Idle land power development identification method and system based on GIS (Geographic Information System)

Abstract

The invention discloses a GIS-based idle land power development identification method and system, and relates to the field of land supervision identification, and the method comprises the steps: carrying out the multi-source heterogeneous fusion of remote sensing image data and aerial image data of a to-be-researched region, and obtaining a fusion image data set; on the basis of a deep convolutional neural network, land parcel identification is performed on the fused image data set in combination with a geographic information system to obtain a land parcel segmentation coordinate set; performing spatial overlay analysis according to the plot segmentation coordinate set in combination with the Internet of Things sensing data to obtain a power development state prediction layer, and generating a human activity thermodynamic layer based on a target tracking algorithm according to the Internet of Things sensing data and the aerial image data; according to the power development state prediction layer and the human activity thermodynamic layer, in combination with the public procedure data, idle land identification is carried out on the to-be-identified land parcel in the to-be-researched area, and an idle land power development identification result is obtained. The identification accuracy of idle land power development can be improved.

Description

Technical Field

[0001] The present application relates to the field of land supervision and identification, and in particular to a GIS-based idle land development identification method and system. Background Art

[0002] Idle land is a typical type of land that is "supplied but not used", and "supplied but not used" land causes serious waste of land resources. Therefore, land resource management of "supplied but not used" land is conducive to promoting sustainable urban development and optimizing the national land space layout.

[0003] Currently, the status of development or disposal of "unused" land, especially idle land, relies on manual inspections and voluntary reporting, supplemented by simple remote sensing image verification and supervision. However, this method of identifying idle land development has obvious flaws: manual inspections are too labor-intensive and inefficient, making it difficult to achieve large-scale, regular supervision; some areas fail to report in a timely manner, resulting in a large discrepancy between the rate of new idle land additions and the rate of disposal; traditional remote sensing technology is limited by the image data itself. For example, weather factors can affect the acquisition and resolution of remote sensing images, resulting in insufficient recognition accuracy when identifying idle land development through remote sensing images. The above flaws have led to insufficient accuracy in the existing identification of idle land development. How to improve the accuracy of idle land development identification remains a difficult problem that needs to be solved urgently. Summary of the Invention

[0004] This application provides a GIS-based idle land development start identification method and system to solve the technical problem of the lack of accuracy in the existing idle land development start identification.

[0005] According to a first aspect of the embodiments of the present application, a GIS-based method for identifying idle land for development is provided, comprising:

[0006] Perform multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset;

[0007] Based on a deep convolutional neural network and combined with a geographic information system, the fused image dataset is subjected to land parcel recognition to obtain a land parcel segmentation coordinate set;

[0008] Based on the plot segmentation coordinate set, combined with the IoT sensor data of the area to be studied, a spatial overlay analysis is performed to obtain a construction development status prediction layer corresponding to the area to be studied, and based on the IoT sensor data and the aerial image data, a human activity thermal layer corresponding to the area to be studied is generated based on a target tracking algorithm;

[0009] Based on the construction and development status prediction layer and the human activity thermal layer, combined with the public procedure data of the area to be studied, idle land is identified on the plots to be identified in the study area to obtain idle land construction and development identification results of the plots to be identified.

[0010] This application performs multi-source heterogeneous fusion on remote sensing image data and aerial image data of the study area to obtain a fused image dataset, and then uses a deep convolutional neural network to perform land parcel identification to obtain a land parcel segmentation coordinate set. The multi-source heterogeneous fusion of remote sensing image data and aerial image data can improve the comprehensiveness of the analyzed data and avoid identification errors caused by a single type of data. Then, spatial overlay analysis is performed on the IoT sensor data of the study area to obtain a construction development status prediction layer. Based on the IoT sensor data and aerial image data, a human activity thermal layer is generated based on a target tracking algorithm. The layer analysis of the IoT sensor data and aerial image data can improve the efficiency of analyzing the study area and thus improve the efficiency of identifying the identified land parcels. At the same time, the addition of multiple types of data improves the comprehensiveness of the analyzed data and the accuracy of identifying the identified land parcels. Then, the public procedure data of the study area is combined to identify idle land for the identified land parcels. The idle land identification results of the identified land parcels can be verified and corrected through the public procedure data, further improving the accuracy of identifying idle land construction development.

