Rural building remote sensing dynamic monitoring method and system and computer equipment

Abstract

The invention relates to the technical field of remote sensing monitoring, and discloses a rural house building remote sensing dynamic monitoring method and system and computer equipment, and the method comprises the steps: summarizing homestead base basic information survey data, house and land integrated right confirmation registration issuing data, stock disorderly occupied cultivated land house building pattern spot data and land space planning data; obtaining rural building basic data; performing change detection on the remote sensing image of the target monitoring area to obtain a change detection result of the newly-built rural house; comparing with approval information in the rural house building basic data, and determining suspected illegal house building pattern spots; issuing the verification result to patrol personnel through the mobile terminal application for field verification to obtain an illegal house building verification confirmation result; in a preset cloud management platform, the rural house building basic data, the suspected illegal house building pattern spots and the illegal house building verification and confirmation result are visually displayed, and the method improves the accuracy of rural house building change detection and realizes full-process digital management.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing monitoring technology, and in particular to a remote sensing dynamic monitoring method, system and computer equipment for rural house construction. Background Art

[0002] Traditional rural housing construction supervision relies primarily on manual inspections and report verification, resulting in limited coverage, delayed detection of illegal construction, and inefficient supervision. The existing supervision model struggles to achieve real-time monitoring of housing construction activities in rural areas. Illegal construction is often discovered only a long time after it occurs, missing the optimal opportunity for action. This leads to a regulatory dilemma where the cost of illegal construction is low but the cost of enforcement is high. Another prominent issue currently facing rural housing construction supervision is the fragmentation of basic data and the severe phenomenon of information silos. This fragmented data prevents supervisory departments from fully understanding the overall situation of rural housing construction in the region, affecting the accuracy of illegal construction identification and the scientific nature of regulatory decisions. Summary of the Invention

[0003] The present invention provides a remote sensing dynamic monitoring method, system and computer equipment for rural house construction, which improves the accuracy of rural house construction change detection and realizes full-process digital management.

[0004] In a first aspect, the present invention provides a method for dynamic remote sensing monitoring of rural housing construction, the method comprising: The basic data on rural housing construction is obtained by summarizing the survey data on basic information of homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for housing construction, and the land space planning data; Based on the rural housing construction basic data, change detection is performed on the remote sensing image of the target monitoring area to obtain the change detection results of the newly built rural houses; Comparing the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots; The suspected illegal building images are sent to the inspectors via the mobile application for on-site verification, and the illegal building verification confirmation results are obtained; In the preset cloud management platform, the basic data of rural house construction, the suspected illegal house construction spots and the illegal house construction verification and confirmation results are visualized, wherein the geographical location distribution of the suspected illegal house construction spots is subjected to spatial clustering analysis and monitoring frequency statistics to obtain the spatial activity trajectory data of illegal house construction; based on the illegal house construction spatial activity trajectory data, the occurrence pattern of illegal house construction in different geographical locations is analyzed to establish a spatial location-related monitoring parameter adjustment mechanism to obtain a full-coverage spatial repeated learning control law; according to the full-coverage spatial repeated learning control law, the monitoring focus and monitoring frequency of different geographical areas are adaptively adjusted to obtain an adaptive spatial monitoring and control scheme; the adaptive spatial monitoring and control scheme is applied to the visualization display update process of the cloud management platform to obtain an adaptively optimized visualization display result.

[0005] In conjunction with the first aspect, in a first implementation of the first aspect of the present invention, the basic information survey data of homesteads, the real estate and land rights registration and certification data, the existing illegally occupied farmland for housing construction data, and the national land space planning data are aggregated to obtain the basic data for rural housing construction, including: Extract the spatial location coordinates, area boundaries, ownership relationship and approval time from the homestead basic information survey data to obtain homestead information records; Extract the building area, building height, building structure and use function from the real estate and land rights registration and certification data to obtain the house rights confirmation information record; Extract the location, type, area and disposal status of illegal buildings from the existing illegal construction data of farmland occupation to obtain historical illegal construction information records; The homestead information records, the house title confirmation information records, the historical illegal construction information records and the national land space planning data are aggregated to obtain basic data on rural house construction.

[0006] In combination with the first aspect, in a second implementation of the first aspect of the present invention, performing change detection on a remote sensing image of a target monitoring area based on the rural housing construction basic data to obtain a newly built rural housing change detection result includes: Acquiring a remote sensing image of the target monitoring area and correcting the remote sensing image to obtain a quality-corrected remote sensing image; The remote sensing images after quality correction are geometrically corrected and spatially registered to obtain spatially standardized remote sensing images, and the remote sensing images are arranged in time sequence according to shooting time information of the spatially standardized remote sensing images to obtain a sequence of rural housing construction remote sensing images; Based on the rural housing construction basic data, change detection is performed on the rural housing construction remote sensing image sequence to obtain a change detection result of the newly built rural houses.

[0007] In combination with the first aspect, in a third implementation of the first aspect of the present invention, performing change detection on the rural housing construction remote sensing image sequence based on the rural housing construction basic data to obtain a newly built rural housing change detection result includes: Extracting features from the rural house construction remote sensing image sequence to obtain house identification feature data including rural building location, area, shape and spectral features; Based on the house recognition feature data, pixel-level difference calculation and target change analysis are performed on images at different times to obtain detection results of changed areas such as new additions, expansions, and demolitions of buildings; The change area detection results are spatially superimposed and attribute matched according to the rural housing construction basic data, and the change areas that do not match the existing building records are screened out to obtain the change detection results of the newly built rural houses.

[0008] In combination with the first aspect, in a fourth implementation of the first aspect of the present invention, performing spatial overlay and attribute matching analysis on the change area detection results based on the rural housing construction basic data, screening out change areas that do not match existing building records, and obtaining new rural housing change detection results includes: Determine the changed area spatial information including position coordinates, area range and geometric shape according to the changed area detection result; Perform spatial overlay analysis on the spatial information of the changed area and the homestead information records in the rural housing construction basic data to identify areas with suspected illegal location changes; Perform attribute matching retrieval on the house ownership confirmation information records and historical illegal construction information records in the rural house construction basic data according to the suspected illegal location change area, and obtain the unrecorded building change area; Based on the unrecorded building change area, the construction activity type is identified and the scale is estimated to obtain the new rural house change detection result.

[0009] In combination with the first aspect, in a fifth implementation of the first aspect of the present invention, comparing the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing patches includes: Extract the building location coordinates, building area, construction time and building type from the newly built farmhouse change detection results and construct a newly built farmhouse element information table; Perform spatial query and approval status search on homestead information records in the rural housing basic data based on the location coordinates in the newly built rural housing element information table to identify suspected areas of construction without approval; Perform deviation analysis on the building area and location information in the newly built rural housing element information table and the corresponding approved area and approved location in the rural housing basic data to identify suspected areas where small buildings are approved for construction and large buildings are approved for construction; Based on the location coordinates in the newly built rural housing element information table, the land use nature query and compliance judgment are performed on the national land space planning data in the rural housing basic data to identify the building locations within the cultivated land protection area, and then the suspected areas of construction without approval, the suspected areas of building large with small approval and building B with approval A, and the locations of buildings occupying cultivated land indiscriminately are classified and summarized to obtain areas of suspected illegal construction.

