Geographic information visualization analysis system based on remote sensing image

Abstract

The invention belongs to the field of geographic information analysis, relates to a data processing technology, and is used for solving the problem that the diversity of map segmentation cannot be improved by adopting a multi-mode segmentation mode in the prior art, in particular to a geographic information visualization analysis system based on a remote sensing image. Comprising an image processing module, a region segmentation module, a visual marking module, a highlighting analysis module and an evaluation analysis module, the image processing module, the region segmentation module, the visual marking module, the highlighting analysis module and the evaluation analysis module are sequentially in communication connection, and the highlighting analysis module and the evaluation analysis module are both in communication connection with the region segmentation module; according to the method, region segmentation processing can be carried out on the coverage image, the diversity of presentation results is improved by adopting a mode of randomly selecting multiple segmentation modes, so that when the prominence of the visual features is unqualified, other modes can be directly switched to continue segmentation processing, and the geographic information processing efficiency is improved.

Description

Technical Field

[0001] The invention belongs to the field of geographic information analysis and relates to data processing technology, in particular to a geographic information visualization analysis system based on remote sensing images. Background Art

[0002] The intuitive understanding of visualization is to transform it into visual perception. The basic meaning of visualization is to express the large amount of non-intuitive, abstract or invisible data generated in scientific computing in the form of graphic image information intuitively and vividly with the help of computer graphics and image processing technologies, and to conduct interactive processing.

[0003] The invention patent with announcement number CN111597288B discloses a three-dimensional geographic information visualization method and system based on video fusion. The three-dimensional geographic information visualization method optimizes the hardware performance allocation by dividing priorities to ensure the accuracy of the three-dimensional geographic information visualization results and the appearance of the picture. However, the three-dimensional geographic information visualization method cannot use a multi-mode segmentation method to improve the diversity of map segmentation, nor can it ensure the intuitiveness of the visualized geographic information by prominence verification.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a geographic information visualization analysis system based on remote sensing images, which is used to solve the problem that the prior art cannot improve the diversity of map segmentation by adopting a multi-mode segmentation method;

[0006] The technical problem to be solved by the present invention is: how to provide a geographic information visualization analysis system based on remote sensing images that can improve the diversity of map segmentation by adopting a multi-mode segmentation method.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A geographic information visualization analysis system based on remote sensing images comprises an image processing module, a region segmentation module, a visualization marking module, a highlight analysis module and an evaluation analysis module; the image processing module, the region segmentation module, the visualization marking module, the highlight analysis module and the evaluation analysis module are sequentially connected in communication, and the highlight analysis module and the evaluation analysis module are both connected in communication with the region segmentation module;

[0009] The image processing module is used to process and analyze the satellite remote sensing image and obtain the coverage image;

[0010] The region segmentation module is used to perform region segmentation processing on the coverage image: randomly select a segmentation mode to perform region segmentation processing on the coverage image to obtain L1 coverage areas, and the segmentation modes include: grid mode, filling mode and random mode;

[0011] The visual marking module is used to mark the visual features of the covered image and obtain the gray value of the covered area, and fill the covered area with grayscale according to the gray value;

[0012] The prominence analysis module is used to analyze the prominence of the visual features of the cover image, generate a processing completion signal when the prominence meets the requirements and send the processing completion signal to the evaluation and analysis module, and generate a re-segmentation signal when the prominence does not meet the requirements and send the re-segmentation signal to the region segmentation module;

[0013] The evaluation and analysis module is used to evaluate and analyze the visualization processing process of the coverage image.

[0014] Furthermore, the process of acquiring the overlay image includes: acquiring satellite remote sensing images containing stereo image pairs, using the information of the stereo image pairs to determine the three-dimensional coordinates of the surface features, thereby establishing a complete three-dimensional geographic information model, generating a bird's-eye view two-dimensional geographic information map based on the three-dimensional geographic information model and marking it as an overlay image.

[0015] Furthermore, the specific process of using the grid pattern to perform region segmentation processing includes: dividing the cover image into L1 coverage areas by a number of horizontal lines and a number of vertical lines in the cover image, and the distance between any two adjacent horizontal lines is equal to the distance between any two adjacent vertical lines; the specific process of using the filling pattern to perform region segmentation processing includes: contact filling of circular coverage areas from the corner points and edge lines of the cover image to the center point, the number of filled circular coverage areas is L1, and the area value of each coverage area is equal; the specific process of using the random pattern to perform region segmentation processing includes: randomly dividing the cover image into L1 coverage areas, and the coverage areas that are not in contact with the edge lines of the cover image are in contact with at least any other L2 coverage areas.

