A method and system for net land identification based on multiple spatial elements

Abstract

The application discloses a kind of net land identification method and system based on multiple space elements, it is related to land supervision field, comprising: obtaining remote sensing image data of the region to be studied, vehicle traffic data and land ownership data;Based on convolutional neural network, the remote sensing image data is carried out block identification, and the remote sensing characteristic distribution diagram of the region to be studied is obtained;The vehicle traffic data is analyzed by heat map, and the road network characteristic distribution diagram of the region to be studied is obtained, and the spatial distribution analysis is carried out to the land ownership data, and the land ownership distribution table of the region to be studied is obtained;According to the remote sensing characteristic distribution diagram, the road network characteristic distribution diagram and the land ownership distribution table, the space-time data expression model of the region to be studied is constructed;According to the space-time data expression model, in combination with the preset net land transfer identification model, the to-be-identified land in the region to be studied is identified.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of land supervision, and in particular to a method and system for identifying net land based on multiple spatial elements. BACKGROUND

[0002] Net land refers to land that meets the following five requirements in the land transfer process: clear land rights; resettlement compensation is in place; no legal and economic disputes; clear planning conditions such as plot location, use nature, and plot ratio; and other basic conditions necessary for development. Identifying and verifying whether the land is net land before land transfer is beneficial to the rational use of land resources and avoids land idling and waste. Therefore, it is necessary to identify and monitor the transfer of net land.

[0003] Existing net land transfer identification and monitoring and supervision mainly provide corresponding materials by various departments, combined with on-site visits, to manually check the land transfer ownership and surface conditions. This method lacks flexibility, has low efficiency and accuracy, and manual identification and verification wastes manpower and resources. Therefore, how to improve the efficiency and accuracy of net land transfer identification and monitoring and supervision is still a problem to be solved in the prior art. SUMMARY

[0004] The present application provides a method and system for identifying net land based on multiple spatial elements to solve the technical problem of low efficiency and accuracy of existing net land identification and supervision.

[0005] According to a first aspect of an embodiment of the present application, a method for identifying net land based on multiple spatial elements is provided, comprising:

[0006] acquiring remote sensing image data, vehicle traffic data, and plot ownership data of a region to be studied;

[0007] performing block identification on the remote sensing image data based on a convolutional neural network to obtain a remote sensing feature distribution map of the region to be studied;

[0008] performing heat map analysis on the vehicle traffic data to obtain a road network feature distribution map of the region to be studied, and performing spatial distribution analysis on the plot ownership data to obtain a plot ownership distribution table of the region to be studied;

[0009] constructing a spatio-temporal data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map, and the plot ownership distribution table;

[0010] identifying a plot to be identified in the region to be studied according to the spatio-temporal data expression model and a preset net land transfer identification model, wherein the net land transfer identification model is obtained based on historical net land transfer data.

[0011] The application firstly performs block recognition on remote sensing image data of a region to be studied based on a convolutional neural network to obtain a remote sensing feature distribution map, then performs heat map analysis on vehicle passing data of the region to be studied to obtain a road network feature distribution map, and performs spatial distribution analysis on land parcel ownership data of the region to be studied to obtain a land parcel ownership distribution table, so that the remote sensing features, road network features and spatial distribution of land parcel ownership of the region to be studied can be accurately recognized and obtained through the convolutional neural network, heat map analysis and spatial distribution analysis, thereby improving the efficiency of net land recognition of the region to be studied, and improving the efficiency of net land recognition supervision; then a space-time data expression model is constructed in combination with the remote sensing feature distribution map, the road network feature distribution map and the land parcel ownership distribution table, so that the information of each land parcel of the region to be studied can be described comprehensively through the three spatial elements, the comprehensiveness of the land parcel information is improved, and the accuracy of net land recognition is improved; then the land parcel to be recognized is recognized in combination with the space-time data expression model and a net land transfer recognition model trained based on historical net land transfer data, so that the advantages of the two models can be combined, the accuracy of net land recognition is improved, and the accuracy of net land recognition supervision is improved.