[0011] In certain embodiments of the present application, the multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset specifically includes:

[0012] Aligning the remote sensing image data and the aerial image data on a time axis according to the timestamp to obtain first remote sensing image data and first aerial image data;

[0013] Aligning the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data;

[0014] The second remote sensing image data and the second aerial image data are fused to obtain a fused image data set.

[0015] This application first aligns the time axis of remote sensing image data and aerial image data according to the timestamp, and then aligns the spatial coordinates according to the spatial coordinates, and then fuses them to obtain a fused image data set. By aligning the two batches of timestamps and spatial coordinates, multi-source heterogeneous data can be converted into multi-source homogeneous data, providing favorable conditions for subsequent fusion.

[0016] In certain embodiments of the present application, the deep convolutional neural network is combined with a geographic information system to perform land parcel recognition on the fused image dataset to obtain a land parcel segmentation coordinate set, specifically including:

[0017] Based on a deep convolutional neural network, semantic segmentation is performed on the fused image dataset to obtain a ground feature classification set;

[0018] According to the feature classification set of the land object, based on the edge detection algorithm, feature matching and recognition are performed on the fused image data set to obtain a land parcel classification image set, and according to the land parcel classification image set, combined with the spatial coordinate map of the provided land parcels obtained by the geographic information system, the association between the land parcels and the coordinates is constructed to obtain a land parcel segmentation coordinate set.

[0019] This application first performs semantic segmentation on the fused image dataset based on a deep convolutional neural network to obtain a classification set of land feature features, which can separate local land feature features from the fused image dataset, and then performs feature matching and recognition on the fused image dataset based on an edge detection algorithm, which can identify and segment different types of plots according to local land feature features. Furthermore, combined with the spatial coordinate map of the provided plots obtained by the geographic information system, the association between the plots and the coordinates is constructed to obtain a plot segmentation coordinate set, thereby providing conditions for subsequent analysis and identification.

[0020] In certain embodiments of the present application, the spatial overlay analysis is performed based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and the human activity thermal layer corresponding to the area to be studied is generated based on the IoT sensor data and the aerial image data and a target tracking algorithm, specifically including:

[0021] According to the plot segmentation coordinate set, combined with the IoT sensor data of the area to be studied, a spatial overlay analysis is performed based on the layer overlay method to obtain the construction development status prediction layer;

[0022] Extracting first human activity trajectory data based on the IoT sensor data, and obtaining second human activity trajectory data based on the aerial image data and a target tracking algorithm;

[0023] Based on the layer overlay method, the first human activity trajectory data and the second human activity trajectory data are spatially overlaid and analyzed to obtain the human activity thermal layer.

[0024] This application first divides the coordinate set according to the plot, combines the Internet of Things sensor data of the area to be studied, and performs spatial overlay analysis based on the layer overlay method to obtain a construction development status prediction layer; then, the first human activity trajectory data is extracted according to the Internet of Things sensor data, and the second human activity trajectory data is obtained based on the target tracking algorithm according to the aerial image data, and then a spatial overlay analysis is performed based on the layer overlay method to obtain a human activity thermal layer. By performing layer analysis on the Internet of Things sensor data and the aerial image data, the efficiency of analyzing the study area can be improved, and the efficiency of identifying the plots to be identified can be improved. At the same time, multiple types of data are added, the comprehensiveness of the analysis data is improved, and the accuracy of identifying the plots to be identified is improved.

[0025] In certain embodiments of the present application, the idle land identification is performed on the plots to be identified in the study area based on the construction and development status prediction layer and the human activity thermal layer, in combination with the public procedure data of the study area, to obtain the idle land construction and development identification results of the plots to be identified, specifically including:

[0026] Determining the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer;

[0027] Determining a human activity recognition result for the land parcel to be recognized based on the human activity thermal map;

[0028] Determining a first idle land identification result according to the land parcel distribution type and the human activity identification result;

[0029] The first idle land identification result is verified and corrected based on the public procedure data of the area to be studied to obtain the idle land development commencement identification result of the land parcel to be identified.

[0030] This application first determines the plot distribution type and human activity identification results of the plot to be identified based on the construction and development status prediction layer and the human activity thermal layer, and then determines the first idle land identification result, and then combines the public procedure data for verification and correction to obtain the idle land construction and development identification result of the plot to be identified, which can improve the accuracy of idle land construction and development identification.