[0016] Furthermore, the process of obtaining the gray value of the covered area includes: forming an altitude range by the lowest altitude value and the highest altitude value of the three-dimensional coordinates corresponding to the covered image, dividing the altitude range into M1 altitude intervals, marking the average value of the maximum boundary value and the minimum boundary value of the altitude interval as the characteristic value of the altitude interval, dividing the grayscale range of 0-255 into M1 grayscale intervals, marking the average value of the maximum boundary value and the minimum boundary value of the grayscale interval as the expression value of the grayscale interval; matching the M1 altitude intervals with the M1 grayscale intervals in the order of increasing characteristic values ​​and expression values; calculating the average altitude value of the covered area, and marking the expression value of the grayscale interval corresponding to the altitude interval to which the average altitude value belongs as the gray value of the covered area.

[0017] Furthermore, the specific process of the salient analysis module analyzing the saliency of the visual features of the coverage image includes: randomly selecting a coverage area and marking it as an analysis area, calculating the variance of the gray value of the analysis area and all adjacent coverage areas to obtain the saliency value of the analysis area, then selecting the next coverage area and marking it as the analysis area, and so on, until all coverage areas are marked as analysis areas and the corresponding saliency values ​​are obtained, summing and averaging the saliency values ​​of all coverage areas to obtain a saliency coefficient, comparing the saliency coefficient with a preset saliency threshold, and judging whether the saliency of the visual features of the coverage image meets the requirements through the comparison result.

[0018] Furthermore, the specific process of comparing the prominence coefficient with the preset prominence threshold includes: if the prominence coefficient is less than the prominence threshold, it is determined that the prominence of the visualization feature of the overlay image does not meet the requirements; if the prominence coefficient is greater than or equal to the prominence threshold, it is determined that the prominence of the visualization feature of the overlay image meets the requirements, and the overlay image after grayscale filling is output.

[0019] Furthermore, the specific process of the evaluation and analysis module evaluating and analyzing the visualization processing process of the cover image includes: generating an evaluation cycle, obtaining the number of times the evaluation and analysis module receives the segmentation optimization signal and the number of times the processing completion signal within the evaluation cycle and marking them as the optimization value and the processing value respectively, marking the ratio of the optimization value to the processing value as the optimization coefficient, and comparing the optimization coefficient with a preset optimization threshold: if the optimization coefficient is greater than or equal to the optimization threshold, it is determined that the evaluation cycle has the necessity of segmentation optimization, generating an optimization execution signal and sending the optimization execution signal to the administrator's mobile phone terminal; if the optimization coefficient is less than the optimization threshold, the segmentation mode selection method is deeply analyzed.

[0020] Furthermore, when the region segmentation module receives the re-segmentation signal, it randomly selects from the remaining segmentation patterns and re-segments the coverage area according to the selected segmentation pattern. If the coverage areas segmented by all the segmentation patterns cannot meet the prominence of the visual features of the coverage image, a segmentation optimization signal is generated and sent to the evaluation and analysis module.

[0021] The present invention has the following beneficial effects:

[0022] 1. The regional segmentation module can be used to perform regional segmentation processing on the coverage image. A variety of segmentation modes are randomly selected to improve the diversity of the presentation results. The information features of the coverage area obtained by segmentation processing with different segmentation logics are quite different. Therefore, when the prominence of the visualization feature is not up to standard, other modes can be directly switched to continue the segmentation processing to improve the efficiency of geographic information processing;

[0023] 2. The visual marking module can be used to mark the visual features of the coverage image. After comparing the altitude interval with the grayscale interval, the corresponding grayscale value can be retrieved according to the altitude value to fill the grayscale of the coverage area, giving intuitive altitude features to different coverage areas;

[0024] 3. The prominence of the visual features of the coverage image can be analyzed through the prominence analysis module. After completing a region segmentation, the prominence values ​​of all coverage areas are numerically calculated to obtain the prominence coefficient. The prominence coefficient is a numerical value used to reflect the color prominence of each coverage area in the coverage image, thereby ensuring the presentation effect of the segmented coverage image;

[0025] 4. The evaluation and analysis module can be used to evaluate and analyze the visualization process of the coverage image, and the optimization coefficient can be obtained by comprehensively analyzing the relevant parameters of the regional segmentation processing according to different segmentation modes. When necessary, the segmentation mode can be optimized. When the segmentation mode does not require segmentation optimization, its selection logic can be optimized to further improve the efficiency of geographic information visualization processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 only 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.

