancement processing on the remote sensing image according to the weights.

[0012] Further, the specific steps of Step S2 include:

[0013] Obtain the local feature index of a preliminary connected region according to the grayscale value corresponding to the peak of the grayscale histogram of the preliminary connected region, the variance of the grayscale values of all pixels in the preliminary connected region, and the mean of the gradients of all pixels in the preliminary connected region.

[0014] Obtain the merging possibility of any two preliminary connected regions according to the local feature indices, areas, and the shortest distance between all edge pixels of the two preliminary connected regions.

[0015] Obtain multiple connected regions of the remote sensing image according to the merging possibilities of any two adjacent preliminary connected regions.

[0016] Further, the grayscale value corresponding to the peak of the grayscale histogram of a preliminary connected region, the variance of the grayscale values of all pixels in the preliminary connected region, and the mean of the gradients of all pixels in the preliminary connected region are all positively correlated with the local feature index of the preliminary connected region.

[0017] The absolute value of the difference between the local feature indices of any two preliminary connected regions, the shortest distance between all edge pixels of the two preliminary connected regions are negatively correlated with the merging possibility of the two preliminary connected regions, and the area difference between the two preliminary connected regions is positively correlated with the merging possibility of the two preliminary connected regions.

[0018] Further, the specific steps of Step S3 include:

[0019] Take the mean of the local feature indices of all preliminary connected regions included in the connected region as the local feature index of the connected region.

[0020] Obtain the clustering feature value of a connected region according to the local feature index of the connected region and the peak of the grayscale histogram of the connected region.

[0021] Use the difference in clustering feature values between connected regions as the clustering distance to cluster all connected regions to obtain multiple clusters, and each cluster represents a surface feature region.

[0022] Further, the specific steps in Step S4 include:

[0023] When a pixel does not belong to an edge pixel, the distance of the pixel from the edge and the gray variance within the connected component to which the pixel belongs are both negatively correlated with the window side length of the pixel;

[0024] When a pixel belongs to an edge pixel, the difference in local feature indices between the connected components on both sides of the pixel is negatively correlated with the window side length of the pixel.

[0025] Furthermore, step S4 further includes:

[0026] When a pixel belongs to an edge pixel and the connected components on both sides of the pixel are regions with different surface features, the larger the window side length of the pixel.

[0027] Furthermore, step S5 specifically includes:

[0028] Based on the difference between the product of the gray value and gradient of a pixel and its first neighborhood pixel within the window, and the difference in local feature indices between the connected component to which the pixel belongs and the connected component to which the neighborhood pixel within the window belongs, obtain the weight of the neighborhood pixel within the window of the pixel;

[0029] Based on the weights of each neighborhood pixel of each pixel, obtain an enhanced remote sensing image.

[0030] Furthermore, both the difference between the product of the gray value and gradient of a pixel and its first neighborhood pixel within the window, and the difference in local feature indices between the connected component to which the pixel belongs and the connected component to which the neighborhood pixel within the window belongs are negatively correlated with the weight of the neighborhood pixel within the window of the pixel.

[0031] Furthermore, step S6:

[0032] For each pixel in the remote sensing image, based on the weights of each neighborhood pixel of each pixel, perform weighted summation on the gray values of all neighborhood pixels within its window, use the result as the new gray value of the central pixel after filtering, assign the calculated weighted sum to the central pixel, and obtain an enhanced remote sensing image.

[0033] On the other hand, the present invention provides a remote sensing image enhancement system based on visual analysis, and the system includes:

[0034] A preliminary connected component acquisition module, configured to obtain a plurality of preliminary connected components of the remote sensing image through a connected component algorithm;

[0035] A connected component acquisition module, configured to obtain a plurality of connected components of the remote sensing image according to the color, texture condition, area, and the shortest distance between all edge pixels within each preliminary connected component;

[0036] A surface feature area acquisition module, which is used to cluster all connected components, and each obtained cluster represents a surface feature area;

[0037] A window side length acquisition module, which is used to obtain the window side length of a pixel point according to the position of the pixel point in its corresponding surface feature area, the gray variance within the connected component where the pixel point is located, and the difference in local feature indices of the connected components on both sides of the pixel point;

[0038] A weight acquisition module, which is used to obtain the weights of each neighboring pixel point within the window of each pixel point according to the gray levels and gradients of each pixel point and other neighboring pixel points within its window;

[0039] An enhancement processing module, which is used to perform enhancement processing on the remote sensing image according to the weights.