[0031] According to a second aspect of the embodiment of the present application, a GIS-based idle land development identification system is provided, comprising a multi-source fusion module, a land parcel identification module, a layer analysis module, and an idle land identification module;

[0032] The multi-source fusion module is used to perform multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image data set;

[0033] The land parcel recognition module is used to perform land parcel recognition on the fused image dataset based on a deep convolutional neural network in combination with a geographic information system to obtain a land parcel segmentation coordinate set;

[0034] The layer analysis module is used to perform spatial overlay analysis based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and generate a human activity thermal layer corresponding to the area to be studied based on the IoT sensor data and the aerial image data and a target tracking algorithm;

[0035] The idle land identification module is used to identify idle land in the to-be-identified plots in the study area based on the construction and development status prediction layer and the human activity thermal layer, combined with the public procedure data of the to-be-identified area, to obtain the idle land construction and development identification results of the to-be-identified plots.

[0036] In certain embodiments of the present application, the multi-source fusion module includes a time axis alignment unit, a spatial coordinate alignment unit, and a data fusion unit;

[0037] The time axis alignment unit is used to perform time axis alignment on the remote sensing image data and the aerial image data according to the timestamp to obtain the first remote sensing image data and the first aerial image data;

[0038] The spatial coordinate alignment unit is configured to perform spatial coordinate alignment on the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data;

[0039] The data fusion unit is used to fuse the second remote sensing image data and the second aerial image data to obtain a fused image data set.

[0040] In certain embodiments of the present application, the land parcel recognition module includes a semantic segmentation recognition unit and a feature matching recognition unit;

[0041] The semantic segmentation and recognition unit is used to perform semantic segmentation on the fused image dataset based on a deep convolutional neural network to obtain a ground feature classification set;

[0042] The feature matching and recognition unit is used to perform feature matching and recognition on the fused image data set based on the edge detection algorithm according to the land feature classification set to obtain a land parcel classification image set, and to construct an association between the land parcels and coordinates based on the land parcel classification image set in combination with the spatial coordinate map of the provided land parcels obtained by the geographic information system to obtain a land parcel segmentation coordinate set.

[0043] In certain embodiments of the present application, the layer analysis module includes a land distribution analysis unit, an activity trajectory analysis unit, and an activity thermal analysis unit;

[0044] The land parcel distribution analysis unit is configured to perform spatial overlay analysis based on the land parcel segmentation coordinate set and the IoT sensor data of the area to be studied, thereby obtaining the construction development status prediction layer;

[0045] The activity trajectory analysis unit is configured to extract first human activity trajectory data based on the IoT sensor data, and obtain second human activity trajectory data based on the aerial image data and a target tracking algorithm;

[0046] The activity thermal analysis unit is configured to perform spatial overlay analysis on the first human activity trajectory data and the second human activity trajectory data based on a layer overlay method to obtain the human activity thermal layer.

[0047] In certain embodiments of the present application, the idle land identification module includes a land parcel type identification unit, a human activity identification unit, an idle land identification unit, and an identification verification and correction unit;

[0048] The land parcel type identification unit is configured to determine the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer;

[0049] The human activity recognition unit is configured to determine a human activity recognition result of a to-be-recognized plot based on the human activity thermal map;

[0050] The idle land identification unit is configured to determine a first idle land identification result based on the land parcel distribution type and the human activity identification result;

[0051] The identification verification and correction unit is used to verify and correct the first idle land identification result based on the public procedure data of the area to be studied, so as to obtain the idle land development commencement identification result of the land parcel to be identified.

[0052] This application performs multi-source heterogeneous fusion on remote sensing image data and aerial image data of the study area to obtain a fused image dataset, and then uses a deep convolutional neural network to perform land parcel identification to obtain a land parcel segmentation coordinate set. The multi-source heterogeneous fusion of remote sensing image data and aerial image data can improve the comprehensiveness of the analyzed data and avoid identification errors caused by a single type of data. Then, spatial overlay analysis is performed on the IoT sensor data of the study area to obtain a construction development status prediction layer. Based on the IoT sensor data and aerial image data, a human activity thermal layer is generated based on a target tracking algorithm. The layer analysis of the IoT sensor data and aerial image data can improve the efficiency of analyzing the study area and thus improve the efficiency of identifying the identified land parcels. At the same time, the addition of multiple types of data improves the comprehensiveness of the analyzed data and the accuracy of identifying the identified land parcels. Then, the public procedure data of the study area is combined to identify idle land for the identified land parcels. The idle land identification results of the identified land parcels can be verified and corrected through the public procedure data, further improving the accuracy of identifying idle land construction development. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 : A flowchart of a GIS-based idle land development identification method shown in certain embodiments of the present application;

