Land space planning auxiliary compilation method and system based on big data

Abstract

The invention discloses a homeland space planning auxiliary compilation method and system based on big data, and belongs to the technical field of land planning, and the method specifically comprises the steps: obtaining a remote sensing image map of a target region, and carrying out the land recognition of the remote sensing image map, and obtaining a specific position region and a region area of any land type in the target region; the method comprises the following steps: acquiring pre-planning information, calculating to obtain a to-be-planned area of any land type, screening lands of a target region, screening out a to-be-planned region corresponding to the to-be-planned area most conforming to the land type, and taking the to-be-planned region as an optimal planning region of the land type; and determining an optimal planning area of any land type, drawing a target boundary line corresponding to the optimal planning area, and outputting a planning remote sensing image map. According to the method, the land is planned by comprehensively considering the topographic features on the basis of the existing land planning of the target area, so that the accuracy of the land planning result is improved, the land resource allocation is optimized, and the planning operability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of land planning, and in particular to a method and system for auxiliary compilation of national land space planning based on big data. Background Art

[0003] Planning preparation is the primary link in planning work. Various indicators of land resources need to be evaluated during planning preparation. At present, it is completed manually through division of labor and cooperation, which makes it difficult to carry out unified planning management of spatial planning projects and has low efficiency. At the same time, there are many complex analysis and calculation problems in planning work. For example, important business functions such as double evaluation analysis and urban-rural boundary prediction are complex to calculate manually, with a large workload, time-consuming and labor-intensive. How to make the planning preparation business process simpler and improve the work efficiency of the compilers is an important starting point for promoting the modernization of the national land space planning governance system and governance capabilities. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for assisting the compilation of national land space planning based on big data, so as to solve the following technical problems:

[0005] Planning preparation is the primary link in planning work. Various indicators of land resources need to be evaluated during planning preparation. At present, it is completed manually through division of labor and cooperation, which makes it difficult to carry out unified planning management of spatial planning projects and has low efficiency. At the same time, there are many complex analysis and calculation problems in planning work. For example, important business functions such as double evaluation analysis and urban-rural boundary prediction are complex to calculate manually, with a large workload, time-consuming and labor-intensive. How to make the planning preparation business process simpler and improve the work efficiency of the compilers is an important starting point for promoting the modernization of the national land space planning governance system and governance capabilities.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for assisting the preparation of national land space planning based on big data, characterized in that it comprises the following steps:

[0008] S1, obtaining a remote sensing image of the target area, and performing land recognition on the remote sensing image to obtain the specific location area, area and total area proportion of any land type in the target area, wherein the land types include farmland type, town type and ecological protection type;

[0009] S2, obtaining pre-planning information to calculate the area to be planned of any land type, screening the land in the target area in the order of ecology, farmland and town according to the area to be planned, screening the area to be planned corresponding to the area to be planned that best matches the land type, and taking the area to be planned as the optimal planning area for the land type;

[0010] S3, determining the optimal planning area of ​​any land type and drawing its corresponding target boundary line, and outputting a planning remote sensing image map containing the target boundary line.

[0011] As a further solution of the present invention: In S1, the specific process of identification is:

[0012] Perform edge detection on the remote sensing image, and divide the remote sensing image into several sub-images according to the detection results, perform HSV color space conversion on any of the sub-images to obtain an HSV color matrix and perform Haar transformation, normalize the matrix after Haar transformation to obtain a 256-dimensional color feature vector M; perform grayscale processing on the sub-image to obtain a grayscale image, perform texture feature extraction on the grayscale image to obtain the roughness, contrast and orientation values ​​of the grayscale image and perform normalization to obtain a texture feature vector N, substitute the color feature vector and texture feature vector into a preset recognition model to obtain the land category of each sub-image.