[0040] The present invention has the following beneficial effects: By calculating the local feature index of the connected component, evaluating the merging possibility, clustering and dividing the surface feature area, determining the window side length of the pixel point and the weights of the neighboring pixels, and applying Gaussian filtering for smoothing processing, the quality of the remote sensing image is effectively enhanced, the recognition accuracy of the surface features is improved, and noise is effectively removed and the image is smoothed while maintaining important details. In this way, the filtering result can more accurately conform to the actual features of the image, retaining both key information and improving the processing efficiency and visual effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0042] Figure 1 It is a schematic diagram of a remote sensing image provided by an embodiment of the present invention.

[0043] Figure 2 It is a flowchart of a remote sensing image enhancement method based on visual analysis provided by an embodiment of the present invention.

[0044] Figure 3 It is a block diagram of a remote sensing image enhancement system based on visual analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the remote sensing image enhancement method based on visual analysis proposed by the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as commonly understood by technicians in the technical field of the present invention.

[0046] The specific scheme of the remote sensing image enhancement method based on visual analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0047] First, please refer to Figure 2 , which shows a flow chart of a remote sensing image enhancement method based on visual analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0048] Step S1: Obtain multiple preliminary connected domains of the remote sensing image through a connected domain algorithm.

[0049] Among them, step S1 specifically includes: using a drone equipped with a camera to take pictures, collecting remote sensing images, preprocessing the images, and obtaining multiple preliminary connected domains of the remote sensing images through a connected domain algorithm.

[0050] More specifically, by using drones equipped with high-precision cameras to capture remote sensing images and pre-processing the images such as denoising, ground features can be further highlighted, providing a solid foundation for subsequent analysis and application. Figure 1 In the remote sensing image shown, the river is a hydrological network composed of multi-level water systems. Its shape is diverse, often in the shape of naturally curved ribbons with different widths. Due to the reflection and absorption characteristics of water bodies to light, the river is reflected in the image as a regular, blue-green image feature, with obvious color and relatively smooth texture features in the remote sensing image; various vegetation, fallow land, etc. appear in dark green and dark brown colors, and also have relatively uniform texture features.

[0051] In remote sensing images, characteristic areas such as rivers and vegetation have different characteristics. Most surface water bodies are reservoirs formed by dikes in low-lying areas, which are obviously different from the surrounding objects. Therefore, it is necessary to divide remote sensing images into multiple connected domains for further analysis.

[0052] Step S2: Acquire multiple connected domains of the remote sensing image based on the color, texture, area, and the shortest distance between all edge pixels in each preliminary connected domain.

[0053] Among them, the specific steps of step S2 include: obtaining the local feature index of a preliminary connected component according to the gray value corresponding to the peak of the gray histogram of the preliminary connected component, the variance of the gray values of all pixel points of the preliminary connected component, and the mean value of the gradients of all pixel points of the preliminary connected component; obtaining the merging possibility of any two preliminary connected components according to the local feature indices, areas, and the shortest distance between all edge pixel points of the two preliminary connected components; and obtaining multiple connected components of the remote sensing image according to the merging possibilities of any two adjacent preliminary connected components.

[0054] More specifically, first, use the connected component algorithm to operate on the remote sensing image to obtain multiple preliminary connected components. Since there are gray value differences in different surface feature regions in the remote sensing image, there are differences in the peaks of the gray histograms of each preliminary connected component in the remote sensing image. For example, the gray value corresponding to the peak of the gray histogram of the connected component in the river area should be larger, and the gray value corresponding to the peak of the gray histogram of the connected component in the ground object area should be smaller. Therefore, the local feature index of each preliminary connected component can be determined according to the color and texture conditions within each preliminary connected component. In this embodiment, the mathematical calculation formula for constructing the local feature index of each preliminary connected component can be expressed as:

[0055] ;

[0056] In the formula, represents the gray value corresponding to the peak of the gray histogram of the th preliminary connected component; represents the variance of the gray values of all pixel points of the th preliminary connected component; represents the mean value of the gradients of all pixel points of the th preliminary connected component; represents the local feature index of the th preliminary connected component.