[0027] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0028] Figure 2This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0030] Embodiment 1: Figure 1 As shown, the geographic information visualization analysis system based on remote sensing images includes an image processing module, a region segmentation module, a visualization marking module, a highlight analysis module and an evaluation analysis module; the image processing module, the region segmentation module, the visualization marking module, the highlight analysis module and the evaluation analysis module are communicatively connected in sequence, and the highlight analysis module and the evaluation analysis module are both communicatively connected with the region segmentation module.

[0031] The image processing module is used to process and analyze satellite remote sensing images: obtain satellite remote sensing images containing stereo image pairs, use the information of the stereo image pairs to determine the three-dimensional coordinates of the surface features, thereby establishing a complete three-dimensional geographic information model, and generate a bird's-eye view two-dimensional geographic information map based on the three-dimensional geographic information model and mark it as a coverage image; send the coverage image to the regional segmentation module.

[0032] The region segmentation module is used to perform region segmentation processing on the coverage image: randomly select a segmentation mode to perform region segmentation processing on the coverage image to obtain L1 coverage areas, and the segmentation modes include: grid mode, filling mode and random mode; the specific process of using the grid mode to perform region segmentation processing includes: in the coverage image, the coverage image is divided into L1 coverage areas by a number of horizontal lines and a number of vertical lines, and the distance between any two adjacent horizontal lines is equal to the distance between any two adjacent vertical lines; the specific process of using the filling mode to perform region segmentation processing includes: contact filling of circular coverage areas from the corner points and edge lines of the coverage image to the center point, the number of filled circular coverage areas is L1, and the area value of each coverage area is equal; the specific process of using the random mode to perform region segmentation processing includes: randomly dividing the coverage image into L1 coverage areas The coverage area, and the coverage area that does not touch the edge line of the coverage image is in contact with at least any other L2 coverage areas; L1 and L2 are both numerical constants, and the specific values ​​of L1 and L2 are set by the management personnel; when the area segmentation module receives the re-segmentation signal, it randomly selects from the remaining segmentation modes, and re-segments the coverage area according to the selected segmentation mode. If the coverage areas segmented by all the segmentation modes cannot meet the prominence of the visualization features of the coverage image, a segmentation optimization signal is generated and sent to the evaluation and analysis module; a variety of segmentation modes are randomly selected to improve the diversity of the presentation results, and the information features of the coverage areas obtained by segmentation processing with different segmentation logics are quite different. Therefore, when the prominence of the visualization features is not up to standard, other modes can be directly switched to continue the segmentation processing, thereby improving the efficiency of geographic information processing.

[0033] The visual marking module is used to mark the visual features of the coverage image: the lowest altitude value and the highest altitude value of the corresponding three-dimensional coordinates of the coverage image constitute the altitude range, the altitude range is divided into M1 altitude intervals, the average value of the maximum boundary value and the minimum boundary value of the altitude interval is marked as the characteristic value of the altitude interval, the grayscale range of 0-255 is divided into M1 grayscale intervals, and the average value of the maximum boundary value and the minimum boundary value of the grayscale interval is marked as the performance value of the grayscale interval; M1 altitude intervals and M1 grayscale intervals are matched in the order of increasing characteristic values ​​and performance values, M1 is a numerical constant, and the specific value of M1 is set by the management personnel; the average altitude value of the coverage area is calculated, the performance value of the grayscale interval corresponding to the altitude interval to which the average altitude value belongs is marked as the gray value of the coverage area, and the coverage area is gray-filled according to the gray value; after comparing the altitude interval with the grayscale interval, the corresponding gray value can be retrieved according to the altitude value to fill the coverage area with grayscale, giving intuitive altitude features to different coverage areas.

[0034] The salient analysis module is used to analyze the salientness of the visual features of the overlay image: randomly select a covered area and mark it as the analysis area, calculate the variance of the gray value of the analysis area and all adjacent covered areas to obtain the salient value of the analysis area, then select the next covered area and mark it as the analysis area, and so on, until all covered areas are marked as analysis areas and the corresponding salient values ​​are obtained, sum and average the salient values ​​of all covered areas to obtain the salient coefficient, and compare the salient coefficient with the preset salient threshold: if the salient coefficient is less than the salient threshold, it is determined that the salientness of the visual features of the overlay image does not meet the requirements; generate a re-segmentation signal and send the re-segmentation signal to the area segmentation module; if the salient coefficient is greater than or equal to the salient threshold, it is determined that the salientness of the visual features of the overlay image meets the requirements, the grayscale filled overlay image is output, generate a processing completion signal and send the processing completion signal to the evaluation and analysis module; after completing one area segmentation, the salient values ​​of all covered areas are numerically calculated to obtain the salient coefficient, which is a numerical value used to reflect the degree of color salientness of each covered area in the overlay image, thereby ensuring the presentation effect of the segmented overlay image.