[0013] As a further solution of the present invention: in S2, the specific process of screening is:

[0014] S11, extracting geographic data from the remote sensing image to generate a geographic feature data set; performing elevation conversion on the geographic feature data set to generate geographic elevation data; performing terrain feature analysis on the geographic elevation data to generate terrain feature analysis data; performing land cover classification on the standard land resource field survey data to generate land cover classification areas; performing regional feature clustering based on the land cover classification areas and terrain feature analysis data to generate a number of feature areas; obtaining the land type in any feature area, and if there are two or more land types, marking the feature area as a pending area;

[0015] S12, select any land type and mark it as the target land type, obtain the area X to be planned of the target land type, screen out all characteristic areas containing the target land type from the to-be-determined area and mark them as target areas, respectively obtain the areas A1, A2, ..., An of all target areas and the areas a1, a2, ..., an corresponding to the land type in the target area, and calculate the remaining planning area A' of any target area according to the calculation formula A'=Ai-ai, where i is the i-th target area;

[0016] S13, selecting all target areas whose remaining planning area A' is greater than or equal to the area to be planned X, scoring each target area in turn, and selecting the target area with the highest score as the optimal planning area corresponding to the land type.

[0017] As a further solution of the present invention: in S13, the specific process of planning scoring is:

[0018] X' = ​​min|XA"i|;

[0019]

[0020] Wherein, A”i represents the area corresponding to the i-th land type in the remaining land types, Dx' is the characteristic distance between the characteristic areas of the land type, and u is the preset correction coefficient.

[0021] As a further solution of the present invention: the specific calculation process of the characteristic distance Dx' is:

[0022] Perform edge detection on the target area, and divide the target area into multiple sub-areas according to the detection results, mark the sub-area belonging to the target land type as the target sub-area, mark the land type corresponding to X' as the comparison land type, and mark the sub-area belonging to the target land type as the comparison sub-area. Establish a rectangular coordinate system with the center point of the target area as the origin, obtain the midpoint position of any comparison sub-area and mark it as (X, Y), calculate the distance D from the midpoint of the comparison sub-area to all edge points of the target sub-area, and select the minimum value as the feature distance Dx'.

[0023] As a further solution of the present invention: if there are multiple target sub-regions and / or multiple comparison sub-regions in the target region, then according to the calculation formula Wherein, M is the total number of contrast sub-regions, Xk is the horizontal coordinate of the midpoint of the kth contrast sub-region, Yk is the vertical coordinate of the midpoint of the kth contrast sub-region, xlp represents the horizontal coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, ylp represents the vertical coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, and p is greater than or equal to 1.

[0024] As a further solution of the present invention: if there are two or more target areas with equal planning scores and both are maximum values, then the target area with the smallest X' is selected as the optimal planning area corresponding to the land type.

[0025] A national land space planning auxiliary compilation system based on big data, characterized by comprising:

[0026] A data acquisition module is used to acquire a remote sensing image of a target area, and to perform land recognition on the remote sensing image to obtain a specific location area, area, and total area ratio of any land type in the target area, wherein the land types include farmland type, town type, and ecological protection type;

[0027] A data analysis module is used to calculate the area to be planned of any land type according to the pre-planning information, and screen the land in the target area in the order of ecology, farmland and town according to the area to be planned, and screen out the area to be planned corresponding to the area to be planned that best matches the land type, and use the area to be planned as the optimal planning area for the land type;

[0028] The result generation module is used to determine the optimal planning area of ​​any land type and draw its corresponding target boundary line, and output the planning remote sensing image map containing the target boundary line.

[0029] Beneficial effects of the present invention:

[0030] The present invention obtains a remote sensing image of a target area, and performs land recognition on the remote sensing image to obtain the specific location area, area and total area proportion of any land type in the target area, so as to provide a reliable basis for subsequent analysis and decision-making, obtains pre-planning information to calculate the area to be planned of any land type, and screens the land in the target area in the order of ecology, farmland and town according to the area to be planned, and generates a terrain feature data set and clusters it by extracting geographic information features to generate a number of feature areas; this can group adjacent plots with similar landforms and land coverage, obtain the land type in any feature area, and if there are two or more land types, mark the feature area as a pending area; It can be understood that when there are different land uses in areas with similar landforms and land cover, they can be given priority when conducting land planning. Similar landforms and land cover usually mean similar environmental conditions and resource distribution, which makes certain land uses more feasible and sustainable in these areas. Giving priority to these areas can improve land use efficiency, reduce ecological impacts, and better meet specific socio-economic needs. The area of ​​all target areas and the area corresponding to the land type in the target area are obtained respectively, and all target areas with remaining planning areas greater than or equal to the area to be planned X are selected. Each target area is scored for planning in turn, and the target area with the highest score is used as the optimal planning area corresponding to the land type, thereby realizing the identification and optimization of the land planning area. The present invention comprehensively considers the terrain characteristics to plan the land in the existing land planning of the target area, improves the accuracy of the land planning results, optimizes the allocation of land resources, and improves the operability of the planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Figure 1 It is a flow chart of a method for assisting in compiling national land space planning based on big data according to the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0034] See also Figure 1 As shown, the present invention is a method for assisting in compiling land space planning based on big data, comprising the following steps:

[0035] S1, obtaining a remote sensing image of the target area, and performing land recognition on the remote sensing image to obtain the specific location area, area and total area proportion of any land type in the target area, wherein the land types include farmland type, town type and ecological protection type;

[0036] S2, obtaining pre-planning information to calculate the area to be planned of any land type, screening the land in the target area in the order of ecology, farmland and town according to the area to be planned, screening the area to be planned corresponding to the area to be planned that best matches the land type, and taking the area to be planned as the optimal planning area for the land type;

[0037] S3, determining the optimal planning area of ​​any land type and drawing its corresponding target boundary line, and outputting a planning remote sensing image map containing the target boundary line.

[0038] The present invention obtains a remote sensing image of a target area, and performs land recognition on the remote sensing image to obtain the specific location area, area and total area proportion of any land type in the target area, so as to provide a reliable basis for subsequent analysis and decision-making, obtains pre-planning information to calculate the area to be planned of any land type, and screens the land in the target area in the order of ecology, farmland and town according to the area to be planned, and generates a terrain feature data set and clusters it by extracting geographic information features to generate a number of feature areas; this can group adjacent plots with similar landforms and land coverage, obtain the land type in any feature area, and if there are two or more land types, mark the feature area as a pending area; It can be understood that when there are different land uses in areas with similar landforms and land cover, they can be given priority when conducting land planning. Similar landforms and land cover usually mean similar environmental conditions and resource distribution, which makes certain land uses more feasible and sustainable in these areas. Giving priority to these areas can improve land use efficiency, reduce ecological impacts, and better meet specific socio-economic needs. The area of ​​all target areas and the area corresponding to the land type in the target area are obtained respectively, and all target areas with remaining planning areas greater than or equal to the area to be planned X are selected. Each target area is scored for planning in turn, and the target area with the highest score is used as the optimal planning area corresponding to the land type, thereby realizing the identification and optimization of the land planning area. The present invention comprehensively considers the terrain characteristics to plan the land in the existing land planning of the target area, improves the accuracy of the land planning results, optimizes the allocation of land resources, and improves the operability of the planning.

[0039] In another preferred embodiment of the present invention, in S1, the specific process of identification is:

[0040] Perform edge detection on the remote sensing image, and divide the remote sensing image into several sub-images according to the detection results, perform HSV color space conversion on any of the sub-images to obtain an HSV color matrix and perform Haar transformation, normalize the matrix after Haar transformation to obtain a 256-dimensional color feature vector M; perform grayscale processing on the sub-image to obtain a grayscale image, perform texture feature extraction on the grayscale image to obtain the roughness, contrast and orientation values ​​of the grayscale image and perform normalization to obtain a texture feature vector N, substitute the color feature vector and texture feature vector into a preset recognition model to obtain the land category of each sub-image.

[0041] In another preferred embodiment of the present invention, in S2, the specific process of screening is:

[0042] S11, extracting geographic data from the remote sensing image to generate a geographic feature data set; performing elevation conversion on the geographic feature data set to generate geographic elevation data; performing terrain feature analysis on the geographic elevation data to generate terrain feature analysis data; performing land cover classification on the standard land resource field survey data to generate land cover classification areas; performing regional feature clustering based on the land cover classification areas and terrain feature analysis data to generate a number of feature areas; obtaining the land type in any feature area, and if there are two or more land types, marking the feature area as a pending area;

[0043] S12, select any land type and mark it as the target land type, obtain the area X to be planned of the target land type, screen out all characteristic areas containing the target land type from the to-be-determined area and mark them as target areas, respectively obtain the areas A1, A2, ..., An of all target areas and the areas a1, a2, ..., an corresponding to the land type in the target area, and calculate the remaining planning area A' of any target area according to the calculation formula A'=Ai-ai, where i is the i-th target area;

[0044] S13, selecting all target areas whose remaining planning area A' is greater than or equal to the area to be planned X, scoring each target area in turn, and selecting the target area with the highest score as the optimal planning area corresponding to the land type.

