Land illegal pattern spot clue extraction method and system and electronic equipment

Abstract

The invention discloses a land illegal pattern spot clue extraction method and system and electronic equipment. The method comprises the steps of S1, data cleaning; s2, calculating a surface shape index of the vector; s3, determining a vector buffer distance; s4, constructing a vector search domain; s5, correlation analysis of the same year; s6, tracing analysis over the years; and S7, vector law violation classification. According to the method, the feasibility of a changing pattern spot-based year-by-year silkworm feeding illegal clue extraction scheme is realized, the work of manual discovery is replaced, after parameters are set, trending and seedling land illegal clues such as suspected year-by-year changing and year-by-year newly added illegal pattern spots can be quickly discovered, the working efficiency of finding natural resource supervision problems is improved, and the working efficiency is improved. And vulnerabilities in the traditional problem clue supervision and discovery path are effectively made up.

Description

Technical Field

[0001] The present invention relates to the field of natural resources supervision, and particularly to a method, a system and an electronic device for extracting clues of land illegal map patches in natural resources supervision. Background Art

[0002] Normalized analysis and judgment of land change map patches is the main channel for national natural resources supervision agencies to obtain problem clues. Satellite images are used to monitor land change situations across the country. Through this means, land change map patches are extracted. According to the "Rules for Judging the Legality of Land Satellite Map Patches for Law Enforcement" and combined with various types of supervision data, a reasonable judgment path for problem map patches is formulated to ensure accurate judgment of the changed map patches. The judgment results are verified and investigated by relevant units.

[0003] In the current natural resources supervision work, map patches with large areas are the focus of attention of supervision agencies, while relatively less attention is paid to small map patches. Therefore, there are deficiencies in the comprehensiveness and sufficiency of discovering suspected illegal and irregular problems. For map patches with small illegal areas in the current year, scattered excavation, and large-scale illegal areas accumulated over the years, there is a lack of means for rapid discovery. That is, in the existing analysis work, the monitoring efficiency of problem map patches of gradually encroaching on land year by year is low, and it is difficult to timely discover potential trend and incipient problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, a system and an electronic device for extracting clues of land illegal map patches based on vector search domains and traceability analysis, which can improve the monitoring efficiency of problem map patches of gradually encroaching on land year by year, timely discover potential trend and incipient problems, and effectively make up for the loopholes in the traditional path of discovering problem clues in supervision.

[0005] According to the first aspect of the present invention, there is provided a method for extracting clues of land illegal map patches, which includes: S1. Data cleaning: Select land satellite image change map patches of multiple years for data cleaning to obtain the initial vector data of the map patches; S2. Calculate the surface shape index of the vector; The surface shape index includes the P / A index and the radial compactness; S3. Determine the vector buffer distance: S4. Construct a vector search domain: Construct a vector search domain based on the surface shape index and the vector buffer distance to obtain the search domain vector results of the same year; S5. Association analysis of the same year: Perform overlay analysis on the search domain vector results of the same year. If there are search domain vectors that overlay each other and have the same land use type, then merge these search domain vectors into a new vector to construct a merged vector search domain; record the monitoring numbers of the merged vectors. S6. Traceability analysis over the years: Overlay the vector search domain data over the years for capping analysis to obtain the vector monitoring numbers, capping areas, and land use types of historical associated cappings; S7. Vector illegal classification: When the number of historical associated monitoring numbers obtained from the traceability analysis is greater than 1, enter the classification determination alternative; Set the threshold of the capping area ratio, divide the patch types based on the vector capping area ratio, and classify the illegal types of the changed patches in combination with the land use types of the patches.

[0006] According to the land illegal patch clue extraction method described above, in step S1, select the land satellite image change patches of multiple years for data cleaning, and the initial vector data of the patches obtained includes: Process the outliers and geometric errors existing in the patch vectors; Break up the patches with multiple vector surfaces and merge the vector patches that overlap each other in the same year to ensure the spatial independence of each vector graph; Standardize the attribute field table and field content of the patch vectors, and the fields contain vector monitoring numbers.

[0007] According to the land illegal patch clue extraction method described above, in step S2, the calculation formulas of the P / A index and the radial compactness are as follows: P / A index = perimeter / area Radial compactness = maximum diameter / minimum diameter Among them, the diameter is counted as the Feret diameter.

[0008] According to the land illegal patch clue extraction method described above, in step S3, determining the vector buffer distance includes: Formulate the basic buffer distance; Calculate the vector buffer distance with the following formula; Vector buffer distance = (area / 1000) * basic buffer distance Among them, 5m ≤ basic buffer distance ≤ 20m. When the calculated vector buffer distance is less than 5m, take the value of 5m, and when it is greater than 50m, take the value of 50m.