[0010] In combination with the first aspect, in a sixth implementation of the first aspect of the present invention, the sending of the suspected illegal building image to an inspector for on-site verification via a mobile application to obtain an illegal building verification confirmation result includes: Extracting location information and assigning tasks to the suspected illegal building spots to obtain a verification task list; Push the verification task list to the corresponding inspectors via the mobile application, and the mobile application provides a mobile verification work interface; Based on the mobile terminal verification work interface, the inspection personnel are guided to the suspected illegal building site to conduct on-site measurement and situation investigation, and obtain on-site verification data records; According to the on-site verification data records, the verification conclusion is determined and the results are uploaded through the mobile application to obtain the verification confirmation results of the illegal building.

[0011] In conjunction with the first aspect, in a seventh implementation of the first aspect of the present invention, the visual display of the rural housing basic data, the suspected illegal housing spots, and the illegal housing verification and confirmation results in the preset cloud management platform includes: In a preset cloud management platform, the rural housing construction basic data is set as a base map layer, the suspected illegal housing construction spots are set as a monitoring layer, and the illegal housing construction verification and confirmation results are set as a disposal layer to obtain a display layer; Based on the display layer, interface layout design and interactive function configuration are performed in the cloud management platform to obtain a management interface, and the management interface is rendered with map distribution, and processing progress statistics and evaluation results are displayed to obtain a visual display result.

[0012] In a second aspect, the present invention provides a remote sensing dynamic monitoring system for rural housing construction, the remote sensing dynamic monitoring system for rural housing construction comprising: The data aggregation module is used to aggregate the basic information survey data of homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for housing construction, and the land space planning data to obtain the basic data on rural housing construction; A change detection module is used to perform change detection on the remote sensing image of the target monitoring area based on the rural housing construction basic data to obtain the change detection results of the newly built rural houses; A comparison module is used to compare the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots; The on-site verification module is used to send the suspected illegal building map to the inspection personnel through the mobile application for on-site verification and obtain the illegal building verification confirmation result; A visualization display module is used to visualize the basic data on rural house construction, the suspected illegal house construction spots and the illegal house construction verification and confirmation results in a preset cloud management platform, wherein spatial clustering analysis and monitoring frequency statistics are performed on the geographical location distribution of the suspected illegal house construction spots to obtain spatial activity trajectory data of illegal house construction; based on the illegal house construction spatial activity trajectory data, a spatial location-related monitoring parameter adjustment mechanism is established to obtain a full-coverage spatial repeated learning control law; according to the full-coverage spatial repeated learning control law, the monitoring focus and monitoring frequency of different geographical areas are adaptively adjusted to obtain an adaptive spatial monitoring and control scheme; the adaptive spatial monitoring and control scheme is applied to the visualization display update process of the cloud management platform to obtain an adaptively optimized visualization display result.

[0013] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned rural house construction remote sensing dynamic monitoring method.

[0014] The technical solution provided by this invention breaks down traditional information silos by integrating and processing data from homestead basic information surveys, integrated real estate and land rights registration and certification data, existing illegally occupied farmland for housing construction, and national land and space planning data. This process establishes a comprehensive data base for rural housing construction. Remote sensing image change detection based on this data base, combined with comprehensive analysis of multi-dimensional information such as historical building distribution, approval information, and planning constraints, significantly improves the accuracy of rural housing change detection. Through multiple comparisons and analyses with approval information, it accurately identifies illegal housing types such as construction without approval, building larger structures with smaller approvals, building second structures with approved structures, and illegally occupying farmland, enabling classification and precise positioning. A complete closed-loop management mechanism has been established, from suspected violation discovery, mobile-side dispatch, on-site verification, to result confirmation, achieving digital management of the entire process. Through the cloud management platform's single-image display function, basic data, monitoring results, and disposal progress are visually displayed, providing management departments with an intuitive and convenient supervision tool, effectively improving the intelligent level and management efficiency of rural housing construction supervision.

[0015] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of an embodiment of a method for dynamic remote sensing monitoring of rural housing construction according to an embodiment of the present invention; Figure 2 A schematic diagram of an embodiment of a remote sensing dynamic monitoring system for rural housing construction according to an embodiment of the present invention; Figure 3 FIG. 1 is a schematic diagram of an embodiment of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] The terms "including," "having," and any variations thereof, as used in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or device.

[0020] To facilitate understanding of this embodiment, a rural house construction remote sensing dynamic monitoring method disclosed in an embodiment of the present invention is first introduced in detail. Figure 1 As shown, this method includes the following steps: 101. Gather data on basic homestead information surveys, real estate and land rights registration and certification, existing illegally occupied farmland for housing construction, and land and space planning data to obtain basic data on rural housing construction. It is understandable that the execution subject of the present invention can be a rural housing remote sensing dynamic monitoring system, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0021] Specifically, key fields are extracted from various types of original data and structured and integrated. When extracting the basic information survey data of homesteads, the spatial location coordinates, area boundary lines, ownership relations and approval time corresponding to each homestead are obtained, and standardized homestead information records are formed in a unified coding method, so as to clarify the geographical distribution status, boundary outlines and legal attributes of each homestead; four core indicators related to the house itself are extracted from the real estate and land rights confirmation registration and certification data, including the building area value, building height and number of floors, the type of building structure adopted and the functional classification of the house. By binding these house indicators with the homestead codes where they are located, house rights confirmation information records are generated to achieve integrated spatial mapping between houses; for the historical map data of illegal occupation of cultivated land for building houses, the recorded location coordinates of previous illegal buildings, the specific types of illegal buildings (such as construction without approval, building large with small approval, etc.), the building area involved in the illegal buildings and the historical disposal status (such as rectified, not handled, etc.) are extracted, thereby generating historical illegal building information records. The above-mentioned homestead information records, house title confirmation information records and historical illegal construction information records are spatially superimposed and attribute merged with the national land space planning data. The national land space planning data includes boundary information such as compliant construction areas, restricted construction areas and farmland protection red lines. By building a unified data fusion engine, the integration of various spatial data and attribute data in the logical coordinate system is completed to form basic data for rural housing construction.

[0022] 102. Based on the basic data of rural housing construction, change detection is performed on the remote sensing image of the target monitoring area to obtain the change detection results of newly built rural houses; Specifically, a remote sensing data source with sufficient spatial and temporal resolution is selected to acquire remote sensing images covering the target monitoring area. These images contain image elements such as building outlines, surface textures, and spatial structures. Quality correction is then performed on the original remote sensing images, including radiometric correction to eliminate the effects of atmospheric scattering and sun angle, spectral correction to calibrate sensor response errors, and noise suppression. This ensures the accuracy of the spectral characteristics and brightness information of the remote sensing images, resulting in quality-corrected remote sensing images. Geometric correction is then performed on the remote sensing images to eliminate geometric distortion caused by earth curvature, terrain undulation, or platform attitude. Spatial registration techniques are then used to align the remote sensing images with the rural housing infrastructure data using the same coordinate system, achieving alignment in two- or three-dimensional geographic space to produce spatially standardized remote sensing images. Based on the acquisition timestamp information of each remote sensing image, the spatially standardized remote sensing images are arranged in chronological order to form a temporally logical remote sensing image sequence of rural housing infrastructure. The basic data of rural housing construction is used as the reference standard for change detection. Through change detection algorithms (such as multi-temporal image difference analysis, change vector analysis, time series convolution analysis, etc.), new changes in building areas are identified in remote sensing image sequences, and historical buildings and compliant construction patches registered in the basic database are eliminated. The focus is on extracting building areas that are newly added or significantly expanded in the latest images compared with historical images, and obtaining the change detection results of newly built rural houses.