[0054] Figure 2 : A module structure diagram of a GIS-based idle land development identification system shown in certain embodiments of the present application. DETAILED DESCRIPTION

[0055] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below in conjunction with the accompanying drawings are exemplary and are only used to explain some embodiments of the present application and should not be understood as limiting the embodiments of the present application. Based on the embodiments shown in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0056] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of this application, unless otherwise clearly specified, "multiple" and "several" mean two or more.

[0057] The status of idle land development or disposal relies on manual inspections and voluntary reporting, supplemented by simple remote sensing image verification and supervision. However, this method of identifying idle land development has obvious flaws: manual inspections are too labor-intensive and inefficient, making it difficult to achieve large-scale, regular supervision; some areas fail to report in a timely manner, resulting in a large discrepancy between the rate of new idle land additions and the rate of disposal; traditional remote sensing technology is limited by image resolution and a single data source, making it difficult to accurately distinguish the actual use status of land. These flaws all lead to insufficient accuracy in the current identification of idle land development. How to improve the accuracy of idle land development identification remains a difficult problem that needs to be solved by existing technologies.

[0058] Based on the above technical background, please refer to Figure 1 The embodiment of the present application provides a GIS-based method for identifying idle land for development, including steps S101 to S104, each of which is specifically as follows:

[0059] Step S101: Perform multi-source heterogeneous fusion on the remote sensing image data and aerial image data of the study area to obtain a fused image dataset.

[0060] In certain embodiments of the present application, the multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset specifically includes:

[0061] Aligning the remote sensing image data and the aerial image data on a time axis according to the timestamp to obtain first remote sensing image data and first aerial image data;

[0062] Aligning the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data;

[0063] The second remote sensing image data and the second aerial image data are fused to obtain a fused image data set.

[0064] In certain embodiments of the present application, the implementation of time axis alignment based on timestamps may be a timestamp interpolation method, and a preferred implementation is a timestamp linear interpolation method.

[0065] In certain embodiments of the present application, the implementation method of performing spatial coordinate alignment according to spatial coordinates may be a spatial coordinate projection method, and a preferred implementation method is a three-dimensional rectangular spatial coordinate projection method.

[0066] In certain embodiments of the present application, the fusion of the second remote sensing image data and the second aerial image data may be performed by splicing each piece of data in the second remote sensing image data with the data of the corresponding timestamp in the second aerial image data according to the timestamp.

[0067] This application first aligns the time axis of remote sensing image data and aerial image data according to the timestamp, and then aligns the spatial coordinates according to the spatial coordinates, and then fuses them to obtain a fused image data set. By aligning the two batches of timestamps and spatial coordinates, multi-source heterogeneous data can be converted into multi-source homogeneous data, providing favorable conditions for subsequent fusion.

[0068] Step S102: Based on a deep convolutional neural network and in combination with a geographic information system, land parcel identification is performed on the fused image dataset to obtain a land parcel segmentation coordinate set.

[0069] In certain embodiments of the present application, the deep convolutional neural network is combined with a geographic information system to perform land parcel recognition on the fused image dataset to obtain a land parcel segmentation coordinate set, specifically including:

[0070] Based on a deep convolutional neural network, semantic segmentation is performed on the fused image dataset to obtain a ground feature classification set;

[0071] According to the feature classification set of the land object, based on the edge detection algorithm, feature matching and recognition are performed on the fused image data set to obtain a land parcel classification image set, and according to the land parcel classification image set, combined with the spatial coordinate map of the provided land parcels obtained by the geographic information system, the association between the land parcels and the coordinates is constructed to obtain a land parcel segmentation coordinate set.

[0072] In certain embodiments of the present application, the edge detection algorithm includes but is not limited to the Canny algorithm, the Sobel algorithm and the Prewitt algorithm, and the preferred embodiment is the Canny algorithm.

[0073] Generally, those skilled in the art can easily understand that the Geographic Information System (GIS) is a geographic information system.