[0009] According to the land illegal patch clue extraction method described above, in step S4, constructing the vector search domain based on the surface shape index and the vector buffer distance includes: When the P / A index is greater than or equal to the first threshold or the radial compactness is greater than or equal to the second threshold, use the original vector and the buffer distance to construct a buffer zone as the vector search domain; When the P / A index is less than the first threshold and the radial compactness is less than the second threshold, first create the convex hull of the vector, and use the convex hull vector and the buffer distance to construct a buffer as the vector search domain; Among them, 0.4 ≤ the first threshold ≤ 0.6, 2 ≤ the second threshold ≤ 4.

[0010] According to the above-mentioned method for extracting clues of land illegal map patches, in step S5, constructing the merged vector search domain includes: Create the minimum geometric boundary for the vectors in the merged search domain, and this minimum geometric boundary serves as the merged vector search domain.

[0011] According to the above-mentioned method for extracting clues of land illegal map patches, in step S7, classifying map patch types based on the proportion of vector overlapping area includes: If the proportion of vector overlapping area is greater than or equal to the set overlapping area proportion threshold, it is determined as an annually changing map patch; if the proportion of vector overlapping area is less than the set overlapping area proportion threshold, it is determined as an annually newly added map patch.

[0012] According to the above-mentioned method for extracting clues of land illegal map patches, in step S7, the value range of the overlapping area proportion threshold is: 20% ≤ the overlapping area proportion threshold ≤ 40%.

[0013] According to the second aspect of the present invention, there is provided a system for extracting clues of land illegal map patches, which includes a processor and a memory. The memory stores multiple instructions; the processor loads instructions from the memory to execute the above-mentioned method for extracting clues of land illegal map patches.

[0014] According to the third aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the above-mentioned method for extracting clues of land illegal map patches.

[0015] Beneficial effects: The present invention realizes the feasibility of the annual encroachment illegal clue extraction scheme based on changing map patches, replaces the work of manual discovery. After setting the parameters, it can quickly discover trend-based and incipient land illegal clues such as suspected annually changing and annually newly added illegal map patches, improves the work efficiency of natural resources supervision problem discovery, and effectively makes up for the loopholes in the traditional supervision problem clue discovery path.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. Description of the Drawings

[0017] The present invention will be further described below in conjunction with the drawings and embodiments: Figure 1It is a schematic diagram of the search domain constructed by the present invention based on the original vector buffer; where the red represents the original patches and the blue represents the search domain.

[0018] Figure 2 It is a schematic diagram of the search domain constructed by the present invention based on the convex hull vector buffer; where the red represents the original patches and the blue represents the search domain.

[0019] Figure 3 It is a schematic diagram of the search domain of vector patches with adjacent relevance in the same year of the present invention; where the red represents the original patches and the blue represents the search domain.

[0020] Figure 4 It is an example of clues for the problem that the present invention automatically discovers the suspected newly added illegal construction on cultivated land gradually encroaching on cultivated land.

[0021] Figure 5 It is an example of clues for the problem that the present invention automatically discovers the suspected renovation and expansion of buildings (structures) gradually encroaching on illegal issues.

[0022] Figure 6 It is an example of clues for the problem that the present invention automatically discovers the suspected newly added backfilling and soil erosion gradually damaging the ecological environment. Detailed implementation manners

[0023] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are usually used to represent similar components.

[0024] As Figures 1-6 shown, according to an embodiment of the present invention, there is provided a method for extracting clues of land illegal patch, which includes the following steps: S1. Data cleaning: Select the land satellite image change patches of multiple years for data cleaning to obtain the initial vector data of the patches; S2. Calculate the surface shape index of the vector; The surface shape index includes the P / A index and the radial compactness; S3. Determine the vector buffer distance: S4. Construct the vector search domain: Construct a vector search domain based on the surface shape index and the vector buffer distance to obtain the vector results of the search domain in the same year; S5. Analysis of relevance in the same year: Perform overlay analysis on the search area vector results of the same year. If there are search area vectors that overlap and have the same land use type, merge these search area vectors into a new vector to construct a merged vector search area (if the land use types are different or there is no overlap, no merging is done); record the monitoring numbers of the merged vectors; S6. Traceability analysis over the years: Overlay the vector search area data of previous years for overlay analysis to obtain the vector monitoring numbers, overlay areas, and land use types of historical associated overlays; S7. Vector illegal classification: When the number of historical associated monitoring numbers obtained from the traceability analysis is greater than 1, enter the classification determination alternative; Set the threshold for the proportion of the overlay area. Based on the proportion of the vector overlay area, divide the patch types, and combine with the land use type of the patch to classify the illegal types of the changed patches.