[0023] 103. Compare the results of the new rural housing change detection with the approval information in the rural housing basic data to identify suspected illegal housing areas; Specifically, the core information of all identified newly built rural houses is extracted from the newly built rural house change detection results, including the building's spatial location coordinates, actual building area, detected construction time, and preliminarily determined building type (such as residential, auxiliary building, or productive building). These elements are then aggregated into a newly built rural house feature information table using a standard field format. Using the location coordinate field in the newly built rural house feature information table as a spatial query condition, the corresponding homestead information records are retrieved from the rural housing basic data, focusing on searching for valid building approval information at that location, including whether there is a matching approval record, whether the approval time matches the construction time, and whether the ownership relationship is consistent. If no corresponding approval entry is retrieved or the construction time is earlier than the approval time, it is determined that the building may have been "built before approval" and the corresponding map is marked as a "suspected map of construction before approval." To identify two types of violations, namely, "approving small buildings for large construction" and "approving Class A for Class B," which deviate from approval requirements, the building area and center coordinates in the newly built rural housing feature information table are used as a benchmark. The approved area and location of the location in the query basic data are then compared. A numerical deviation analysis algorithm is used to calculate the area excess ratio and the location offset distance. When the actual area exceeds the approved area or the offset between the building center and the designated approved location exceeds a preset threshold (e.g., 5 meters or 10 meters), it is identified as a suspected case of "approving small buildings for large construction" or "approving Class A for Class B," and the corresponding area is categorized and marked. Furthermore, using the location of the newly built rural housing as input, the land use nature of the national land space planning layer in the rural housing basic data is queried, specifically focusing on highly restricted land types such as cultivated land protection redline areas and permanent basic farmland areas. Spatial overlay analysis is used to determine whether the building is located within the cultivated land protection area. If there is overlap or crossing, the area is identified as "illegal occupation of cultivated land," and the illegal land use type and area of ​​the "illegal occupation of cultivated land" area is recorded in the land use planning map. The identified areas of unapproved construction, large buildings built with small buildings approved, areas where Class A buildings were built with Class B buildings, and areas of illegally occupied farmland were summarized and classified, and their attribute information was combined to give them a unified numbering and structured annotation, and output as a dataset of suspected illegal housing construction areas.

[0024] 104. Send the suspected illegal building images to the inspectors through the mobile application for on-site verification and obtain the verification and confirmation results of the illegal building; Specifically, each suspected illegal building spot is standardized, and its core fields such as spatial location information, spot code, suspected violation type, area index and identification time are extracted. Based on the geographical distribution and number density of the spots and the inspector's territorial management area or work authority, an automated task allocation algorithm is used to generate corresponding verification task lists for all spots. The verification task list clearly marks the task number, spot coordinates, recommended inspection sequence, on-site key issues and completion time limit. The verification task list is pushed to the corresponding responsible person through a dedicated mobile application platform. The mobile application has a built-in verification task management interface that supports task query, navigation guidance, on-site photography, measurement entry and result submission. It ensures that every inspector can view the list of spots to be verified and the basic attributes of each spot on the platform, and directly link the spot location to the map navigation interface through the one-click positioning function, helping inspectors to reach the scene efficiently by the shortest path. Upon arrival at the site, the mobile app provides a standardized verification interface, guiding inspectors through the set process to perform measurement, investigation, and evidence collection tasks. This includes measuring building dimensions, photographing structures, describing usage, observing surrounding land use, and recording interviews with household owners. All data collected on-site is automatically compiled into on-site verification data records in the form of images and text. Inspectors are guided to make a preliminary assessment of the nature of the image patches based on what they see on-site and the information they collect, clarifying whether violations are indeed identified and, if so, which type of violation they fall under. Inspectors then complete the verification conclusion and additional notes through the mobile app, uploading all information to the cloud-based monitoring platform with one click, generating the results of the illegal building inspection and confirmation.

[0025] 105. In the preset cloud management platform, basic data on rural housing construction, suspected illegal housing construction areas and illegal housing construction verification and confirmation results are displayed visually.

[0026] Specifically, the cloud management platform completes the basic configuration of its layer architecture. Standardized rural housing data is imported into the system as a basemap layer. This basemap layer contains records of homestead land, housing title confirmation, land and space planning boundaries, and historical illegal construction records, ensuring the platform's spatial benchmark. Identified suspected illegal building sites are loaded into a separate monitoring layer. This layer displays all suspected building boundaries in vector form and binds key fields such as violation type, detection time, and changed area through site attributes. Simultaneously, the results of illegal building inspections are imported into a disposal layer. Within this layer, each confirmed illegal building site is labeled with the inspection conclusion, disposal status, disposal time, responsible person information, and inspection site photos. Different disposal stages, such as pending inspection, inspected, under rectification, and demolished, are color-coded. The cloud management platform's interface layout and interactive features are configured based on this display layer system. The interface design is modularized around user logic, including a layer switching control panel, a site attribute query window, a disposal progress statistics chart, and an evaluation results display area. In terms of interactive functionality, support for pop-up windows upon clicking on patches, linked attribute queries, timeline scrolling, patch filtering, and classification statistics is required to enhance user data manipulation and information perception efficiency. After the interface is officially deployed, patch distribution rendering is automatically performed based on the loaded display layer. By setting parameters such as patch color, border thickness, and transparency, a visual comparison relationship is established between the layers, ensuring that the rural housing base map, monitoring patches, and disposal patches are clearly distributed spatially and do not obscure each other. Simultaneously, the platform uses attribute data from the disposal layer in real time to automatically generate disposal progress statistics, including indicators such as the number of verified patches, the number of patches awaiting rectification, and the number of demolitions completed. These statistics are embedded in the display interface in the form of bar charts, pie charts, or dynamic charts. The verification conclusions of the verified patches are summarized and analyzed to generate reports on the distribution of violation types, regional problem clustering trends, and disposal effectiveness evaluations. These reports are integrated into the management interface through chart overlays, heat map displays, or list summaries, thus forming a visual display of the entire rural housing monitoring and disposal process.

[0027] In a specific embodiment, the process of executing step 101 may specifically include the following steps: Extract the spatial location coordinates, area boundaries, ownership relationship and approval time from the homestead basic information survey data to obtain homestead information records; Extract the building area, building height, building structure and use function from the real estate and land rights registration and certification data to obtain the house rights confirmation information record; Extract the location, type, area and disposal status of illegal buildings from the existing illegal construction data of farmland occupation to obtain historical illegal construction information records; The homestead information records, house title confirmation information records, historical illegal construction information records and land space planning data are aggregated to obtain the basic data of rural house construction.