[0074] This application first performs semantic segmentation on the fused image dataset based on a deep convolutional neural network to obtain a classification set of land feature features, which can separate local land feature features from the fused image dataset, and then performs feature matching and recognition on the fused image dataset based on an edge detection algorithm, which can identify and segment different types of plots according to local land feature features. Furthermore, combined with the spatial coordinate map of the provided plots obtained by the geographic information system, the association between the plots and the coordinates is constructed to obtain a plot segmentation coordinate set, thereby providing conditions for subsequent analysis and identification.

[0075] Step S103: Based on the plot segmentation coordinate set, spatial overlay analysis is performed in combination with the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and based on the IoT sensor data and the aerial image data and a target tracking algorithm, a human activity thermal layer corresponding to the area to be studied is generated.

[0076] In certain embodiments of the present application, the spatial overlay analysis is performed based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and the human activity thermal layer corresponding to the area to be studied is generated based on the IoT sensor data and the aerial image data and a target tracking algorithm, specifically including:

[0077] According to the plot segmentation coordinate set, combined with the IoT sensor data of the area to be studied, a spatial overlay analysis is performed based on the layer overlay method to obtain the construction development status prediction layer;

[0078] Extracting first human activity trajectory data based on the IoT sensor data, and obtaining second human activity trajectory data based on the aerial image data and a target tracking algorithm;

[0079] Based on the layer overlay method, the first human activity trajectory data and the second human activity trajectory data are spatially overlaid and analyzed to obtain the human activity thermal layer.

[0080] In certain embodiments of the present application, extracting the first human activity trajectory data based on the IoT sensor data is specifically: determining multiple groups of individual activity trajectories based on the usage logs of each sensor in the IoT sensor data; and extracting the first human activity trajectory data based on the multiple groups of individual activity trajectories.

[0081] This application first divides the coordinate set according to the plot, combines the Internet of Things sensor data of the area to be studied, and performs spatial overlay analysis based on the layer overlay method to obtain a construction development status prediction layer; then, the first human activity trajectory data is extracted according to the Internet of Things sensor data, and the second human activity trajectory data is obtained based on the target tracking algorithm according to the aerial image data, and then a spatial overlay analysis is performed based on the layer overlay method to obtain a human activity thermal layer. By performing layer analysis on the Internet of Things sensor data and the aerial image data, the efficiency of analyzing the study area can be improved, and the efficiency of identifying the plots to be identified can be improved. At the same time, multiple types of data are added, the comprehensiveness of the analysis data is improved, and the accuracy of identifying the plots to be identified is improved.

[0082] Step S104: Idle land identification is performed on the plots to be identified in the study area based on the construction and development status prediction layer and the human activity thermal layer, in combination with the public procedure data of the study area, to obtain idle land construction and development identification results for the plots to be identified.

[0083] In certain embodiments of the present application, the idle land identification is performed on the plots to be identified in the study area based on the construction and development status prediction layer and the human activity thermal layer, in combination with the public procedure data of the study area, to obtain the idle land construction and development identification results of the plots to be identified, specifically including:

[0084] Determining the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer;

[0085] Determining a human activity recognition result for the land parcel to be recognized based on the human activity thermal map;

[0086] Determining a first idle land identification result according to the land parcel distribution type and the human activity identification result;

[0087] The first idle land identification result is verified and corrected based on the public procedure data of the area to be studied to obtain the idle land development commencement identification result of the land parcel to be identified.

[0088] This application first determines the plot distribution type and human activity identification results of the plot to be identified based on the construction and development status prediction layer and the human activity thermal layer, and then determines the first idle land identification result, and then combines the public procedure data for verification and correction to obtain the idle land construction and development identification result of the plot to be identified, which can improve the accuracy of idle land construction and development identification.

[0089] Compared with the existing technology, the present application performs multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset, and then performs land parcel identification based on a deep convolutional neural network to obtain a land parcel segmentation coordinate set. The multi-source heterogeneous fusion of remote sensing image data and aerial image data can improve the comprehensiveness of the analysis data and avoid recognition errors caused by a single type of data. Then, spatial overlay analysis is performed on the IoT sensor data of the study area to obtain a construction development status prediction layer, and a human activity thermal layer is generated based on the target tracking algorithm based on the IoT sensor data and aerial image data. The layer analysis of the IoT sensor data and aerial image data can improve the efficiency of analyzing the study area and thus improve the efficiency of identifying the identified land parcels. At the same time, multiple types of data are added, the comprehensiveness of the analysis data is improved, and the recognition accuracy of the identified land parcels is improved. Then, the public procedure data of the study area is combined to identify idle land for the identified land parcels. The idle land identification results of the identified land parcels can be verified and corrected through the public procedure data, further improving the accuracy of identifying idle land construction development.