[0045] In another preferred embodiment of the present invention, in S13, the specific process of planning scoring is:

[0046] X' = ​​min|XA"i|;

[0047]

[0048] Wherein, A”i represents the area corresponding to the i-th land type in the remaining land types, Dx' is the characteristic distance between the characteristic areas of the land type, and u is the preset correction coefficient.

[0049] In another preferred embodiment of the present invention, the specific calculation process of the characteristic distance Dx' is:

[0050] Perform edge detection on the target area, and divide the target area into multiple sub-areas according to the detection results, mark the sub-area belonging to the target land type as the target sub-area, mark the land type corresponding to X' as the comparison land type, and mark the sub-area belonging to the target land type as the comparison sub-area. Establish a rectangular coordinate system with the center point of the target area as the origin, obtain the midpoint position of any comparison sub-area and mark it as (X, Y), calculate the distance D from the midpoint of the comparison sub-area to all edge points of the target sub-area, and select the minimum value as the feature distance Dx'.

[0051] In another preferred embodiment of the present invention, the target area includes multiple target sub-areas and / or multiple comparison sub-areas, and according to the calculation formula Wherein, M is the total number of contrast sub-regions, Xk is the horizontal coordinate of the midpoint of the kth contrast sub-region, Yk is the vertical coordinate of the midpoint of the kth contrast sub-region, xlp represents the horizontal coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, ylp represents the vertical coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, and p is greater than or equal to 1.

[0052] In another preferred embodiment of the present invention, if there are two or more target areas with equal planning scores and both are maximum values, the target area with the smallest X' is selected as the optimal planning area corresponding to the land type.

[0053] A national land space planning auxiliary compilation system based on big data, characterized by comprising:

[0054] A data acquisition module is used to acquire a remote sensing image of a target area, and to perform land recognition on the remote sensing image to obtain a specific location area, area, and total area ratio of any land type in the target area, wherein the land types include farmland type, town type, and ecological protection type;

[0055] A data analysis module is used to calculate the area to be planned of any land type according to the pre-planning information, and screen the land in the target area in the order of ecology, farmland and town according to the area to be planned, and screen out the area to be planned corresponding to the area to be planned that best matches the land type, and use the area to be planned as the optimal planning area for the land type;

[0056] The result generation module is used to determine the optimal planning area of ​​any land type and draw its corresponding target boundary line, and output the planning remote sensing image map containing the target boundary line.

[0057] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for assisting the preparation of national land space planning based on big data, characterized in that: The following steps are involved: S1, obtaining a remote sensing image of the target area and performing land identification on the remote sensing image to obtain the specific location area, area and total area proportion of any land type in the target area, wherein the land types include farmland type, town type and ecological protection type; S2, obtaining pre-planning information to calculate the area to be planned of any land type, screening the land in the target area in the order of ecology, farmland and town according to the area to be planned, screening the area to be planned corresponding to the area to be planned that best matches the land type, and taking the area to be planned as the optimal planning area for the land type; S3, determining the optimal planning area of ​​any land type and drawing its corresponding target boundary line, and outputting a planning remote sensing image map containing the target boundary line.

2. According to the big data-based national land space planning auxiliary compilation method of claim 1, it is characterized in that: In S1, the specific process of identification is: Perform edge detection on the remote sensing image, and divide the remote sensing image into several sub-images according to the detection results, perform HSV color space conversion on any of the sub-images to obtain an HSV color matrix and perform Haar transformation, normalize the matrix after Haar transformation to obtain a 256-dimensional color feature vector M; perform grayscale processing on the sub-image to obtain a grayscale image, perform texture feature extraction on the grayscale image to obtain the roughness, contrast and orientation values ​​of the grayscale image and perform normalization to obtain a texture feature vector N, substitute the color feature vector and texture feature vector into a preset recognition model to obtain the land category of each sub-image.