[0028] Specifically, information describing the spatial and administrative attributes of homesteads is extracted from the basic homestead information survey data, obtaining spatial coordinates and calibrating the geographic location of each homestead in latitude and longitude. Area boundary information is also extracted, expressing the homestead boundaries as closed polygons. This data is formatted and encoded according to the surveying and mapping technical specifications issued by the National Bureau of Surveying and Mapping, ensuring that the boundary data has a unified vector format and spatial reference system. The ownership field corresponding to the homestead is also extracted, recording the identity of the homestead owner or user, including their household registration, ID number, and household head code. The approval time serves as a time stamp for the legality of homestead use, recording the issuance date of the approval document and the approving authority. Spatial location, area boundary, ownership information, and time stamp are combined to construct a standardized homestead information record, indexed by a unique homestead number. Information fields reflecting the actual construction status of the house are extracted from the real estate and land rights confirmation, registration, and certification data, and spatially associated with the corresponding homestead. Building area, a core field in housing registration, records the legal building footprint and total floor area, enabling area deviation calculations with remote sensing interpretations of building outlines. Building height is a key indicator for evaluating building scale. Maximum vertical height, extracted through manual measurement or elevation data, is used to assist in determining building category and over-limit behavior. Building structural information indicates the primary construction materials and load-bearing structure type, such as brick-concrete, steel, light steel, and wood, to support feature mapping for remote sensing image texture recognition models. Building use provides a basis for categorized supervision, clarifying whether a building is intended for owner-occupied housing, ancillary use, livestock breeding facility, or production purposes. These fields are combined according to field standards to form a housing title confirmation record, supplemented by auxiliary fields such as the title confirmation certificate number, title confirmation date, and titleholder information. This is then linked to homestead information records using an integrated real estate and land space number. Furthermore, historical illegal construction information is extracted from existing data on illegally occupied farmland for housing. The location coordinates of each historical illegal building patch are extracted and recorded as a center point or boundary surface, using a unified reference coordinate system. When extracting the illegal building type field, its behavioral characteristics are categorized and annotated, such as construction without approval, building a larger structure with a smaller one, building a second structure with approval for a Class A structure, or illegally occupying arable land. The illegal building area field records the actual floor space and building area of ​​the building corresponding to the patch, extracted using a plane calculation method or building outline recognition method, and retains the calculation method identifier. The disposal status field simultaneously annotates the processing progress of the illegal building patch, such as demolished, rectified, in the process of disposal, or unprocessed, forming a closed loop of historical problem data. Once the historical illegal building information record is formed, a spatial or attribute association is established with the homestead number. Homestead information records, housing title information records, and historical illegal building information records are used as three core data units and integrated with national land space planning data to form a basic data set for rural housing construction.The national land space planning data includes boundary information such as construction land planning areas, restricted development areas, permanent basic farmland protection areas, and ecological red line areas, and is loaded into the system in the form of GIS layers, and spatial overlay analysis is performed with the above three types of records under a unified coordinate reference.

[0029] In a specific embodiment, the process of executing step 102 may specifically include the following steps: Acquire remote sensing images of the target monitoring area and calibrate the remote sensing images to obtain quality-corrected remote sensing images; The quality-corrected remote sensing images are geometrically corrected and spatially registered to obtain spatially standardized remote sensing images, which are then sorted in chronological order according to their shooting time information to obtain a sequence of rural housing construction remote sensing images. Based on the basic data of rural house construction, change detection is performed on the remote sensing image sequence of rural house construction to obtain the change detection results of newly built rural houses.

[0030] Specifically, raw remote sensing images covering the target monitoring area are extracted from a high-resolution remote sensing image acquisition system. The image sources are optical remote sensing satellites, aerial photography platforms, or unmanned aerial vehicle multispectral imaging equipment. Quality correction is then performed on the raw remote sensing images. Because raw remote sensing images are subject to various interference factors, such as radiation distortion, atmospheric interference, illumination differences, and photosensitivity offset, preprocessing operations, including radiation correction, brightness normalization, atmospheric correction, and image enhancement, are performed. Radiation correction is calculated using sensor calibration parameters and solar altitude correction formulas to eliminate nonlinear sensor response issues. Atmospheric correction uses physics-based algorithms such as FLAASH or the QUAC module to subtract the effects of aerosol scattering. Image enhancement utilizes local contrast enhancement or edge sharpening based on the target scene to generate quality-corrected remote sensing images. Geometric correction and spatial registration are performed on the remote sensing images to form spatially standardized remote sensing images that can be spatially superimposed and regionally aligned. The geometric correction phase uses high-precision terrain data (such as digital elevation models (DEMs)) and control points (such as property benchmarks, road intersections, and bridge centers) to correct geometric distortion. Using a set of affine or polynomial transformation models, the images are reprojected into a standard map projection system and aligned to a unified geographic coordinate system (such as WGS 84). Spatial registration builds on this foundation by aligning remote sensing images captured at different times at the pixel level to ensure consistent spatial positions of the same building across images captured at different times. Registration methods include the SIFT algorithm based on feature point matching, a grayscale optimization algorithm based on mutual information, or a deep learning-based registration network. After registration, all remote sensing images have a unified geospatial reference, forming a spatially standardized remote sensing image collection. All spatially standardized images are chronologically organized based on the acquisition time tag of each remote sensing image, forming a rural housing construction remote sensing image sequence with a clear timeline structure. This rural housing construction remote sensing image sequence is annotated with metadata such as image acquisition time, source, resolution, coverage area, and quality level to construct a remote sensing time stack. Based on basic rural housing construction data, change detection is performed on remote sensing image sequences of rural housing construction to achieve dynamic identification of newly added rural housing targets. The change detection process introduces a spatial overlay mechanism and feature extraction model. By comparing the differences in surface targets between images of different phases, it is determined whether new construction has occurred. A building recognition model is applied to each remote sensing image to extract building areas. The building recognition model uses a deep segmentation structure based on convolutional neural networks, such as U-Net, Mask R-CNN, or Transformer fusion architecture. It uses pre-trained samples to identify buildings with typical geometric structures and spectral characteristics, and extracts element information such as their outline, area, boundary, and center position.A differential analysis is performed on building extraction results within the same spatial unit in the time series, comparing the presence of newly constructed areas or significant expansion of building outlines between the previous and current phases. If the differential area, absent in the previous phase but clearly discernible in the current phase, does not include existing building patterns or approval information recorded in the rural housing infrastructure data, it is preliminarily identified as a newly constructed farmhouse. To improve the robustness of change detection, a multidimensional threshold judgment mechanism is introduced, setting a minimum area change threshold to filter out non-substantial changes caused by image errors. Time span constraints are also incorporated to filter out misidentifications of seasonal temporary structures or farmland obstruction. The change detection module outputs a dataset of newly constructed farmhouse change detection results, including indicator fields such as spatial location coordinates, building area, time of change, structural morphology, and spectral properties.

[0031] Among them, before performing change detection on the remote sensing images of the target monitoring area based on the basic data of rural housing construction, it also includes: image quality assessment, temporal coverage continuity analysis and spatial coverage integrity calculation processing of the multi-source remote sensing images of the target monitoring area, and obtaining image evaluation parameters including image clarity index, temporal continuity and spatial coverage; establishing a multivariate optimization selection model for remote sensing images for rural housing construction monitoring based on the image evaluation parameters, setting the image clarity index as the quality optimization target, temporal continuity as the time correlation optimization target, and spatial coverage as the monitoring range optimization target, and obtaining a ternary optimization objective function; constrained optimization calculation and weight allocation processing are performed on the multi-source remote sensing images according to the ternary optimization objective function, and the optimal image combination scheme is solved by genetic algorithm to obtain a preferred monitoring image set; the preferred monitoring image set is divided into image data segments and redundant configuration processing according to the needs of rural housing construction monitoring, and the main and backup image data are allocated according to the importance of the monitoring area to obtain a distributed monitoring image data group; data integrity verification and quality consistency check processing are performed on the distributed monitoring image data group, and the reliability of the monitoring data is ensured through cross-validation and compensatory recombination to obtain a rural housing construction remote sensing image sequence.