[0090] Corresponding to the above method, see Figure 2 , the embodiment of the present application provides a GIS-based idle land development identification system, including a multi-source fusion module 210, a land parcel identification module 220, a layer analysis module 230 and an idle land identification module 240;

[0091] The multi-source fusion module 210 is used to perform multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset;

[0092] The land parcel identification module 220 is used to perform land parcel identification on the fused image dataset based on a deep convolutional neural network in combination with a geographic information system to obtain a land parcel segmentation coordinate set;

[0093] The layer analysis module 230 is configured to perform spatial overlay analysis based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and generate a human activity thermal layer corresponding to the area to be studied based on the IoT sensor data and the aerial image data and a target tracking algorithm;

[0094] The idle land identification module 240 is used to identify idle land for the plots to be identified in the study area based on the construction and development status prediction layer and the human activity thermal layer, combined with the public procedure data of the study area, to obtain idle land construction and development identification results for the plots to be identified.

[0095] In certain embodiments of the present application, the multi-source fusion module 210 includes a time axis alignment unit, a spatial coordinate alignment unit, and a data fusion unit;

[0096] The time axis alignment unit is used to perform time axis alignment on the remote sensing image data and the aerial image data according to the timestamp to obtain the first remote sensing image data and the first aerial image data;

[0097] The spatial coordinate alignment unit is configured to perform spatial coordinate alignment on the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data;

[0098] The data fusion unit is used to fuse the second remote sensing image data and the second aerial image data to obtain a fused image data set.

[0099] In certain embodiments of the present application, the land parcel identification module 220 includes a semantic segmentation identification unit and a feature matching identification unit;

[0100] The semantic segmentation and recognition unit is used to perform semantic segmentation on the fused image dataset based on a deep convolutional neural network to obtain a ground feature classification set;

[0101] The feature matching and recognition unit is used to perform feature matching and recognition on the fused image data set based on the edge detection algorithm according to the land feature classification set to obtain a land parcel classification image set, and to construct an association between the land parcels and coordinates based on the land parcel classification image set in combination with the spatial coordinate map of the provided land parcels obtained by the geographic information system to obtain a land parcel segmentation coordinate set.

[0102] In certain embodiments of the present application, the layer analysis module 230 includes a land distribution analysis unit, an activity trajectory analysis unit, and an activity thermal analysis unit;

[0103] The land parcel distribution analysis unit is configured to perform spatial overlay analysis based on the land parcel segmentation coordinate set and the IoT sensor data of the area to be studied, thereby obtaining the construction development status prediction layer;

[0104] The activity trajectory analysis unit is configured to extract first human activity trajectory data based on the IoT sensor data, and obtain second human activity trajectory data based on the aerial image data and a target tracking algorithm;

[0105] The activity thermal analysis unit is configured to perform spatial overlay analysis on the first human activity trajectory data and the second human activity trajectory data based on a layer overlay method to obtain the human activity thermal layer.

[0106] In certain embodiments of the present application, the idle land identification module 240 includes a land parcel type identification unit, a human activity identification unit, an idle land identification unit, and an identification verification and correction unit;

[0107] The land parcel type identification unit is configured to determine the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer;

[0108] The human activity recognition unit is configured to determine a human activity recognition result of a to-be-recognized plot based on the human activity thermal map;

[0109] The idle land identification unit is configured to determine a first idle land identification result based on the land parcel distribution type and the human activity identification result;

[0110] The identification verification and correction unit is used to verify and correct the first idle land identification result based on the public procedure data of the area to be studied, so as to obtain the idle land development commencement identification result of the land parcel to be identified.