[0012] In some embodiments of the application, the remote sensing image data is recognized in blocks based on the convolutional neural network to obtain a remote sensing feature distribution map of the region to be studied, specifically comprising:

[0013] The remote sensing image data is image enhanced to obtain a remote sensing enhanced image;

[0014] The remote sensing enhanced image is divided into land parcels with a preset land parcel length as a recognition unit length to obtain a remote sensing block image;

[0015] The remote sensing block image is recognized in blocks based on the convolutional neural network to obtain a remote sensing feature distribution map.

[0016] The remote sensing image data is image enhanced to obtain a remote sensing enhanced image, and the remote sensing block image is obtained by dividing the land parcels with a preset land parcel length, so that the feature recognition can be divided into each land parcel, thereby improving the accuracy of the remote sensing feature distribution map obtained by recognizing the remote sensing block image based on the convolutional neural network.

[0017] In some embodiments of the application, the vehicle passing data is analyzed by heat map to obtain a road network feature distribution map of the region to be studied, specifically comprising:

[0018] The vehicle passing data is divided into a plurality of vehicle passing sub-data groups with a preset time length as a division unit time;

[0019] The plurality of vehicle passing sub-data groups are analyzed by heat map respectively to obtain a plurality of road network sub-feature distribution maps;

[0020] The plurality of road network sub-feature distribution maps are superimposed to obtain a road network feature distribution map.

[0021] The vehicle passing data is divided into multiple groups of vehicle passing sub-data according to time, and multiple groups of road network sub-feature distribution maps are obtained through heat map analysis, and then a road network feature distribution map is obtained. Through the division of vehicle passing data and heat map analysis, the accuracy of the heat map analysis can be improved, thereby improving the accuracy of the obtained road network feature distribution map.

[0022] In some embodiments of the present application, the spatial distribution analysis of the land ownership data obtains a land ownership distribution table of the region to be studied, specifically including:

[0023] The land ownership data is divided into multiple groups of land ownership distribution data based on land division;

[0024] The multiple groups of land ownership distribution data are subjected to spatial distribution analysis to obtain multiple groups of land ownership distribution sub-tables;

[0025] The multiple groups of land ownership distribution sub-tables are integrated to obtain a land ownership distribution table.

[0026] The land ownership data is divided into multiple groups of land ownership distribution data according to land division, and then spatial distribution analysis is performed to obtain a land ownership distribution table. By first dividing each land and then performing spatial distribution analysis, the spatial distribution of the ownership of each land can be accurately determined, thereby better meeting the current task requirements.

[0027] In some embodiments of the present application, the time-space data expression model of the region to be studied is constructed according to the remote sensing feature distribution map, the road network feature distribution map, and the land ownership distribution table, specifically including:

[0028] The remote sensing feature distribution map and the road network feature distribution map are fused based on latitude and longitude to obtain a regional feature distribution map;

[0029] According to each land in the land ownership distribution table, the land ownership distribution table is embedded into the regional feature distribution map to obtain a time-space data expression model.

[0030] The remote sensing feature distribution map and the road network feature distribution map are fused based on latitude and longitude, and then the land ownership distribution table is embedded to obtain a time-space data expression model. The spatio-temporal data of the three can be fused, and the information of each land in the region to be studied is described by comprehensively considering the three spatial elements, thereby better meeting the current task requirements.

[0031] In some embodiments of the present application, the land to be identified in the region to be studied is identified according to the time-space data expression model and in combination with a preset net land transfer identification model, specifically including:

[0032] Based on the spatio-temporal data representation model, search to obtain the identification information matrix of the to-be-identified land plot;

[0033] Input the identification information matrix into the net land transfer identification model to obtain the net land identification result of the to-be-identified land plot.

[0034] The present application first searches the to-be-identified land plot based on the spatio-temporal data representation matrix to obtain the identification information matrix, and then inputs the net land transfer identification model to obtain the net land identification result. The advantages of the two models can be combined to identify through comprehensive land information types, improve the accuracy of net land identification, and thus improve the accuracy of net land identification supervision.