[0032] In a specific embodiment, the execution step performs change detection on a remote sensing image sequence of rural housing construction based on the basic data of rural housing construction to obtain the change detection results of newly built rural housing. The process may specifically include the following steps: Feature extraction is performed on the remote sensing image sequence of rural housing construction to obtain house identification feature data including the location, area, shape and spectral characteristics of rural buildings; Based on the house recognition feature data, pixel-level difference calculation and target change analysis are performed on images at different times to obtain the detection results of the changed areas of new buildings, expansions and demolitions; Based on the basic data of rural housing construction, the change area detection results were spatially superimposed and attribute matching analyzed to screen out the change areas that did not match the existing building records, and obtain the change detection results of newly built rural houses.

[0033] Specifically, for a series of remote sensing images of rural housing, a deep learning algorithm is used to process each phase of the imagery, extracting building identification data including the building's spatial location, outline shape, actual area, and spectral reflectance. To improve recognition accuracy, a convolutional neural network model based on multi-scale feature fusion is employed, such as a U-Net variant with an encoder-decoder architecture or an improved Mask R-CNN architecture with a spatial attention mechanism. During the training phase, the convolutional neural network model is pre-trained with a large number of rural building samples and fully learns their texture structure, edge contours, and spectral characteristics in the remote sensing images, such as the reflectance bands of roof materials, image shadows caused by height projection, and the spatial pattern of building arrangement. After the model identifies buildings in each phase of remote sensing imagery, it generates a standardized set of building patches. Each patch contains the building's location coordinates (depicted as a center point or bounding polygon), its area (calculated from the pixel count within the bounding box), the building's geometry (such as aspect ratio, rectangularity, and edge complexity), and a multi-band spectral feature vector of the building's roof (using a combination of red, green, blue, and near-infrared bands). This information collectively constitutes the building identification data. Based on the time sequence, the house identification feature data is paired in pairs in a time-phased manner. Pixel-level difference calculation and building target change analysis are performed on remote sensing images at different times. Pixel-level difference calculation requires direct differentiation of the spectral reflectance, edge gradient, and texture structure of pixels at the same location after the two images are aligned. This identifies pixels that have changed from non-building areas to building areas or disappeared from building areas. Building target change analysis not only focuses on pixel-level changes but also analyzes the spatial state transition of the building at the overall level, including the appearance of new patches (indicating new buildings), the expansion of the original patch (indicating expansion), or the disappearance of the original patch (indicating demolition). For this type of target-level analysis, an IoU (Intersection over Union) matching algorithm is used to establish correspondences between building patches in the preceding and following time phases. When a patch is absent in the preceding time phase but appears in the following time phase, it is labeled "new." When the patch boundary significantly expands and maintains positional consistency between the two time phases, it is labeled "expansion." When a patch is completely missing in the following time phase and not replaced by another patch, it is considered "demolished." All identified new, expanded, and demolished building patches constitute the change area detection results, forming a set of change targets with clear temporal stratification and spatial boundaries. The change area detection results are then spatially overlaid and attribute-matched with basic rural housing data. This spatial overlay operation involves geometric intersection analysis of each change patch with homestead information records, housing title confirmation records, and historical illegal construction patch records to determine whether it falls within registered homesteads, has existing housing title confirmation records, or falls within the boundaries of historically known illegal construction.If a change patch is completely within an existing legal building patch and its shape and area do not exceed the set tolerance of the known patch boundaries, it is considered to be maintenance of an existing building and is removed. If the change patch overlaps with the legal homestead boundary but its area has significantly expanded beyond the originally approved value, and the building structure and functional parameters do not match the original records, it is further marked as an expansion-type newly added house. If the change patch is entirely located on unregistered homestead or non-construction land and there is no title confirmation record, no approval information, and no corresponding historical patch in the basic data, it is preliminarily determined to be an unapproved new rural house. During the attribute matching process, the construction time tag in the change patch (inferred from the time of remote sensing image capture) is compared with the homestead approval time for time series consistency verification. If the construction time is earlier than the approval time or the two do not match at all, it is used as an important identification factor for new rural houses. The national land space planning layer is also used to determine whether the change patch is located within the cultivated land protection red line, restricted construction area, or ecological control zone. If it falls within such a prohibited construction area and lacks legal land use procedures, it is marked as illegal construction involving the unauthorized occupation of cultivated land. After completing the spatial intersection analysis and attribute rule matching, the change patches that do not match the legal building records in the existing rural housing basic data are screened out from the original change area detection results, and all registered, approved or disposed of building targets are eliminated. The set of patches with new locations, sudden increases in area or contradictory attributes is retained to form the change detection results of newly built rural houses.

[0034] In a specific embodiment, the execution step performs spatial overlay and attribute matching analysis on the change area detection results based on the rural housing basic data, filters out the change areas that do not match the existing building records, and obtains the change detection results of the newly built rural houses. The process can specifically include the following steps: Determine the spatial information of the changed area including the position coordinates, area range and geometric shape according to the changed area detection result; The spatial information of the changed areas is spatially overlaid with the homestead information records in the rural housing construction basic data to identify areas with suspected illegal location changes; Based on the suspected illegal location change areas, the property rights confirmation information records and historical illegal construction information records in the rural housing basic data are matched and retrieved to obtain the areas where no building changes are recorded; Based on the areas where no building changes were recorded, the types of construction activities were identified and the scale was estimated to obtain the change detection results of newly built rural houses.

[0035] Specifically, geometric analysis is performed on newly added, expanded, or rebuilt buildings identified in the change area detection results to extract the core spatial parameters of each change patch, primarily including location coordinates, area, and geometric shape information. Location coordinates are represented by extracting the geometric center point of the patch polygon or constructing a bounding box. Area is accumulated based on the pixel area within the patch boundary and converted to actual area using the spatial resolution of the remote sensing imagery to determine the footprint and projected area of ​​each patch. Geometric shape information involves extracting metrics such as boundary structure complexity, outline aspect ratio, and shape regularity. Through this process, the change area detection results are converted into a set of structured spatial information about the change areas. This spatial information is then spatially overlaid with homestead information records from the rural housing infrastructure data to determine whether each change falls within the approved construction area. Homestead information records are stored as polygons, with their boundaries corresponding to the legally approved scope of the homestead. During the spatial overlay analysis, spatial operations such as face intersection and point-in-polygon determination are used to geometrically compare the changed areas with the homestead boundaries to determine whether they are completely contained within a specific homestead or whether they extend beyond the boundaries. If a changed area is located outside the homestead area, or if it is within the homestead boundary but the overlap ratio falls below a set threshold (e.g., 60%), it is preliminarily identified as a suspected illegal location change. Attribute matching searches are performed on suspected illegal location change areas against housing title confirmation records and historical illegal construction records in the rural housing construction basic data to determine whether the changed areas have been registered or previously included in illegal locations. Attribute matching searches are primarily based on a comprehensive assessment of the location's spatial number, spatial location overlap, building area proximity, and corresponding ownership codes. In particular, if the center point or primary boundary of a changed area lies within a confirmed housing location, and if the area and shape differ within reasonable limits from the original registration information, it is considered an extension or update of the registered location and does not require duplicate recording. For areas where no corresponding records can be found in the property rights database and which do not belong to the historical illegal construction patterns, they are marked as areas with no recorded building changes. For areas with no recorded building changes, the type of construction activity is intelligently identified based on the shape characteristics, area indicators, and time nodes of the patterns, and the construction scale is estimated. The identification of the type of construction activity is based on the characteristic parameters of the pattern changes and the historical sample model. If the pattern area is small, the shape is simple, and the change cycle is short, it is judged to be a simple temporary building or ancillary building; if the pattern structure is regular, the area is within the permitted area of ​​the homestead, and the change trajectory conforms to the construction cycle, it is judged to be a new standard residential building; if the pattern boundary is complex, the area significantly exceeds the homestead area, or it exhibits non-residential functional characteristics (such as abnormal roof reflection, location near farmland), it is an illegal industrial construction, a farm, or a temporary processing point.Based on the initial determination of the type of construction activity, the building's area, estimated number of floors, and building volume are measured. Area is calculated directly from the pixel area at the edge of the image patch, while height is indirectly calculated by combining image shadow length and solar altitude. Building volume is calculated by multiplying the area and estimated height for classification management and graded disposal. The newly constructed patch data set, generated after spatial identification, attribute elimination, type determination, and scale measurement, is aggregated into the results of newly constructed rural housing change detection. Each record is clearly labeled with the location coordinates, change time, area indicator, type classification, compliance status, and risk level.