[0111] This application performs multi-source heterogeneous fusion on remote sensing image data and aerial image data of the study area to obtain a fused image dataset, and then uses a deep convolutional neural network to perform land parcel identification to obtain a land parcel segmentation coordinate set. The multi-source heterogeneous fusion of remote sensing image data and aerial image data can improve the comprehensiveness of the analyzed data and avoid identification errors caused by a single type of data. Then, spatial overlay analysis is performed on the IoT sensor data of the study area to obtain a construction development status prediction layer. Based on the IoT sensor data and aerial image data, a human activity thermal layer is generated based on a target tracking algorithm. The layer analysis of the IoT sensor data and aerial image data can improve the efficiency of analyzing the study area and thus improve the efficiency of identifying the identified land parcels. At the same time, the addition of multiple types of data improves the comprehensiveness of the analyzed data and the accuracy of identifying the identified land parcels. Then, the public procedure data of the study area is combined to identify idle land for the identified land parcels. The idle land identification results of the identified land parcels can be verified and corrected through the public procedure data, further improving the accuracy of identifying idle land construction development.

[0112] It should be understood that the system provided in the embodiment of the present application corresponds to the aforementioned method. The idle land construction and development identification system based on GIS provided in the embodiment of the present application can implement the idle land construction and development identification method based on GIS provided in any embodiment of the present application.

[0113] Adaptively, the embodiments of the present application further provide a computer device and a computer-readable storage medium.

[0114] The computer device comprises: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor;

[0115] Among them, when the processor executes the computer program, it implements a GIS-based idle land development identification method of the present application.

[0116] The computer-readable storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute a GIS-based idle land development identification method of the present application.

[0117] The above description is a partial embodiment of the present application, which further describes the purpose, technical solutions, and beneficial effects of the present application in detail. It should be understood that the above description of the partial embodiment of the present application is not to be construed as limiting the present application. In particular, it is pointed out that for those skilled in the art, any changes, modifications, equivalent substitutions, and variations made within the spirit and principles of the present application should be included within the scope of protection of the present application.

Claims

1. A GIS-based method for identifying idle land for development, characterized by: include: Perform multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset; Based on a deep convolutional neural network and combined with a geographic information system, the fused image dataset is subjected to land parcel recognition to obtain a land parcel segmentation coordinate set; Based on the plot segmentation coordinate set, combined with the IoT sensor data of the area to be studied, a spatial overlay analysis is performed to obtain a construction development status prediction layer corresponding to the area to be studied, and based on the IoT sensor data and the aerial image data, a human activity thermal layer corresponding to the area to be studied is generated based on a target tracking algorithm; Based on the construction and development status prediction layer and the human activity thermal layer, combined with the public procedure data of the area to be studied, idle land is identified on the plots to be identified in the study area to obtain idle land construction and development identification results of the plots to be identified.

2. The GIS-based idle land development identification method according to claim 1 is characterized in that: The multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image dataset specifically includes: Aligning the remote sensing image data and the aerial image data on a time axis according to the timestamp to obtain first remote sensing image data and first aerial image data; Aligning the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data; The second remote sensing image data and the second aerial image data are fused to obtain a fused image data set.

3. The GIS-based idle land development identification method according to claim 1 is characterized in that: The method of performing land parcel recognition on the fused image dataset based on a deep convolutional neural network in combination with a geographic information system to obtain a land parcel segmentation coordinate set specifically includes: Based on a deep convolutional neural network, semantic segmentation is performed on the fused image dataset to obtain a ground feature classification set; According to the feature classification set of the land object, based on the edge detection algorithm, feature matching and recognition are performed on the fused image data set to obtain a land parcel classification image set, and according to the land parcel classification image set, combined with the spatial coordinate map of the provided land parcels obtained by the geographic information system, the association between the land parcels and the coordinates is constructed to obtain a land parcel segmentation coordinate set.

4. The GIS-based idle land development identification method according to claim 1 is characterized in that: The method further comprises: performing spatial overlay analysis based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied; and generating a human activity thermal layer corresponding to the area to be studied based on the target tracking algorithm and the IoT sensor data and the aerial image data, specifically including: According to the plot segmentation coordinate set, combined with the IoT sensor data of the area to be studied, a spatial overlay analysis is performed based on the layer overlay method to obtain the construction development status prediction layer; Extracting first human activity trajectory data based on the IoT sensor data, and obtaining second human activity trajectory data based on the aerial image data and a target tracking algorithm; Based on the layer overlay method, the first human activity trajectory data and the second human activity trajectory data are spatially overlaid and analyzed to obtain the human activity thermal layer.