[0035] According to a second aspect of the embodiments of the present application, a net land identification system based on multiple spatial elements is provided, comprising a data acquisition module, a first processing module, a second processing module, a model construction module and a land plot identification module;

[0036] The data acquisition module is configured to acquire remote sensing image data, vehicle traffic data and land plot ownership data of a to-be-studied area;

[0037] The first processing module is configured to perform block identification on the remote sensing image data based on a convolutional neural network to obtain a remote sensing feature distribution map of the to-be-studied area;

[0038] The second processing module is configured to perform heat map analysis on the vehicle traffic data to obtain a road network feature distribution map of the to-be-studied area, and perform spatial distribution analysis on the land plot ownership data to obtain a land plot ownership distribution table of the to-be-studied area;

[0039] The model construction module is configured to construct a spatio-temporal data representation model of the to-be-studied area according to the remote sensing feature distribution map, the road network feature distribution map and the land plot ownership distribution table;

[0040] The land plot identification module is configured to identify a to-be-identified land plot in the to-be-studied area according to the spatio-temporal data representation model and in combination with a preset net land transfer identification model. The net land transfer identification model is trained based on historical net land transfer data.

[0041] In some embodiments of the present application, the first processing module comprises an image enhancement unit, a land plot division unit and a block identification unit;

[0042] The image enhancement unit is configured to perform image enhancement on the remote sensing image data to obtain a remote sensing enhanced image;

[0043] The land plot division unit is configured to divide the remote sensing enhanced image into land plots with a preset land plot length as an identification unit length to obtain a remote sensing block image;

[0044] The block identification unit is configured to perform block identification on the remote sensing block image based on a convolutional neural network to obtain a remote sensing feature distribution map.

[0045] In some embodiments of the present application, the second processing module includes a traffic division unit, a heat analysis unit, and a feature superposition unit.

[0046] The traffic division unit is configured to divide the vehicle traffic data into a plurality of groups of vehicle traffic sub-data with a preset time length as a division unit time.

[0047] The heat analysis unit is configured to perform heat map analysis on the plurality of groups of vehicle traffic sub-data respectively to obtain a plurality of groups of road network sub-feature distribution maps.

[0048] The feature superposition unit is configured to superimpose the plurality of groups of road network sub-feature distribution maps to obtain a road network feature distribution map.

[0049] In some embodiments of the present application, the second processing module includes a property division unit, a time sequence analysis unit, and a data integration unit.

[0050] The property division unit is configured to divide the land property data into a plurality of groups of land property distribution data with a land block as a division basis.

[0051] The time sequence analysis unit is configured to perform spatial distribution analysis on the plurality of groups of land property distribution data to obtain a plurality of groups of land property distribution sub-tables.

[0052] The data integration unit is configured to integrate the plurality of groups of land property distribution sub-tables to obtain a land property distribution table.

[0053] In some embodiments of the present application, the model construction module includes a feature fusion unit and a model construction unit.

[0054] The feature fusion unit is configured to fuse the remote sensing feature distribution map and the road network feature distribution map based on latitude and longitude to obtain a regional feature distribution map.

[0055] The model construction unit is configured to embed the land property distribution table into the regional feature distribution map according to each land block in the land property distribution table to obtain a spatio-temporal data expression model.

[0056] In some embodiments of the present application, the land block identification module includes a land block searching unit and a net land identification unit.

[0057] The land block searching unit is configured to search for an identification information matrix of a to-be-identified land block based on the spatio-temporal data expression model.

[0058] The net land identification unit is configured to input the identification information matrix into the net land transfer identification model to obtain a net land identification result of the to-be-identified land block.

[0059] The application firstly performs block identification on remote sensing image data of the to-be-researched region based on a convolutional neural network to obtain a remote sensing feature distribution map, then performs heat map analysis on vehicle traffic data of the to-be-researched region to obtain a road network feature distribution map, and performs spatial distribution analysis on land block ownership data of the to-be-researched region to obtain a land block ownership distribution table, so as to accurately identify and obtain remote sensing features, road network features and spatial distribution of land block ownership of the to-be-researched region through the convolutional neural network, heat map analysis and spatial distribution analysis, thereby improving the net land identification efficiency of the land block and the efficiency of net land identification supervision. Then, a space-time data expression model is constructed in combination with the remote sensing feature distribution map, the road network feature distribution map and the land block ownership distribution table, so as to comprehensively describe information of each land block of the to-be-researched region through the three kinds of spatial elements, improve the comprehensiveness of the land block information and improve the accuracy of the net land identification. Finally, the to-be-identified land block is identified in combination with the space-time data expression model and the net land transfer identification model trained based on historical net land transfer data, so as to comprehensively improve the accuracy of the net land identification through the advantages of the two models, thereby improving the accuracy of the net land identification supervision. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 FIG. 1 is a flowchart of a net land identification method based on multiple spatial elements according to some embodiments of the present application;