[0025] Among them, in step S1, when selecting the land satellite image change patches of multiple years for data cleaning to obtain the initial vector data of the patches, the specific content includes: Process the outliers and geometric errors in the patch vectors by elimination or correction; use QGIS or ArcGIS tools to break up the patches with multiple vector surfaces and merge the vector patches that overlap with each other in the same year to ensure the spatial independence of each vector graphic; standardize the attribute field table and field content of the patch vectors, and the fields include year, administrative region code, vector monitoring number, monitoring area, cultivated land area, land use area, previous time, etc.

[0026] The standardized attributes are shown in Table 1 (part of the content of this table, such as the process attribute field and the result attribute field, will be filled and used in subsequent steps; mainly the basic attribute fields are filled in step S1).

[0027] Table 1 Attribute fields of vector patches after data cleaning In step S2, express the surface shape index of the vector from two dimensions: the perimeter-to-area ratio (P / A index) and the radial compactness (based on the Feret diameter). The calculation formulas for the P / A index and the radial compactness are as follows: P / A index = perimeter / area Radial compactness = maximum diameter / minimum diameter Generally, the result of the surface shape index can be accurate to 2 - 3 decimal places.

[0028] In step S3, to meet the needs of the natural resources supervision business and the requirement of focusing on the major issues and neglecting the minor ones in supervision problems, the buffer distance is determined according to the land use type and the vector area. Specifically, the steps for determining the vector buffer distance include: Set the basic buffer distance according to the land use type (default value: 10m, value range: 5m - 20m); Calculate the vector buffer distance using the following formula; Vector buffer distance = (area / 1000) * basic buffer distance Among them, the larger the area, the larger the buffer distance. When the calculated vector buffer distance is less than 5m, the vector buffer distance is directly set to 5m; when it is greater than 50m, the vector buffer distance is directly set to 50m. The vector buffer distance is usually related to the key points of supervision and the current land policies. For example, in recent years, the country has attached great importance to ecological protection, and strict standards have been implemented in land violations such as ecological damage (illegal mining, deforestation and grass destruction, lake excavation for landscaping). When setting the basic buffer distance, a larger value should be adopted to discover more suspected problems. For example, for land use types such as rural residences, road slopes, and agricultural facilities land, a smaller value can be taken within the above range when formulating the basic buffer distance; for land use types such as industrial and mining warehouses, industrial factories, and commercial services, a larger value can be taken within the above range when formulating the basic buffer distance.

[0029] In step S4, to avoid the problem of long and narrow faces in the vector, a vector search domain is constructed based on the face shape index and the vector buffer distance. The specific content includes: When the P / A index is greater than or equal to the first threshold or the radial compactness is greater than or equal to the second threshold, use the original vector and the buffer distance to construct a buffer zone as the vector search domain (see Figure 1 ); When the P / A index is less than the first threshold and the radial compactness is less than the second threshold, first create the convex hull of the vector (also known as the minimum bounding geometry, created using ArcGIS tools), and use the convex hull vector and the buffer distance to construct a buffer zone as the vector search domain (see Figure 2 ); Among them, the value range of the first threshold is 0.4 - 0.6, and the default value is usually 0.5; the second threshold is 2 - 4, and the default value is usually 3.

[0030] In step S5, the specific content of constructing the merged vector search domain includes: Create the minimum geometric boundary for the vectors in the merged search domain, and this minimum geometric boundary serves as the merged vector search domain (no further buffer zone is created). As shown in Figure 3 is the search domain after the annual joint merge. This merged vector search domain is regarded as a whole for the subsequent overlay analysis.

[0031] In step S6, search for domain vector results according to the changes in the same year, overlay the vector data of changes over the years for capping analysis, and obtain the vector monitoring numbers, capping areas, and land use types of historical associated cappings. In this step, as long as there is a historical associated capping, the corresponding vector enters the classification determination alternative in the subsequent steps.

[0032] Evaluate the confidence level based on the number of associated vectors over the years, the number of associated years, the proportion of the area with consistent land use types, and the distance between vector centroids. The more associated historical vectors, the more associated years, the larger the proportion of the area with consistent land use types, and the closer the distance between vector centroids, the higher the confidence level that the patch encroaches illegally year by year.

[0033] In step S7, the value range of the capping area proportion threshold is 20% - 40%, and the default value of 30% is usually taken. The specific content of dividing patch types based on the vector capping area proportion includes: if the vector capping area proportion is greater than or equal to the set threshold parameter, it is determined as a patch with annual changes; if the vector capping area proportion is less than the set threshold parameter, it is determined as a newly added patch year by year.