5. The GIS-based idle land development identification method according to claim 1 is characterized in that: The idle land identification is performed on the plots to be identified in the study area based on the construction and development status prediction layer and the human activity thermal layer, in combination with the public procedure data of the study area, to obtain the idle land construction and development identification results of the plots to be identified, specifically including: Determining the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer; Determining a human activity recognition result for the land parcel to be recognized based on the human activity thermal map; Determining a first idle land identification result according to the land parcel distribution type and the human activity identification result; The first idle land identification result is verified and corrected based on the public procedure data of the area to be studied to obtain the idle land development commencement identification result of the land parcel to be identified.

6. A GIS-based idle land development identification system, characterized by: It includes multi-source fusion module, land parcel identification module, layer analysis module and idle land identification module; The multi-source fusion module is used to perform multi-source heterogeneous fusion of remote sensing image data and aerial image data of the study area to obtain a fused image data set; The land parcel recognition module is used to perform land parcel recognition on the fused image dataset based on a deep convolutional neural network in combination with a geographic information system to obtain a land parcel segmentation coordinate set; The layer analysis module is used to perform spatial overlay analysis based on the plot segmentation coordinate set and the IoT sensor data of the area to be studied to obtain a construction development status prediction layer corresponding to the area to be studied, and generate a human activity thermal layer corresponding to the area to be studied based on the IoT sensor data and the aerial image data and a target tracking algorithm; The idle land identification module is used to identify idle land in the to-be-identified plots in the study area based on the construction and development status prediction layer and the human activity thermal layer, combined with the public procedure data of the to-be-identified area, to obtain the idle land construction and development identification results of the to-be-identified plots.

7. The GIS-based idle land development identification system according to claim 6 is characterized in that: The multi-source fusion module includes a time axis alignment unit, a space coordinate alignment unit and a data fusion unit; The time axis alignment unit is used to perform time axis alignment on the remote sensing image data and the aerial image data according to the timestamp to obtain the first remote sensing image data and the first aerial image data; The spatial coordinate alignment unit is configured to perform spatial coordinate alignment on the first remote sensing image data and the first aerial image data according to spatial coordinates to obtain second remote sensing image data and second aerial image data; The data fusion unit is used to fuse the second remote sensing image data and the second aerial image data to obtain a fused image data set.

8. The GIS-based idle land development identification system according to claim 6 is characterized in that: The land parcel recognition module includes a semantic segmentation recognition unit and a feature matching recognition unit; The semantic segmentation and recognition unit is used to perform semantic segmentation on the fused image dataset based on a deep convolutional neural network to obtain a ground feature classification set; The feature matching and recognition unit is used to perform feature matching and recognition on the fused image data set based on the edge detection algorithm according to the land feature classification set to obtain a land parcel classification image set, and to construct an association between the land parcels and coordinates based on the land parcel classification image set in combination with the spatial coordinate map of the provided land parcels obtained by the geographic information system to obtain a land parcel segmentation coordinate set.

9. The GIS-based idle land development identification system according to claim 6 is characterized in that: The layer analysis module includes a land distribution analysis unit, an activity trajectory analysis unit and an activity thermal analysis unit; The land parcel distribution analysis unit is configured to perform spatial overlay analysis based on the land parcel segmentation coordinate set and the IoT sensor data of the area to be studied, thereby obtaining the construction development status prediction layer; The activity trajectory analysis unit is configured to extract first human activity trajectory data based on the IoT sensor data, and obtain second human activity trajectory data based on the aerial image data and a target tracking algorithm; The activity thermal analysis unit is configured to perform spatial overlay analysis on the first human activity trajectory data and the second human activity trajectory data based on a layer overlay method to obtain the human activity thermal layer.

10. The GIS-based idle land development identification system according to claim 6 is characterized in that: The idle land identification module includes a land type identification unit, a human activity identification unit, an idle land identification unit and an identification verification and correction unit; The land parcel type identification unit is configured to determine the land parcel distribution type of the land parcel to be identified based on the construction and development status prediction layer; The human activity recognition unit is configured to determine a human activity recognition result of a to-be-recognized plot based on the human activity thermal map; The idle land identification unit is configured to determine a first idle land identification result based on the land parcel distribution type and the human activity identification result; The identification verification and correction unit is used to verify and correct the first idle land identification result based on the public procedure data of the area to be studied, so as to obtain the idle land development commencement identification result of the land parcel to be identified.

Images