[0061] Figure 2 FIG. 2 is a block diagram of a net land identification system based on multiple spatial elements according to some embodiments of the present application. DETAILED DESCRIPTION

[0062] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, in which the same or similar notations are used to denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are only used to explain some embodiments of the present application, and cannot be understood as limiting the embodiments of the present application. Based on the embodiments shown in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0063] In the description of the present application, it should be understood that the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" can be explicitly or implicitly included at least one of the features. In the description of the present application, unless otherwise specifically limited, the meaning of "a plurality of" "several" is two or more.

[0064] The existing net land transfer identification and monitoring supervision is mainly through the departments to provide corresponding materials, combined with on-site visits, to manually check the land transfer ownership and surface conditions. This method lacks flexibility, low efficiency and accuracy, and manual identification and verification exist the situation of wasting manpower and material resources. Therefore, how to improve the efficiency and accuracy of net land transfer identification and monitoring supervision is still a problem to be solved in the prior art.

[0065] Based on the above technical background, please refer to Figure 1 The embodiment of the present application provides a net land identification method based on multiple space elements, comprising steps S101 to S10a, and each step is as follows:

[0066] Step S101: acquiring remote sensing image data, vehicle passing data and land ownership data of a region to be studied.

[0067] Step S102: based on a convolutional neural network, the remote sensing image data is identified in blocks to obtain a remote sensing feature distribution map of the region to be studied.

[0068] In some embodiments of the present application, the remote sensing image data is identified in blocks based on the convolutional neural network to obtain the remote sensing feature distribution map of the region to be studied, specifically comprising:

[0069] The remote sensing image data is image enhanced to obtain a remote sensing enhanced image;

[0070] The remote sensing enhanced image is divided into blocks with a preset block length as the identification unit length to obtain a remote sensing block image;

[0071] The remote sensing block image is identified in blocks based on the convolutional neural network to obtain the remote sensing feature distribution map.

[0072] In some embodiments of the present application, the implementation of the image enhancement includes but is not limited to histogram equalization, gray world algorithm, Retinex algorithm and automatic color equalization (ACE) algorithm, and the preferred implementation is the histogram equalization algorithm.

[0073] In some embodiments of the present application, the preferred value of the preset block length is 100m.

[0074] In some embodiments of the present application, the implementation of the convolutional neural network includes, but is not limited to, the R-CNN model and its improved models, the R-FCN model, and the SPP-Net model, and the preferred implementation is the R-CNN model.

[0075] By identifying the remote sensing image data through the convolutional neural network, the remote sensing feature data of the buildings, structures, pits, and vegetation on the ground surface can be identified and obtained to form a remote sensing feature distribution map. Generally, the buildings, structures, pits, and vegetation on the ground surface are closely related to the "clear table" work of the corresponding land, and whether it is a net land is also inseparable from the "clear table" work. Therefore, by forming a remote sensing feature distribution map through the remote sensing feature data of the buildings, structures, pits, and vegetation on the ground surface, the identification of the net land can be ensured.

[0076] The present application first performs image enhancement on the remote sensing image data to obtain a remote sensing enhanced image, and then performs land division on the remote sensing enhanced image to obtain a remote sensing divided image, which can divide the feature recognition into each land, thereby improving the accuracy of the remote sensing feature distribution map obtained by the convolutional neural network based on the divided recognition.

[0077] Step S103: performing heat map analysis on the vehicle passing data to obtain a road network feature distribution map of the region to be studied, and performing spatial distribution analysis on the land ownership data to obtain a land ownership distribution table of the region to be studied.

[0078] In some embodiments of the present application, the heat map analysis on the vehicle passing data to obtain a road network feature distribution map of the region to be studied specifically includes:

[0079] Dividing the vehicle passing data into a plurality of groups of vehicle passing sub-data with a preset time length as the division unit time;

[0080] Performing heat map analysis on each group of vehicle passing sub-data to obtain a plurality of road network sub-feature distribution maps;

[0081] Superimposing the plurality of road network sub-feature distribution maps to obtain a road network feature distribution map.