[0057] In the above mathematical calculation formula for constructing the local feature index of the preliminary connected component, represents restricting the range of the gray value corresponding to the peak of the gray histogram of the th preliminary connected component to be between 0 and 1; represents the degree of dispersion of the gray values of all pixel points of the th preliminary connected component, that is, the contrast of the th preliminary connected component; represents the gray value change situation of all pixel points of the th preliminary connected component, that is, the clarity of the th preliminary connected component; all three are important components of the local feature index of the th preliminary connected component, so all three are positively correlated with the th preliminary connected component. The local feature index of a preliminary connected component.

[0058] Therefore, the gray value corresponding to the peak of the gray histogram of a preliminary connected component, the variance of the gray values of all pixel points in this preliminary connected component, and the mean value of the gradients of all pixel points in this preliminary connected component are all positively correlated with the local feature index of this preliminary connected component.

[0059] In a remote sensing image, due to the complexity of surface features, a certain actually continuous feature area may be misidentified as two or even more connected components. For example, at river junctions, branches, or the border between two rivers. Therefore, it is necessary to calculate the merging possibility of any two adjacent preliminary connected components according to the local feature index of the preliminary connected component and the distance between adjacent connected components. In this embodiment, the mathematical calculation formula for constructing the merging possibility of any two adjacent preliminary connected components can be expressed as:

[0060] ;

[0061] In the formula, represents the merging possibility of the th and the th preliminary connected components; respectively represent the local feature indices of the th and the th preliminary connected components; respectively represent the areas of the th and the th preliminary connected components; represents the shortest distance between all edge pixel points of the th and the th preliminary connected components; represents the normalization function.

[0062] In the above-mentioned mathematical calculation formula for constructing the merging possibility of any two adjacent preliminary connected components, if , it indicates that the local feature indices of these two adjacent preliminary connected components are the same. However, if the local feature indices of these two adjacent preliminary connected components are the same, during the preliminary connected component construction stage, these two places will be divided into one preliminary connected component. Therefore, in this formula, ; Obviously, there must be a distance between all edge pixel points of the th and the th preliminary connected components, so ; When the area difference between these two preliminary connected components is larger, it indicates that the smaller preliminary connected component should be merged into the larger preliminary connected component more. Therefore, is positively correlated with ; When the th and the The smaller the difference in the local feature indices of two preliminary connected components, the more similar the features of the two preliminary connected components are and the more they should be merged. Therefore is negatively correlated with ; Similarly, the shorter the shortest distance between all the edge pixels of the -th and the -th preliminary connected components, the closer the two preliminary connected components are and the more they should be merged. Therefore, is negatively correlated with .

[0063] Therefore, the absolute value of the difference in the local feature indices of any two preliminary connected components, the shortest distance between all the edge pixels of the two preliminary connected components, and the possibility of merging the two preliminary connected components are negatively correlated, and the difference in the areas of the two preliminary connected components is positively correlated with the possibility of merging the two preliminary connected components.

[0064] After obtaining the possibility of merging any two adjacent preliminary connected components, a preset merging threshold is set to 0.6, which can be adjusted according to specific application scenarios; when is greater than the preset merging threshold, without affecting other adjacent preliminary connected components, the -th and the -th preliminary connected components are merged. According to the merging rules, the adjacent preliminary connected components that meet the conditions are iteratively merged until no adjacent preliminary connected components that meet the conditions can be found. In this way, multiple connected components of the remote sensing image are obtained.

[0065] For each connected component, it represents one of the surface feature regions in the remote sensing image, including ground objects such as rivers and vegetation. Therefore, it is very necessary to determine the relationship between the connected components. According to clustering all the connected components, the connected components with the same surface features are grouped into one category. Therefore, the following steps are further set in this embodiment.

[0066] Step S3: Cluster all the connected components, and each obtained cluster represents a surface feature region.