[0036] In a specific embodiment, the process of executing step 103 may specifically include the following steps: Extract building location coordinates, building area, construction time and building type from the newly built rural house change detection results and construct a newly built rural house element information table; Based on the location coordinates in the newly built rural housing feature information table, spatial query and approval status search are performed on the homestead information records in the rural housing basic data to identify suspected areas of construction without approval. The deviation analysis is conducted between the building area and location information in the newly built rural housing element information table and the corresponding approved area and approved location in the rural housing basic data, and suspected areas of approval for small-scale construction and approval for large-scale construction are identified; Based on the location coordinates in the new rural housing feature information table, the land use nature query and compliance judgment are carried out on the national land space planning data in the rural housing basic data, and the building locations located in the cultivated land protection area are identified. Then, the suspected areas of construction without approval, the suspected areas of building large with approval for small, the suspected areas of building B with approval for Class A, and the areas of buildings occupying cultivated land indiscriminately are classified and summarized to obtain the suspected areas of illegal construction.

[0037] Specifically, key fields are extracted from each patch included in the newly built rural housing change detection results, including building location coordinates, building area, construction time, and building type. Building location coordinates are obtained by extracting the patch's geometric center point or calculating the minimum enclosing rectangle (MBR) of its outline and projecting it into the system's standard coordinate system. Building area is calculated by converting the number of pixels and resolution of the patch in the remote sensing image to obtain the actual floor space, with a quantitative error control boundary. Construction time is archived based on the remote sensing image capture time, representing the time when the building first appears in the remote sensing sequence. Building type is determined as residential, ancillary, or other building types based on the geometric morphology, spectral characteristics, and contextual information of the change patch, combined with the results of a deep learning recognition model. This information is integrated into a standard field format to construct a newly built rural housing feature information table. Using the building location coordinates in the newly built rural housing feature information table as search criteria, spatial queries and approval status searches are performed on homestead information records in the rural housing basic data to identify objects with construction but no approval records. The spatial query process uses a "point within polygon" or "polygon intersection" analysis method to align the location of newly constructed plots with the boundaries of homesteads. If a plot is completely outside a parcel of homestead land or its location has no corresponding numbered entry in the homestead database, it is preliminarily determined that the building was not constructed within the permitted scope. If a plot falls within the boundaries of a legal homestead land, but no approval information consistent with the construction time can be found in the approval records attached to the parcel of homestead land, or the approved building use is inconsistent, it is considered unlicensed construction, i.e., "construction before approval." Such plots are logically categorized as suspected "pre-approval" plots, and a field is added to the information table to indicate their source as "missing approval record" or "approval time sequence discrepancy." Based on the identification of pre-approval plots, a quantitative deviation analysis is conducted based on the building area and location in the newly constructed rural housing element information table, compared with the approved area and location of the corresponding homestead land in the rural housing basic data, to identify two types of over-limit construction: "approving small and building large" and "approving A and building B." Identifying "approved small, built larger" construction relies on calculating area deviation. This involves comparing the actual area of ​​a newly constructed plot with the approved area registered in the approval document. A threshold for area deviation (e.g., 15%-20%) is set as the basis for judgment. If the plot area exceeds the approved area by a certain amount or more, it is considered oversized construction and flagged as a suspected "approved small, built larger" plot. Identifying "approved A, built B" construction focuses on determining positional deviation. The spatial offset between the center coordinates of the newly constructed plot and the planned construction location in the approval record is calculated using Euclidean distance measurement or polygon overlap analysis. If the deviation exceeds a set tolerance (e.g., 10 meters) and the overlap of building outlines falls below a set standard (e.g., below 40%), the construction location is deemed inconsistent with the approved location, constituting "approved A, built B" construction, and the plot is individually flagged as a suspected "approved A, built B" construction plot. Area and positional deviations can be determined simultaneously. When both exceed the limit, multiple violations should be prioritized.The coordinates of the building locations in the newly constructed rural housing feature information table were matched with the national land space planning data in the rural housing basic data to identify buildings with illegal land use types. Spatial overlay analysis was performed on the building locations and land use units in the planning layer (such as urban construction land, cultivated land, gardens, woodlands, and water bodies) to determine whether the buildings were located within non-construction areas. In particular, the locations were examined for nationally restricted construction areas, such as cultivated land protection zones, permanent basic farmland control lines, and ecological protection red lines. If the building's spatial location fell completely or partially within these red lines, regardless of the existence of approval documents, it was considered a land use violation and classified as an illegal occupation of cultivated land. Information such as the illegal land use type, illegal land area, and percentage of the overlay range was also recorded. Suspected areas of unapproved construction, small approvals for larger structures, and approved A for B, as well as the locations of buildings illegally occupying cultivated land, were categorized and summarized to form a dataset of suspected illegal housing areas.

[0038] In a specific embodiment, the process of executing step 104 may specifically include the following steps: Extract location information and assign tasks to suspected illegal building sites to obtain a verification task list; Push the verification task list to the corresponding inspectors through the mobile application, and the mobile application provides a mobile verification work interface; Based on the mobile terminal verification work interface, the inspection personnel are guided to the suspected illegal construction site to conduct on-site measurement and situation investigation, and obtain on-site verification data records; According to the on-site verification data records, the verification conclusion is determined and the results are uploaded through the mobile application to obtain the verification confirmation results of illegal building construction.