[0082] In some embodiments of the present application, the preferred value of the preset time length is 24h.

[0083] The present application first divides the vehicle passing data into a plurality of groups of vehicle passing sub-data according to time, and then performs heat map analysis to obtain a plurality of road network sub-feature distribution maps, and further superimposes to obtain a road network feature distribution map. By dividing the vehicle passing data and performing heat map analysis respectively, the accuracy of the heat map analysis can be improved, thereby improving the accuracy of the obtained road network feature distribution map.

[0084] The road network feature distribution map obtained by the heat map analysis of the vehicle traffic heat map can obtain the access condition of each land plot, and the access condition is an important identification factor of the net land. If the access condition is poor or there is no access, it indicates that the corresponding land plot is non-net land. Therefore, the road network feature distribution map obtained by the heat map analysis of the vehicle traffic heat map to study the access condition of the land plot can provide guarantee for the identification of the net land.

[0085] In some embodiments of the present application, the spatial distribution analysis of the land plot ownership data obtains a land plot ownership distribution table of the region to be studied, specifically including:

[0086] The land plot ownership data is divided into a plurality of sets of land plot ownership distribution data according to the land plot;

[0087] The plurality of sets of land plot ownership distribution data are subjected to spatial distribution analysis to obtain a plurality of sets of land plot ownership distribution sub-tables;

[0088] The plurality of sets of land plot ownership distribution sub-tables are integrated to obtain a land plot ownership distribution table.

[0089] The spatial distribution analysis of the land plot ownership data can obtain the current ownership condition of each land plot, and the ownership condition is another important identification factor of the net land. If the current land plot has ownership problems, such as collective ownership or state-owned, collective land use rights, etc. The current land plot is non-net land. Therefore, the land plot ownership distribution table obtained by the spatial distribution analysis of the land plot ownership data can provide guarantee for the identification of the net land.

[0090] The present application first divides the land plot ownership data into a plurality of sets of land plot ownership distribution data according to the land plot, and then performs spatial distribution analysis to obtain a land plot ownership distribution table. By dividing each land plot first and then performing spatial distribution analysis, the spatial distribution of the ownership of each land plot can be accurately determined, thereby better meeting the current task requirements.

[0091] Step S104: constructing a space-time data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map and the land plot ownership distribution table.

[0092] In some embodiments of the present application, the space-time data expression model of the region to be studied is constructed according to the remote sensing feature distribution map, the road network feature distribution map and the land plot ownership distribution table, specifically including:

[0093] The remote sensing feature distribution map and the road network feature distribution map are fused based on latitude and longitude to obtain a regional feature distribution map;

[0094] According to each plot in the plot ownership distribution table, the plot ownership distribution table is embedded into the regional feature distribution map to obtain a spatiotemporal data expression model.

[0095] Specifically, when the remote sensing feature distribution map and the road network feature distribution map are fused based on the latitude and longitude to obtain the regional feature distribution map, the latitude and longitude points on the remote sensing feature distribution map and the road network feature distribution map are first aligned according to the latitude and longitude, and then the respective information is superimposed to obtain the regional feature distribution map.

[0096] Specifically, when the plot ownership distribution table is embedded into the regional feature distribution map according to each plot in the plot ownership distribution table to obtain the spatiotemporal data expression model, the plot ownership distribution table of a plot is written into all latitude and longitude points corresponding to the plot, so as to embed the plot ownership distribution table into the regional feature distribution map to obtain the spatiotemporal data expression model.

[0097] The remote sensing feature distribution map and the road network feature distribution map are first fused based on the latitude and longitude, and then the plot ownership distribution table is embedded to obtain the spatiotemporal data expression model, which can fuse the spatiotemporal data of the three, comprehensively describe the information of each plot in the region to be studied by the three spatial elements, and better meet the current task requirements.

[0098] Step S105: According to the spatiotemporal data expression model, a preset net land transfer recognition model is combined to recognize the to-be-recognized plot in the region to be studied.

[0099] In some embodiments of the present application, the to-be-recognized plot in the region to be studied is recognized according to the spatiotemporal data expression model and the preset net land transfer recognition model, specifically including:

[0100] Based on the spatiotemporal data expression model, an identification information matrix of the to-be-recognized plot is searched.