[0035] The evaluation and analysis module is used to evaluate and analyze the visualization processing of the overlay image: generate an evaluation cycle, obtain the number of times the evaluation and analysis module receives the segmentation optimization signal and the number of times the processing completion signal is received within the evaluation cycle, and mark them as the optimization value and the processing value respectively, mark the ratio of the optimization value to the processing value as the optimization coefficient, and compare the optimization coefficient with the preset optimization threshold: if the optimization coefficient is greater than or equal to the optimization threshold, it is determined that the evaluation cycle has the necessity of segmentation optimization, generate an optimization execution signal and send the optimization execution signal to the mobile phone terminal of the administrator; if the optimization coefficient is less than the optimization threshold, then the selection method of the segmentation mode is deeply analyzed: when the prominence of the visualization features of the overlay image meets the requirements, the number of times the corresponding grid mode, fill mode and random mode are selected is marked as the grid selected value, fill selected value and random selected value respectively; the sum of the grid selected value, fill selected value and random selected value is marked as the statistical value, and the ratio of the grid selected value, fill selected value, random selected value to the statistical value is calculated. They are marked as grid priority value, filling priority value and random priority value respectively; the variance of grid priority value, filling priority value and random priority value is calculated to obtain the concentration coefficient, and the concentration coefficient is compared with the concentration threshold: if the concentration coefficient is less than the concentration threshold, the random selection weights of the grid mode, filling mode and random mode in the next evaluation cycle are marked as grid priority value, filling priority value and random priority value respectively; if the concentration coefficient is greater than or equal to the concentration threshold, the grid mode, filling mode and random mode are arranged in descending order according to the corresponding grid priority value, filling priority value and random priority value to obtain the priority order, and the segmentation mode is selected according to the priority order in the next evaluation cycle; the relevant parameters of regional segmentation processing according to different segmentation modes are comprehensively analyzed to obtain the optimization coefficient, and the segmentation mode is optimized when necessary. When the segmentation mode does not have the necessity of segmentation optimization, its selection logic is optimized to further improve the efficiency of geographic information visualization processing.

[0036] Embodiment 2: Figure 2 As shown in FIG. 1 , the geographic information visualization analysis method based on remote sensing images includes the following steps:

[0037] Step 1: Process and analyze satellite remote sensing images and obtain coverage images;

[0038] Step 2: Perform region segmentation on the coverage image and obtain L1 coverage areas;

[0039] Step 3: Mark the visual features of the coverage image and obtain the gray value of the coverage area, and fill the coverage area with grayscale according to the gray value;

[0040] Step 4: Analyze the prominence of the visual features of the grayscale filled cover image. If the prominence meets the requirements, execute step 5; if the prominence does not meet the requirements, execute step 2.

[0041] Step 5: Evaluate and analyze the visualization process of the overlay image.

[0042] The geographic information visualization analysis system based on remote sensing images processes and analyzes the satellite remote sensing images and obtains the coverage images; performs regional segmentation processing on the coverage images and obtains L1 coverage areas; marks the visualization features of the coverage images and obtains the gray value of the coverage areas, and grayscale fills the coverage areas according to the gray value; analyzes the prominence of the visualization features of the coverage images after grayscale filling, and evaluates and analyzes the visualization processing of the coverage images when the prominence meets the requirements; and re-segmentates the coverage areas when the prominence does not meet the requirements.

[0043] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0045] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A geographic information visualization analysis system based on remote sensing images, characterized in that: It includes an image processing module, a region segmentation module, a visual marking module, a highlight analysis module and an evaluation analysis module; the image processing module, the region segmentation module, the visual marking module, the highlight analysis module and the evaluation analysis module are sequentially connected in communication, and the highlight analysis module and the evaluation analysis module are both connected in communication with the region segmentation module; The image processing module is used to process and analyze the satellite remote sensing image and obtain the coverage image; The region segmentation module is used to perform region segmentation processing on the coverage image: randomly select a segmentation mode to perform region segmentation processing on the coverage image to obtain L1 coverage areas, and the segmentation modes include: grid mode, filling mode and random mode; The visual marking module is used to mark the visual features of the covered image and obtain the gray value of the covered area, and fill the covered area with grayscale according to the gray value; The prominence analysis module is used to analyze the prominence of the visual features of the cover image, generate a processing completion signal when the prominence meets the requirements and send the processing completion signal to the evaluation and analysis module, and generate a re-segmentation signal when the prominence does not meet the requirements and send the re-segmentation signal to the region segmentation module; The evaluation and analysis module is used to evaluate and analyze the visualization processing process of the coverage image.