[0067] Among them, step S3 specifically includes: taking the mean value of the local feature indices of all the preliminary connected components included in the connected component as the local feature index of the connected component; obtaining the clustering feature value of the connected component according to the local feature index of the connected component and the peak value of the gray histogram of the connected component; using the difference in the clustering feature values between the connected components as the clustering distance, clustering all the connected components, and obtaining multiple clusters, and each cluster represents a surface feature region.

[0068] More specifically, first, when the connected component is obtained by merging multiple preliminary connected components, the average value of the local feature indices of all preliminary connected components is used as the local feature index of this connected component. Moreover, for different surface feature regions, the area of the river region is usually smaller than that of the ground object region, so the number of pixel points at the peak in its grayscale histogram also varies. Therefore, in this embodiment, the mathematical calculation formula for the clustering feature value of each connected component in the remote sensing image can be expressed as:

[0069] ;

[0070] In the formula, represents the clustering feature value of the th connected component; represents the local feature index of the th connected component; represents the peak of the grayscale histogram of the th connected component.

[0071] In the above mathematical calculation formula for the clustering feature value of each connected component, when the local feature indices between connected components and the peaks of their grayscale histograms are closer, it is more likely that they belong to the same surface feature region. Therefore, when clustering, they should have a smaller clustering distance, that is, the difference in clustering feature values is smaller. So, the clustering feature value of the th connected component and the local feature index of the th connected component are both positively correlated with the clustering feature value of this connected component.

[0072] Furthermore, in the remote sensing image, using the difference in clustering feature values between connected components as the clustering distance, all connected components are clustered to obtain several clusters, and the connected components of all different clusters are labeled with different codes. For example, the codes can be 1, 2, 3…, and the connected components in the same cluster have the same code. Based on this, all connected components are divided into multiple surface feature regions, and each surface feature region has a code.

[0073] To effectively enhance the remote sensing image, it is necessary to further determine the dynamic window size for each pixel point in the remote sensing image. Therefore, this embodiment further sets the following steps.

[0074] Step S4: Obtain the window side length of this pixel point according to the position of a pixel point in the surface feature region where it is located, the grayscale variance within the connected component where this pixel point is located, and the difference in local feature indices of the connected components on both sides of this pixel point.

[0075] Among them, step S4 specifically includes: when a pixel does not belong to an edge pixel, the distance of the pixel from the edge and the gray variance within the connected domain where the pixel is located are both negatively correlated with the window side length of the pixel; when a pixel belongs to an edge pixel, the difference in the local feature indices of the connected domains on both sides of the pixel is negatively correlated with the window side length of the pixel, and when a pixel belongs to an edge pixel and the connected domains on both sides of the pixel are different surface feature regions, the larger the window side length of the pixel.

[0076] More specifically, when performing Gaussian filtering on a remote sensing image, when a pixel belongs to a large smooth area within a certain surface feature region, a larger window should be given to avoid over-enhancing invalid information. When a pixel is near an edge pixel, that is, it belongs to the edge detail information that should be enhanced to a large extent, a smaller window should be given because edge information is crucial for the recognition and segmentation of surface features, and using a small window can better retain and enhance these edge details. That is, the farther the pixel within the connected domain is from the edge, the larger the window of the pixel; and when the pixel is an edge pixel and the connected domains on both sides are different surface feature regions, that is, the codes of the connected domains on both sides are different, then it is the effective detail that needs to be enhanced and has a relatively small window.

[0077] In this embodiment, the mathematical calculation formula for the window side length of each pixel in the remote sensing image is constructed as follows:

[0078] ;

[0079] In the formula, represents the window side length of pixel m in the remote sensing image; represents the preset standard window side length; represents the minimum value of the distance between pixel m and all edge pixels in its connected domain. Obviously, ; represents the gray variance within the connected domain where pixel m is located. Since the gray levels in a connected domain are not exactly the same, so ; represents the absolute value of the difference in the local feature indices of the connected domains on both sides of pixel m; is a coefficient, taking 1 when the codes of the connected domains on both sides of pixel m are the same and taking 2 when they are different; represents the set of edge pixels; represents the normalization function; represents the exponential function with the natural constant e as the base.