[0039] Specifically, the location information of suspected illegal building sites is extracted and a task list is generated. The location information of the site includes the latitude and longitude values ​​of the center coordinate point, the vector description of the boundary range, and the administrative division number to which the site belongs. Based on the extracted site location, the task weight is calculated based on the type of violation identified by the site (such as construction without approval, large construction with small approval, illegal occupation of arable land, etc.), the site area, the time of discovery, the priority level, the inspection history status, and other information. By setting task scheduling rules, the sites are automatically divided according to the responsibility area, the functional scope of the inspectors, and the available human resources, and a structured inspection task list is generated. Each task in the inspection task list includes auxiliary information such as the unique site number, the type of inspection object, on-site operation suggestions, the estimated time and the recommended inspection time period. The inspection task list is sent to the mobile application of the corresponding inspector in the form of a digital task package. After receiving the task, the mobile application provides a dedicated mobile verification work interface, which integrates the task list module, the site map navigation module, the task details module, and the data collection module. In the map navigation module, the application automatically calls the coordinates of the center point of the map and links the map service interface to achieve accurate marking and path navigation of the target map, helping inspectors to quickly reach the scene; the task details module displays the violation type of the current map, the basis for system judgment, spatial location, approval information matching status and historical verification records; the data collection module provides a variety of data input methods such as photo shooting, voice recording, text notes, and form filling. When the inspectors arrive at the site of the suspected illegal building under guidance, they complete the field measurement and situation investigation according to the standard operating procedures provided by the mobile terminal verification work interface. The measurement content includes the length and width of the actual building boundary, building height estimation, structural material records, on-site construction status, surrounding land use, etc. The investigation content includes whether the building is occupied, whether there is a construction permit posted, whether the statements of the on-site management personnel or household owners are consistent with the system approval records, and the verification of information reported by the public. All on-site inspection data is directly filled in through the mobile terminal and is structured in the interface. For example, on-site photos are bound to the shooting time and map number, voice instructions are automatically transcribed into text copies and placed in the remarks column, size measurements should be associated with map distance tracks or manually input fields, and material structures are selected with the assistance of image labels, etc., to improve the accuracy and convenience of inspection information collection. After the inspection is completed, the inspectors complete the inspection conclusion judgment in the mobile terminal application based on the collected data. The process is set as a standardized judgment process, including "determining whether it is an actual building", "determining whether it is consistent with the system map", "determining whether it is an illegal construction", and "determining the type of violation". Each step is equipped with an option judgment and a text description box to support the conclusion formed by combining subjective judgment with objective evidence.After the integrity check of the verification conclusion, the user is guided to upload the data with one click to form the verification and confirmation results of illegal building construction. The verification and confirmation results of illegal building construction are logically bound to the original map data and pushed to the cloud-based supervision platform database. At the same time, the task status update module is triggered, and the map status is switched from "pending verification" to "verified" and multiple fields such as verification results, verification time, verification personnel, on-site photo summary, positioning trajectory, etc. are marked.

[0040] In a specific embodiment, the process of executing step 105 may specifically include the following steps: In the preset cloud management platform, the basic data of rural housing construction is set as the base map layer, the suspected illegal housing construction spots are set as the monitoring layer, and the illegal housing construction verification and confirmation results are set as the disposal layer to obtain the display layer; Based on the display layer, the interface layout design and interactive function configuration are carried out in the cloud management platform to obtain the management interface, and the management interface is rendered with map distribution, the disposal progress statistics and evaluation results are displayed to obtain a visual display result.

[0041] Specifically, various remote sensing analysis and management results are classified into layers, and the layer roles are set according to the data usage and management logic. The basic data of rural housing construction is loaded as the background geographic information for building the display interface. The base map layer contains information such as the boundaries of homesteads, the outlines of confirmed buildings, historical records of illegal construction, the red lines of national land space planning, and the boundaries of land use classification. The base map layer is loaded in the form of a fusion of vector layers and raster base maps to ensure clear graphic outlines, excellent rendering performance, and support for operations such as zooming and querying. The suspected illegal housing construction spots identified in the remote sensing change detection and comparison analysis results, such as construction without approval, building large buildings with small approvals, building B buildings with approval A, and illegal occupation of cultivated land, are loaded as monitoring layers. The monitoring layer is presented in the form of surface spots, including the spatial range, identification time, initial judgment type, change area, judgment threshold, and spot code of each spot. The verification conclusion data formed after the mobile terminal inspection and confirmation is loaded into the disposal layer. The disposal layer records the spots that have been verified and is accompanied by multiple attribute fields such as on-site photos, verification conclusions, verification personnel, verification time, processing suggestions and disposal progress. The status of the spots in the layer is distinguished by different colors according to the verification progress, such as "pending verification" spots are yellow, "confirmed violations" spots are red, "rectified" spots are blue, "demolished" spots are green, etc., to achieve graphical marking of the disposal situation. The base map layer, monitoring layer and disposal layer are loaded into the same spatial projection system, and the layer attribute structure, field naming and coordinate base are unified to form a display layer system. Based on the display layer, the interface layout design and interactive function configuration are carried out in the cloud management platform to build a management interface for daily supervision, verification scheduling and decision analysis. The interface layout takes the "map main view" as the core component, and cooperates with the layer control area, attribute information pop-up area, statistical chart area and tool operation bar to achieve functional coordination. The map main view presents the spatial distribution status of various map spots and supports layer overlay, map spot selection and dynamic rendering. The layer control area allows users to switch layer display status, adjust layer transparency and set map spot highlighting rules as needed. The attribute information pop-up area displays attribute fields when the user clicks on a map spot, including map spot source, identification parameters, inspection records and disposal status, etc. The statistical chart area displays visual indicators such as the number of maps divided by region, distribution of violation types, verification completion ratio, rectification completion progress, etc. The tool operation bar provides auxiliary functions such as map spot filtering, timeline browsing, map spot export, batch marking and task issuance. The functions of rendering the distribution of spots, statistics on the handling progress and displaying the evaluation results of various display elements in the management interface are realized. The spot distribution rendering link sets the visual expression rules of different spots on the map, such as setting the border color, fill transparency, spot boundary style or dynamic flashing frequency according to the spot status, so as to improve the spot recognition and sense of urgency; at the same time, it supports hierarchical rendering, that is, setting the layered rendering logic according to parameters such as violation level, area size or discovery time, so as to make important spots more prominent.The disposal progress statistics link automatically summarizes the field data in the disposal layer, and classifies the statistics by patch status to show the total number of inspections, the number of violation patches, the number of resolved patches, the distribution of various types of violations, and regional distribution trends. The statistical results are dynamically rendered in the chart area of ​​the interface in the form of pie charts, bar charts, line charts, etc., and support the linkage operation of charts and layers. Users can click on the chart to highlight the corresponding patch. The evaluation result display link conducts a comprehensive analysis based on the patch verification confirmation results and the disposal effectiveness data, displaying indicators such as the violation rate, rectification rate, and recurrence rate of each township, and forming a disposal effect evaluation index. It also supports exporting to reports, linking to early warning modules, or generating heat maps.

[0042] In this embodiment, the process of performing visualization on a preset cloud management platform further includes: performing spatial cluster analysis and monitoring frequency statistics on the geographic location distribution of suspected illegal building spots to identify non-periodic spatial distribution trajectory characteristics of rural building violations and obtain spatial activity trajectory data of illegal building violations; constructing an adaptive spatial repetitive monitoring learning model based on the illegal building spatial activity trajectory data, establishing a spatial location-related monitoring parameter adjustment mechanism by analyzing the occurrence patterns of illegal building in different geographic locations, and obtaining a full-coverage spatial repetitive learning control law; adaptively adjusting the monitoring focus and monitoring frequency of different geographic areas based on the full-coverage spatial repetitive learning control law, increasing the monitoring density and update frequency for high-incidence areas of violations, and obtaining an adaptive spatial monitoring control scheme; applying the adaptive spatial monitoring control scheme to the visualization display update process of the cloud management platform, accurately correcting it through a geographic location-related seasonal and regional monitoring uncertainty compensation algorithm to obtain high-precision rural building violation tracking display parameters; and performing real-time adaptive updating and precise positioning of the visualization interface based on the high-precision rural building violation tracking display parameters to achieve high-precision spatial tracking and display of non-periodic rural building violation activities and obtain an adaptively optimized visualization display result.