[0101] The identification information matrix is input into the net land transfer recognition model to obtain a net land recognition result of the to-be-recognized plot.

[0102] In some embodiments of the present application, the identification information matrix includes remote sensing features, road network features, and a plot ownership distribution table of the to-be-recognized plot.

[0103] The remote sensing feature distribution map and the road network feature distribution map are first fused based on the latitude and longitude, and then the plot ownership distribution table is embedded to obtain the spatiotemporal data expression model, which can comprehensively utilize the advantages of the two models, recognize through comprehensive plot information types, improve the accuracy of net land recognition, and thus improve the accuracy of net land recognition supervision.

[0104] Compared with the prior art, the application first performs block identification on the remote sensing image data of the region to be studied based on a convolutional neural network to obtain a remote sensing feature distribution map, then performs heat map analysis on the vehicle traffic data of the region to be studied to obtain a road network feature distribution map, and performs spatial distribution analysis on the land ownership data of the region to be studied to obtain a land ownership distribution table, so that the remote sensing features, road network features and spatial distribution of land ownership of the region to be studied can be accurately identified and obtained through the convolutional neural network, heat map analysis and spatial distribution analysis, thereby improving the efficiency of net land identification of the land, and improving the efficiency of net land identification supervision; then, a spatio-temporal data expression model is constructed in combination with the remote sensing feature distribution map, the road network feature distribution map and the land ownership distribution table, so that the information of each land in the region to be studied can be described comprehensively by the three spatial elements, the comprehensiveness of the land information is improved, and the accuracy of net land identification is improved; then, the land to be identified is identified in combination with the spatio-temporal data expression model and a net land transfer identification model trained based on historical net land transfer data, so that the advantages of the two models can be combined to improve the accuracy of net land identification, thereby improving the accuracy of net land identification supervision.

[0105] Corresponding to the foregoing method, see Figure 2 The embodiment of the application provides a net land identification system based on multiple spatial elements, comprising a data acquisition module 210, a first processing module 220, a second processing module 230, a model construction module 240 and a land identification module 250.

[0106] The data acquisition module 210 is configured to acquire remote sensing image data, vehicle traffic data and land ownership data of a region to be studied.

[0107] The first processing module 220 is configured to perform block identification on the remote sensing image data based on a convolutional neural network to obtain a remote sensing feature distribution map of the region to be studied.

[0108] The second processing module 230 is configured to perform heat map analysis on the vehicle traffic data to obtain a road network feature distribution map of the region to be studied, and perform spatial distribution analysis on the land ownership data to obtain a land ownership distribution table of the region to be studied.

[0109] The model construction module 240 is configured to construct a spatio-temporal data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map and the land ownership distribution table.

[0110] The land identification module 250 is configured to identify a land to be identified in the region to be studied in combination with a preset net land transfer identification model according to the spatio-temporal data expression model, wherein the net land transfer identification model is trained based on historical net land transfer data.

[0111] In some embodiments of the present application, the first processing module 220 comprises an image enhancement unit, a land parcel division unit, and a block recognition unit.

[0112] The image enhancement unit is configured to perform image enhancement on the remote sensing image data to obtain a remote sensing enhanced image.

[0113] The land parcel division unit is configured to divide the remote sensing enhanced image into remote sensing block images with a preset land parcel length as a recognition unit length.

[0114] The block recognition unit is configured to perform block recognition on the remote sensing block images based on a convolutional neural network to obtain a remote sensing feature distribution map.

[0115] In some embodiments of the present application, the second processing module 230 comprises a traffic division unit, a heat analysis unit, and a feature superposition unit.

[0116] The traffic division unit is configured to divide the vehicle traffic data into a plurality of groups of vehicle traffic sub-data with a preset time length as a division unit time.

[0117] The heat analysis unit is configured to perform heat map analysis on the plurality of groups of vehicle traffic sub-data respectively to obtain a plurality of groups of road network sub-feature distribution maps.

[0118] The feature superposition unit is configured to superimpose the plurality of groups of road network sub-feature distribution maps to obtain a road network feature distribution map.

[0119] In some embodiments of the present application, the second processing module 230 comprises a property division unit, a time sequence analysis unit, and a data integration unit.