[0080] In the mathematical calculation formula of the window side length of each pixel point in the remotely sensed image constructed above, when the pixel point m is not an edge pixel point, the farther it is from the edge, the more it is in the relatively smooth area within the connected domain. And when the gray variance within the connected domain where the pixel point m is located is smaller, it indicates that the connected domain is more uniform, then the larger the window is given, and the weaker the filtering enhancement effect is; when the pixel point m is an edge pixel point, when the difference in the local feature index of the connected domains on both sides of the edge pixel point is larger, the smaller the window is, and when the connected domains on both sides are different surface feature regions, the stronger the enhancement degree should be, that is, the smaller the window is.

[0081] After obtaining the window side length of the pixel point in the remotely sensed image, the square of the side length is the window size of the pixel point. Further, it is necessary to accurately determine the weights of all neighboring pixel points within the window to perform enhancement processing on the remotely sensed image through the weights of all neighboring pixel points within the window. Therefore, this embodiment further sets the following steps.

[0082] Step S5: Obtain the weight of each neighboring pixel point within the window of each pixel point according to the gray level and gradient of each pixel point and other neighboring pixel points within its window.

[0083] Among them, step S5 specifically includes: obtaining the weight of the neighboring pixel point within the window of the pixel point according to the difference between the product of the gray level and gradient of a pixel point and the first neighboring pixel point within its window and the difference in the local feature index of the connected domain where the neighboring pixel point within the window of this pixel point is located; obtaining the enhanced remotely sensed image according to the weights of each neighboring pixel point of each pixel point.

[0084] More specifically, generally, the features (such as color, brightness, texture, etc.) of a neighboring pixel are highly consistent with the features of the central pixel. Then, when performing image enhancement, this neighboring pixel will be given a higher weight because it is more likely to contain information valuable to the central pixel. This mechanism ensures the local consistency and smoothness of image processing, enabling effective noise removal or other enhancement processing while retaining image edges and details. Within the window of each pixel point, when the features of the neighboring pixel points are more similar to the central pixel point, the greater their weights are, and accordingly, the weights of each neighboring pixel point within the window of each pixel point are determined. In this embodiment, the mathematical calculation formula for the weights of each neighboring pixel point within the window of each pixel point is constructed as follows:

[0085] ;

[0086] In the formula, represents the weight of the th neighboring pixel point within the window of the pixel point m in the remotely sensed image, where , represents the number of all neighboring pixel points within the window of the pixel point m; represents the difference between the product of the grayscale and gradient of pixel point m and that of the th neighborhood pixel within its window. Obviously, ; represents the difference in the local feature indices of the connected component where pixel point m and the th neighborhood pixel within its window are located.

[0087] Within the window of pixel point m in the remotely sensed image constructed above, in the mathematical calculation formula of the weight of the th neighborhood pixel, the difference between the product of the grayscale and gradient of pixel point m and that of the th neighborhood pixel within its window is smaller, and the difference in the local feature indices of the connected component where pixel point m and the th neighborhood pixel within its window are located is smaller, indicating that the characteristics of its neighborhood pixels are more consistent with those of the central pixel. Since it is more likely to contain information valuable to the central pixel, it needs to be assigned a higher weight.

[0088] Therefore, both the difference between the product of the grayscale and gradient of a pixel point and that of the first neighborhood pixel within its window and the difference in the local feature indices of the connected component where the pixel point and the neighborhood pixel within its window are located are negatively correlated with the weight of the neighborhood pixel within the window of the pixel point.

[0089] Step S6: Enhance the remotely sensed image according to the weight.

[0090] Specifically, for each pixel point in the remotely sensed image, according to the weight of each neighborhood pixel point of each pixel point, the grayscale values of all neighborhood pixel points within its window are weighted and summed, and the result is used as the new grayscale value of the central pixel point after filtering. The calculated weighted sum is assigned to the central pixel point to obtain the enhanced remotely sensed image.