2. The geographic information visualization analysis system based on remote sensing images according to claim 1 is characterized in that: The process of acquiring the overlay image includes: acquiring satellite remote sensing images containing stereo image pairs, using the information of the stereo image pairs to determine the three-dimensional coordinates of the surface features, thereby establishing a complete three-dimensional geographic information model, and generating a bird's-eye view two-dimensional geographic information map based on the three-dimensional geographic information model and marking it as an overlay image.

3. The geographic information visualization analysis system based on remote sensing images according to claim 2 is characterized in that: The specific process of using the grid pattern to perform region segmentation processing includes: dividing the cover image into L1 coverage areas by a number of horizontal lines and a number of vertical lines in the cover image, and the distance between any two adjacent horizontal lines is equal to the distance between any two adjacent vertical lines; the specific process of using the filling pattern to perform region segmentation processing includes: contact filling of circular coverage areas from the corner points and edge lines of the cover image to the center point, the number of filled circular coverage areas is L1, and the area value of each coverage area is equal; the specific process of using the random pattern to perform region segmentation processing includes: randomly dividing the cover image into L1 coverage areas, and the coverage areas that are not in contact with the edge lines of the cover image are in contact with at least any other L2 coverage areas.

4. The geographic information visualization analysis system based on remote sensing images according to claim 3 is characterized in that: The process of obtaining the gray value of the covered area includes: forming an altitude range by the lowest altitude value and the highest altitude value of the three-dimensional coordinates corresponding to the covered image, dividing the altitude range into M1 altitude intervals, marking the average value of the maximum boundary value and the minimum boundary value of the altitude interval as the characteristic value of the altitude interval, dividing the grayscale range of 0-255 into M1 grayscale intervals, marking the average value of the maximum boundary value and the minimum boundary value of the grayscale interval as the expression value of the grayscale interval; matching the M1 altitude intervals with the M1 grayscale intervals in the order of increasing characteristic values ​​and expression values; calculating the average altitude value of the covered area, and marking the expression value of the grayscale interval corresponding to the altitude interval to which the average altitude value belongs as the gray value of the covered area.

5. The geographic information visualization analysis system based on remote sensing images according to claim 4 is characterized in that: The specific process of the salient analysis module analyzing the saliency of the visual features of the coverage image includes: randomly selecting a coverage area and marking it as the analysis area, calculating the variance of the gray value of the analysis area and all adjacent coverage areas to obtain the saliency value of the analysis area, then selecting the next coverage area and marking it as the analysis area, and so on, until all coverage areas are marked as analysis areas and the corresponding saliency values ​​are obtained, summing and averaging the saliency values ​​of all coverage areas to obtain the saliency coefficient, comparing the saliency coefficient with the preset saliency threshold, and judging whether the saliency of the visual features of the coverage image meets the requirements through the comparison results.

6. The geographic information visualization analysis system based on remote sensing images according to claim 5 is characterized in that: The specific process of comparing the prominence coefficient with the preset prominence threshold includes: if the prominence coefficient is less than the prominence threshold, it is determined that the prominence of the visualization feature of the overlay image does not meet the requirements; if the prominence coefficient is greater than or equal to the prominence threshold, it is determined that the prominence of the visualization feature of the overlay image meets the requirements, and the overlay image after grayscale filling is output.

7. The geographic information visualization analysis system based on remote sensing images according to claim 6 is characterized in that: The specific process of the evaluation and analysis module evaluating and analyzing the visualization processing of the overlay image includes: generating an evaluation cycle, obtaining the number of times the evaluation and analysis module receives the segmentation optimization signal and the number of times the processing completion signal within the evaluation cycle and marking them as the optimization value and the processing value respectively, marking the ratio of the optimization value to the processing value as the optimization coefficient, and comparing the optimization coefficient with the preset optimization threshold: if the optimization coefficient is greater than or equal to the optimization threshold, it is determined that the evaluation cycle has the necessity of segmentation optimization, generating an optimization execution signal and sending the optimization execution signal to the administrator's mobile terminal; if the optimization coefficient is less than the optimization threshold, the segmentation mode selection method is deeply analyzed.

8. The geographic information visualization analysis system based on remote sensing images according to claim 7 is characterized in that: When the region segmentation module receives the re-segmentation signal, it randomly selects from the remaining segmentation patterns and re-segments the coverage area according to the selected segmentation pattern. If the coverage areas segmented by all segmentation patterns cannot meet the prominence of the visual features of the coverage image, a segmentation optimization signal is generated and sent to the evaluation and analysis module.

Images