[0120] The property division unit is configured to divide the land parcel property data into a plurality of groups of land parcel property distribution data with land parcels as a division basis.

[0121] The time sequence analysis unit is configured to perform spatial distribution analysis on the plurality of groups of land parcel property distribution data to obtain a plurality of groups of land parcel property distribution sub-tables.

[0122] The data integration unit is configured to integrate the plurality of groups of land parcel property distribution sub-tables to obtain a land parcel property distribution table.

[0123] In some embodiments of the present application, the model construction module 240 comprises a feature fusion unit and a model construction unit.

[0124] The feature fusion unit is configured to fuse the remote sensing feature distribution map and the road network feature distribution map based on latitude and longitude to obtain a regional feature distribution map.

[0125] The model construction unit is configured to embed the land ownership distribution table into the regional feature distribution map according to each land plot in the land ownership distribution table, and obtain a spatio-temporal data expression model.

[0126] In some embodiments of the present application, the land plot identification module 250 comprises a land plot searching unit and a net land identification unit.

[0127] The land plot searching unit is configured to search for an identification information matrix of a land plot to be identified based on the spatio-temporal data expression model.

[0128] The net land identification unit is configured to input the identification information matrix into the net land transfer identification model to obtain a net land identification result of the land plot to be identified.

[0129] The present application first performs block identification on remote sensing image data of a region to be studied based on a convolutional neural network to obtain a remote sensing feature distribution map, then performs heat map analysis on vehicle traffic data of the region to be studied to obtain a road network feature distribution map, and performs spatial distribution analysis on land ownership data of the region to be studied to obtain a land ownership distribution table. The remote sensing feature, road network feature, and land ownership spatial distribution of the region to be studied can be accurately identified and obtained through the convolutional neural network, heat map analysis, and spatial distribution analysis, thereby improving the net land identification efficiency of the land plot and the efficiency of net land identification supervision. The spatio-temporal data expression model is constructed in combination with the remote sensing feature distribution map, the road network feature distribution map, and the land ownership distribution table, which can comprehensively describe the information of each land plot of the region to be studied by the three spatial elements, improve the comprehensiveness of the land plot information, and improve the accuracy of net land identification. The land plot to be identified is identified in combination with the spatio-temporal data expression model and the net land transfer identification model trained based on historical net land transfer data, which can comprehensively utilize the advantages of the two models to improve the accuracy of net land identification, thereby improving the accuracy of net land identification supervision.

[0130] It should be understood that the system provided by the embodiments of the present application corresponds to the foregoing method. The net land identification system based on multiple spatial elements provided by the embodiments of the present application can implement the net land identification method based on multiple spatial elements provided by any one of the embodiments of the present application.

[0131] Adaptively, the embodiments of the present application further provide a computer device and a computer readable storage medium.

[0132] The computer device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor.

[0133] When the processor executes the computer program, the net land identification method based on multiple spatial elements is implemented.

[0134] The computer readable storage medium stores a plurality of instructions adapted to be loaded by the processor to execute a method for identifying a net land based on a plurality of spatial elements.

[0135] The above is part of the embodiments of the present application, and the purposes, technical solutions and beneficial effects of the present application are further described in detail. It should be clear that the above part of the embodiments of the present application cannot be understood as a limitation of the present application. It is particularly pointed out that any changes, modifications, equivalent replacements and variations, etc. made by those skilled in the art within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for net land identification based on multi-space elements, characterized in that, The method comprises the following steps: acquiring remote sensing image data, vehicle traffic data and land ownership data of a region to be studied; performing block recognition on the remote sensing image data based on a convolutional neural network to obtain a remote sensing feature distribution map of the region to be studied; performing heat map analysis on the vehicle traffic data to obtain a road network feature distribution map of the region to be studied, and performing spatial distribution analysis on the land ownership data to obtain a land ownership distribution table of the region to be studied; constructing a spatiotemporal data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map and the land ownership distribution table; identifying a land block to be identified in the region to be studied according to the spatiotemporal data expression model and a preset net land transfer identification model, wherein the net land transfer identification model is obtained by training historical net land transfer data; the step of constructing the spatiotemporal data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map and the land ownership distribution table specifically comprises the following steps: fusing the remote sensing feature distribution map and the road network feature distribution map based on latitude and longitude to obtain a regional feature distribution map; and embedding the land ownership distribution table into the regional feature distribution map according to each land block in the land ownership distribution table to obtain the spatiotemporal data expression model; the step of identifying the land block to be identified in the region to be studied according to the spatiotemporal data expression model and the preset net land transfer identification model specifically comprises the following steps: searching for an identification information matrix of the land block to be identified based on the spatiotemporal data expression model; and inputting the identification information matrix into the net land transfer identification model to obtain a net land identification result of the land block to be identified.