[0091] In a second aspect, the present embodiment provides a remotely sensed image enhancement system based on visual analysis. Please refer to Figure 3 , which shows a block diagram of a remotely sensed image enhancement system based on visual analysis provided by an embodiment of the present invention. The system includes:

[0092] A preliminary connected component acquisition module 101, configured to obtain multiple preliminary connected components of the remotely sensed image through a connected component algorithm;

[0093] A connected component acquisition module 102, configured to obtain multiple connected components of the remotely sensed image according to the color, texture condition, area, and the shortest distance between all edge pixel points within each preliminary connected component;

[0094] The surface feature area acquisition module 103 is configured to cluster all connected components, and each obtained cluster represents a surface feature area;

[0095] The window side length acquisition module 104 is configured to obtain the window side length of a pixel according to the position of the pixel in its corresponding surface feature area, the gray variance within the connected component where the pixel is located, and the difference in local feature indices of the connected components on both sides of the pixel;

[0096] The weight acquisition module 105 is configured to obtain the weight of each neighboring pixel within the window of each pixel according to the gray level and gradient of each pixel and other neighboring pixels within its window;

[0097] The enhancement processing module 106 is configured to perform enhancement processing on the remote sensing image according to the weights of each neighboring pixel within the window of each pixel.

[0098] For the remote sensing image enhancement method and system provided in this embodiment, first, multiple preliminary connected components of the remote sensing image are obtained through the connected component algorithm; then, multiple connected components of the remote sensing image are obtained according to the color, texture condition, area, and the shortest distance between all edge pixels within each preliminary connected component. Further, all connected components are clustered, and each obtained cluster represents a surface feature area. The window side length of a pixel is obtained according to the position of the pixel in its corresponding surface feature area, the gray variance within the connected component where the pixel is located, and the difference in local feature indices of the connected components on both sides of the pixel. Finally, the weight of each neighboring pixel within the window of each pixel is obtained according to the gray level and gradient of each pixel and other neighboring pixels within its window, and the remote sensing image is enhanced according to the weights. Such a remote sensing image enhancement processing method can make the filtering result more accurately conform to the actual features of the image, retain key information, and improve the processing efficiency and visual effect.

[0099] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A remote sensing image enhancement method based on visual analysis, characterized in that: The method comprises: Step S1: obtaining multiple preliminary connected domains of the remote sensing image through a connected domain algorithm; Step S2: obtaining multiple connected domains of the remote sensing image according to the color, texture, area, and the shortest distance between all edge pixels in each preliminary connected domain; Step S3: clustering all connected domains, and each obtained cluster represents a surface feature area; Step S4: Obtain the window side length of a pixel point according to the position of the pixel point in the surface feature area where the pixel point is located, the grayscale variance in the connected domain where the pixel point is located, and the difference in local feature indexes of the connected domains on both sides of the pixel point; Step S5: Obtain the weight of each neighboring pixel in the window of each pixel according to the grayscale and gradient of each pixel and other neighboring pixels in its window; Step S6: performing enhancement processing on the remote sensing image according to the weight; The step S2 specifically includes: According to the grayscale value corresponding to the peak value of the grayscale histogram of a preliminary connected domain, the variance of the grayscale values ​​of all the pixels of the preliminary connected domain, and the mean value of the gradients of all the pixels of the preliminary connected domain, a local feature index of the preliminary connected domain is obtained; the grayscale value corresponding to the peak value of the grayscale histogram of the preliminary connected domain, the variance of the grayscale values ​​of all the pixels of the preliminary connected domain, and the mean value of the gradients of all the pixels of the preliminary connected domain are all positively correlated with the local feature index of the preliminary connected domain; According to the local feature index, area, and the shortest distance between all edge pixels of any two preliminary connected domains, the possibility of merging the two preliminary connected domains is obtained; the absolute value of the difference between the local feature indexes of any two preliminary connected domains and the shortest distance between all edge pixels of the two preliminary connected domains are negatively correlated with the possibility of merging the two preliminary connected domains, and the area difference between the two preliminary connected domains is positively correlated with the possibility of merging the two preliminary connected domains; According to the possibility of merging any two adjacent preliminary connected domains, a plurality of connected domains of the remote sensing image are obtained.

2. The remote sensing image enhancement method based on visual analysis according to claim 1, characterized in that: The step S3 specifically includes: The average value of the local feature indexes of all preliminary connected domains contained in the connected domain is taken as the local feature index of the connected domain; According to the local feature index of a connected domain and the peak value of the grayscale histogram of the connected domain, a clustering feature value of the connected domain is obtained; The difference in clustering feature values ​​between connected domains is used as the clustering distance, and all connected domains are clustered to obtain multiple clusters, each of which represents a surface feature area.