[0034] Combine the land use types of the patches to classify the illegal types of the changing patches and fill the result attribute fields. The extraction and classification determination results are as Figures 4-6 shown. Among them, the field content filled in Table 1 is archived and distributed as reference data to the relevant departments for verification and investigation.

[0035] The present invention also provides a system for extracting clues of land illegal patches, which includes a processor and a memory. The memory stores multiple instructions; the processor loads the instructions from the memory to execute the above-mentioned method for extracting clues of land illegal patches.

[0036] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the above-mentioned method for extracting clues of land illegal patches.

[0037] Although the foregoing methods are illustrated and described as a series of acts for simplicity of explanation, it should be understood and appreciated that the methods are not limited by the order of the acts, since according to one or more embodiments, some acts may occur in different orders and / or concurrently with other acts not illustrated and described herein or other acts that would be understood by those skilled in the art. Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. The various illustrative logical blocks, modules, and circuits described in connection with the embodiments disclosed herein can be implemented using a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read from, and write to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal. In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer readable medium as one or more instructions or code.Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Storage media can be any available media that can be accessed by a computer. By way of example and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is properly termed a computer-readable media. For example, if software is transmitted from a web site, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. As used herein, disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc where disks typically reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0038] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for extracting clues from illegal land spots, characterized in that: include: S1. Data cleaning: Select the land satellite image change spots of multiple years for data cleaning to obtain the initial vector data of the spots; S2, calculate the surface shape index of the vector; The surface shape index includes P / A index and radial compactness; S3. Determine the vector buffer distance: S4. Construct vector search domain: Construct a vector search domain based on the surface shape index and vector buffer distance to obtain the search domain vector results of the same year; S5. Correlation analysis in the same year: Conduct overlap analysis on the search domain vector results of the same year. If there are search domain vectors that overlap each other and have the same land use type, merge these search domain vectors into a new vector to construct a merged vector search domain; record the monitoring number of the merged vector; S6. Historical traceability analysis: Overlay the vector search domain data of previous years to conduct coverage analysis, and obtain the vector monitoring number, coverage area, and land use type of historical associated coverage; S7. Vector Violation Classification: When the number of historical related monitoring numbers obtained through source tracing analysis is greater than 1, the classification and selection process will be started; Set the threshold of the proportion of the overlapped area, divide the map types based on the proportion of the vector overlapped area, and classify the illegal types of the changed maps based on the land use type of the maps.

2. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S1, land satellite image change spots from multiple years are selected for data cleaning, and the initial vector data of the spots obtained include: Handling outliers and geometric errors in patch vectors; Break up the spots with multiple vector surfaces and merge the overlapping vector spots of the same year to ensure the spatial independence of each vector graphic; Standardize the attribute field table and field content of the map spot vector, and the field contains the vector monitoring number.

3. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S2, the calculation formulas of the P / A index and radial compactness are as follows: P / A Index = Perimeter / Area Radial compactness = maximum diameter / minimum diameter The diameter is the Feret diameter.

4. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S3, determining the vector buffer distance includes: Establish basic buffer distance; The vector buffer distance is calculated using the following formula; Vector buffer distance = (area / 1000) * basic buffer distance Among them, 5m≤basic buffer distance≤20m, the calculated vector buffer distance is 5m when it is less than 5m, and 50m when it is greater than 50m.

5. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S4, constructing a vector search domain based on the surface shape index and the vector buffer distance includes: When the P / A index is greater than or equal to the first threshold or the radial compactness is greater than or equal to the second threshold, the original vector and the buffer distance are used to construct a buffer as the vector search domain; When the P / A index is less than the first threshold and the radial compactness is less than the second threshold, the convex hull of the vector is first created, and the convex hull vector and the buffer distance are used to construct a buffer as the vector search domain; Among them, 0.4≤first threshold≤0.6, 2≤second threshold≤4.

6. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S5, constructing a merged vector search domain includes: A minimum geometric boundary is created for the merged search domain vector, and the minimum geometric boundary serves as the merged vector search domain.

7. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S7, the pattern type is divided based on the proportion of the vector coverage area, including: If the vector coverage area ratio is greater than or equal to the set coverage area ratio threshold, it is judged as a map spot that changes year by year. If the vector coverage area ratio is less than the set coverage area ratio threshold, it is judged as a newly added map spot year by year.

8. The method for extracting clues of illegal land spots according to claim 1 is characterized in that: In step S7, the value range of the threshold value of the coverage area ratio is: 20%≤the threshold value of the coverage area ratio≤40%.

9. The land illegal spot clue extraction system is characterized by: It includes a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the method for extracting clues of illegal land patterns as described in any one of claims 1-8.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method for extracting clues of land illegal patterns as described in any one of claims 1-8.

Images