2. The method of claim 1, wherein, the step of performing block recognition on the remote sensing image data based on the convolutional neural network to obtain the remote sensing feature distribution map of the region to be studied specifically comprises the following steps: performing image enhancement on the remote sensing image data to obtain a remote sensing enhanced image; dividing the remote sensing enhanced image into land blocks with a preset land block length as a recognition unit length to obtain a remote sensing block image; performing block recognition on the remote sensing block image based on the convolutional neural network to obtain the remote sensing feature distribution map.

3. The method of claim 1, wherein, the step of performing heat map analysis on the vehicle traffic data to obtain the road network feature distribution map of the region to be studied specifically comprises the following steps: dividing the vehicle traffic data into a plurality of vehicle traffic sub-data groups with a preset time length as a division unit time; performing heat map analysis on the plurality of vehicle traffic sub-data groups to obtain a plurality of road network sub-feature distribution maps; superimposing the plurality of road network sub-feature distribution maps to obtain the road network feature distribution map.

4. The method of claim 1, wherein, the step of performing spatial distribution analysis on the land ownership data to obtain the land ownership distribution table of the region to be studied specifically comprises the following steps: dividing the land ownership data into a plurality of land ownership distribution data groups according to land blocks as a division basis; performing spatial distribution analysis on the plurality of land ownership distribution data groups to obtain a plurality of land ownership distribution sub-tables; integrating the plurality of land ownership distribution sub-tables to obtain the land ownership distribution table.

5. A net land identification system based on multi-space elements, characterized by, The method comprises a data acquisition module, a first processing module, a second processing module, a model construction module and a land block identification module. The data acquisition module is configured to acquire remote sensing image data, vehicle traffic data, and land ownership data of a region to be studied. The first processing module is configured to perform block identification on the remote sensing image data based on a convolutional neural network to obtain a remote sensing feature distribution map of the region to be studied. The second processing module is configured to perform heat map analysis on the vehicle traffic data to obtain a road network feature distribution map of the region to be studied, and perform spatial distribution analysis on the land ownership data to obtain a land ownership distribution table of the region to be studied. The model construction module is configured to construct a spatio-temporal data expression model of the region to be studied according to the remote sensing feature distribution map, the road network feature distribution map, and the land ownership distribution table. The land block identification module is configured to identify a land block to be identified in the region to be studied according to the spatio-temporal data expression model and a preset net land transfer identification model, wherein the net land transfer identification model is trained based on historical net land transfer data. The model construction module includes a feature fusion unit and a model construction unit. The feature fusion unit is configured to fuse the remote sensing feature distribution map and the road network feature distribution map based on latitude and longitude to obtain a regional feature distribution map. The model construction unit is configured to embed the land ownership distribution table into the regional feature distribution map according to each land block in the land ownership distribution table to obtain a spatio-temporal data expression model. The land block identification module includes a land block searching unit and a net land identification unit. The land block searching unit is configured to search for an identification information matrix of the land block to be identified based on the spatio-temporal data expression model. The net land identification unit is configured to input the identification information matrix into the net land transfer identification model to obtain a net land identification result of the land block to be identified.

6. A clean lot identification system based on multiple spatial elements according to claim 5, wherein, The first processing module includes an image enhancement unit, a land block division unit, and a block identification unit. The image enhancement unit is configured to perform image enhancement on the remote sensing image data to obtain a remote sensing enhanced image. The land block division unit is configured to divide the remote sensing enhanced image into remote sensing block images with a preset land block length as an identification unit length. The block identification unit is configured to perform block identification on the remote sensing block images based on a convolutional neural network to obtain a remote sensing feature distribution map.

Images