3. The remote sensing image enhancement method based on visual analysis according to claim 1, characterized in that: Step S4 specifically includes: When a pixel does not belong to an edge pixel, the distance between the pixel and the edge and the grayscale variance in the connected domain where the pixel is located are negatively correlated with the window side length of the pixel; When a pixel is an edge pixel, the difference in local feature index of the connected domains on both sides of the pixel is negatively correlated with the window side length of the pixel.

4. The remote sensing image enhancement method based on visual analysis according to claim 3 is characterized in that: Step S4 also includes: When a pixel is an edge pixel and the connected domains on both sides of the pixel are different surface feature areas, the longer the window side length of the pixel is.

5. The remote sensing image enhancement method based on visual analysis according to claim 1, characterized in that: The step S5 specifically includes: The weight of the neighboring pixel in the window of the pixel is obtained according to the difference between the grayscale and gradient product of a pixel and the first neighboring pixel in its window, and the difference between the local feature index of the connected domain where the pixel and the neighboring pixel in its window are located; According to the weight of each neighborhood pixel of each pixel, an enhanced remote sensing image is obtained.

6. The remote sensing image enhancement method based on visual analysis according to claim 5, characterized in that: The difference between the grayscale and gradient product of a pixel and the first neighboring pixel in its window, and the difference in the local feature index of the connected domain where the pixel and the neighboring pixel in its window are located are negatively correlated with the weight of the neighboring pixel in the window of the pixel.

7. The remote sensing image enhancement method based on visual analysis according to claim 5, characterized in that: Step S6: For each pixel in the remote sensing image, the grayscale values ​​of all neighboring pixels in its window are weighted and summed according to the weight of each neighboring pixel of each pixel. The result is used as the new grayscale value of the central pixel after filtering. The calculated weighted sum is assigned to the central pixel to obtain an enhanced remote sensing image.

8. A remote sensing image enhancement system based on visual analysis, characterized in that: The system comprises: A preliminary connected domain acquisition module is used to acquire multiple preliminary connected domains of a remote sensing image through a connected domain algorithm; A connected domain acquisition module is used to acquire multiple connected domains of the remote sensing image according to the color, texture, area, and the shortest distance between all edge pixels in each preliminary connected domain; The surface feature region acquisition module is used to cluster all connected domains, and each acquired cluster represents a surface feature region; The window side length acquisition module is used to obtain the window side length of a pixel point according to the position of the pixel point in the surface feature area where the pixel point is located, the grayscale variance in the connected domain where the pixel point is located, and the difference in local feature indexes of the connected domains on both sides of the pixel point; A weight acquisition module is used to obtain the weight of each neighboring pixel point in the window of each pixel point according to the grayscale and gradient of each pixel point and other neighboring pixel points in its window; An enhancement processing module, used for performing enhancement processing on the remote sensing image according to the weight; The connected domain acquisition module is specifically used to obtain the local feature index of a preliminary connected domain according to the gray value corresponding to the peak of the gray histogram of the preliminary connected domain, the variance of the gray values ​​of all pixels of the preliminary connected domain, and the mean of the gradients of all pixels of the preliminary connected domain; the gray value corresponding to the peak of the gray histogram of the preliminary connected domain, the variance of the gray values ​​of all pixels of the preliminary connected domain, and the mean of the gradients of all pixels of the preliminary connected domain are all positively correlated with the local feature index of the preliminary connected domain; And, according to the local feature index, area, and the shortest distance between all edge pixels of any two preliminary connected domains, the possibility of merging the two preliminary connected domains is obtained; the absolute value of the difference between the local feature indexes of any two preliminary connected domains and the shortest distance between all edge pixels of the any two preliminary connected domains are negatively correlated with the possibility of merging the two preliminary connected domains, and the area difference between the any two preliminary connected domains is positively correlated with the possibility of merging the two preliminary connected domains; And, according to the possibility of merging any two adjacent preliminary connected domains, a plurality of connected domains of the remote sensing image are obtained.

Images