3. According to the big data-based national land space planning auxiliary compilation method of claim 1, it is characterized in that: In S2, the specific process of screening is: S11, extracting geographic data from the remote sensing image to generate a geographic feature data set; performing elevation conversion on the geographic feature data set to generate geographic elevation data; performing terrain feature analysis on the geographic elevation data to generate terrain feature analysis data; Classify the land cover of standard land resource field survey data and generate land cover classification areas; Based on the land cover classification area and terrain feature analysis data, regional feature clustering is performed to generate several feature areas; the land type in any feature area is obtained, and if there are two or more land types, the feature area is marked as a pending area; S12, select any land type and mark it as the target land type, obtain the area X to be planned of the target land type, screen out all characteristic areas containing the target land type from the to-be-determined area and mark them as target areas, respectively obtain the areas A1, A2, ..., An of all target areas and the areas a1, a2, ..., an corresponding to the land type in the target area, and calculate the remaining planning area A' of any target area according to the calculation formula A'=Ai-ai, where i is the i-th target area; S13, selecting all target areas whose remaining planning area A' is greater than or equal to the area to be planned X, scoring each target area in turn, and selecting the target area with the highest score as the optimal planning area corresponding to the land type.

4. According to the big data-based national land space planning auxiliary compilation method of claim 3, it is characterized in that: In S13, the specific process of planning scoring is as follows: X'=min|X-A”i| ； Wherein, A”i represents the area corresponding to the i-th land type in the remaining land types, Dx' is the characteristic distance between the characteristic areas of the land type, and u is the preset correction coefficient.

5. The method for assisting in compiling national land space planning based on big data according to claim 4 is characterized in that: The specific calculation process of the characteristic distance Dx' is: Perform edge detection on the target area, and divide the target area into multiple sub-areas according to the detection results, mark the sub-area belonging to the target land type as the target sub-area, mark the land type corresponding to X' as the comparison land type, and mark the sub-area belonging to the target land type as the comparison sub-area. Establish a rectangular coordinate system with the center point of the target area as the origin, obtain the midpoint position of any comparison sub-area and mark it as (X, Y), calculate the distance D from the midpoint of the comparison sub-area to all edge points of the target sub-area, and select the minimum value as the feature distance Dx'.

6. The method for assisting in compiling national land space planning based on big data according to claim 5 is characterized in that: If there are multiple target sub-regions and / or multiple comparison sub-regions in the target region, then according to the calculation formula Wherein, M is the total number of contrast sub-regions, Xk is the horizontal coordinate of the midpoint of the kth contrast sub-region, Yk is the vertical coordinate of the midpoint of the kth contrast sub-region, xlp represents the horizontal coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, ylp represents the vertical coordinate of the edge point corresponding to the minimum value of the distance D from the center point of the contrast sub-region to all edge points of the pth target sub-region, and p is greater than or equal to 1.

7. The method for assisting in compiling national land space planning based on big data according to claim 3 is characterized in that: It also includes that if there are two or more target areas with equal planning scores and both are maximum values, the target area with the smallest X' is selected as the optimal planning area corresponding to the land type.

8. A national land space planning auxiliary compilation system based on big data, characterized in that: include: A data acquisition module is used to acquire a remote sensing image of a target area, and to perform land recognition on the remote sensing image to obtain a specific location area, area, and total area ratio of any land type in the target area, wherein the land types include farmland type, town type, and ecological protection type; A data analysis module is used to calculate the area to be planned of any land type according to the pre-planning information, and screen the land in the target area in the order of ecology, farmland and town according to the area to be planned, and screen out the area to be planned corresponding to the area to be planned that best matches the land type, and use the area to be planned as the optimal planning area for the land type; The result generation module is used to determine the optimal planning area of ​​any land type and draw its corresponding target boundary line, and output the planning remote sensing image map containing the target boundary line.

Images