[0043] The above describes the rural house construction remote sensing dynamic monitoring method according to the embodiment of the present invention. The following describes the rural house construction remote sensing dynamic monitoring system according to the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a remote sensing dynamic monitoring system for rural housing construction includes: The data aggregation module 201 is used to aggregate the basic information survey data of homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for building, and the land space planning data to obtain basic data on rural housing construction; The change detection module 202 is used to perform change detection on the remote sensing image of the target monitoring area based on the basic data of rural housing construction to obtain the change detection results of the newly built rural houses; Comparison module 203, used to compare the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots; On-site verification module 204 is used to send suspected illegal building images to inspectors through mobile applications for on-site verification and obtain illegal building verification confirmation results; The visualization display module 205 is used to visualize the basic data of rural housing construction, suspected illegal housing construction spots and illegal housing construction verification and confirmation results in a preset cloud management platform.

[0044] Through the collaborative cooperation of the above-mentioned components, the present invention breaks the traditional information island state by uniformly summarizing and processing the basic information survey data of homesteads, the data of the registration and certification of the integrated real estate rights, the data of the existing illegally occupied farmland for building houses and the land space planning data, and establishes a complete rural housing construction basic data base. The present invention performs change detection on remote sensing images based on the basic data of rural housing construction, and can conduct comprehensive analysis in combination with multi-dimensional information such as the distribution of historical buildings, approval information, and planning constraints, significantly improving the accuracy of rural housing construction change detection and effectively reducing false positives and omissions. Through multiple comparison and analysis with approval information, the present invention can accurately identify the four main types of illegal building such as building without approval, building large with small approval, building B with approval of A, and illegal occupation of farmland, realizes the classification identification and precise positioning of illegal behaviors, and improves the pertinence and effectiveness of supervision. The present invention constructs a complete closed-loop management mechanism from suspected illegal discovery, mobile terminal issuance, on-site verification to result confirmation, realizes digital management of the entire process of discovery, verification, disposal, and tracking, and effectively improves supervision efficiency and timeliness of disposal. Through the one-picture display function of the cloud management platform, the present invention uniformly visualizes basic data, monitoring results, disposal progress and other information, provides an intuitive and convenient supervision tool for management departments, and effectively improves the scientific nature of supervision decisions and management efficiency.

[0045] above Figure 2 The remote sensing dynamic monitoring system for rural housing construction in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The computer equipment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0046] Figure 3This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. The computer device 300 may vary significantly due to different configurations or performance. It may include one or more processors (central processing units, CPUs) 310 (for example, one or more processors), memory 320, and one or more storage media 330 (for example, one or more mass storage devices) storing application programs 333 or data 332. The memory 320 and storage medium 330 may be either transient or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations on the computer device 300. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, executing the series of instruction operations in the storage medium 330 on the computer device 300 to implement the steps of the above-described method for dynamic remote sensing monitoring of rural housing construction.

[0047] The computer device 300 may further include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The illustrated computer device structure does not constitute a limitation on the computer device provided by the present invention, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0048] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0050] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote sensing dynamic monitoring method for rural housing construction, characterized in that: include: The basic data on rural housing construction is obtained by summarizing the survey data on basic information of homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for housing construction, and the land space planning data; Based on the rural housing construction basic data, change detection is performed on the remote sensing image of the target monitoring area to obtain the change detection results of the newly built rural houses; Comparing the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots; The suspected illegal building images are sent to the inspectors via the mobile application for on-site verification, and the illegal building verification confirmation results are obtained; In the preset cloud management platform, the basic data of rural house construction, the suspected illegal house construction spots and the illegal house construction verification and confirmation results are visualized, wherein the geographical location distribution of the suspected illegal house construction spots is subjected to spatial clustering analysis and monitoring frequency statistics to obtain the spatial activity trajectory data of illegal house construction; based on the illegal house construction spatial activity trajectory data, the occurrence pattern of illegal house construction in different geographical locations is analyzed to establish a spatial location-related monitoring parameter adjustment mechanism to obtain a full-coverage spatial repeated learning control law; according to the full-coverage spatial repeated learning control law, the monitoring focus and monitoring frequency of different geographical areas are adaptively adjusted to obtain an adaptive spatial monitoring and control scheme; the adaptive spatial monitoring and control scheme is applied to the visualization display update process of the cloud management platform to obtain an adaptively optimized visualization display result.

2. The remote sensing dynamic monitoring method for rural housing construction according to claim 1 is characterized in that: The basic data on rural housing construction is obtained by summarizing the basic information survey data on homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for housing construction, and the land space planning data, including: Extract the spatial location coordinates, area boundaries, ownership relationship and approval time from the homestead basic information survey data to obtain homestead information records; Extract the building area, building height, building structure and use function from the real estate and land rights registration and certification data to obtain the house rights confirmation information record; Extract the location, type, area and disposal status of illegal buildings from the existing illegal construction data of farmland occupation to obtain historical illegal construction information records; The homestead information records, the house title confirmation information records, the historical illegal construction information records and the national land space planning data are aggregated to obtain basic data on rural house construction.

3. The remote sensing dynamic monitoring method for rural housing construction according to claim 1 is characterized in that: The change detection of the remote sensing image of the target monitoring area based on the rural housing construction basic data is performed to obtain the change detection result of the newly built rural houses, including: Acquiring a remote sensing image of the target monitoring area and correcting the remote sensing image to obtain a quality-corrected remote sensing image; The remote sensing images after quality correction are geometrically corrected and spatially registered to obtain spatially standardized remote sensing images, and the remote sensing images are arranged in time sequence according to shooting time information of the spatially standardized remote sensing images to obtain a sequence of rural housing construction remote sensing images; Based on the rural housing construction basic data, change detection is performed on the rural housing construction remote sensing image sequence to obtain a change detection result of the newly built rural houses.

4. The remote sensing dynamic monitoring method for rural housing construction according to claim 3 is characterized in that: The performing change detection on the rural housing construction remote sensing image sequence based on the rural housing construction basic data to obtain the newly built rural housing change detection result includes: Extracting features from the rural house construction remote sensing image sequence to obtain house identification feature data including rural building location, area, shape and spectral features; Based on the house recognition feature data, pixel-level difference calculation and target change analysis are performed on images at different times to obtain detection results of changed areas such as new additions, expansions, and demolitions of buildings; The change area detection results are spatially superimposed and attribute matched according to the rural housing construction basic data, and the change areas that do not match the existing building records are screened out to obtain the change detection results of the newly built rural houses.

5. The remote sensing dynamic monitoring method for rural housing construction according to claim 4 is characterized in that: The change area detection results are spatially superimposed and attribute matched according to the rural housing construction basic data to screen out the change areas that do not match the existing building records, and obtain the new rural housing change detection results, including: Determine the changed area spatial information including position coordinates, area range and geometric shape according to the changed area detection result; Perform spatial overlay analysis on the spatial information of the changed area and the homestead information records in the rural housing construction basic data to identify areas with suspected illegal location changes; Perform attribute matching retrieval on the house ownership confirmation information records and historical illegal construction information records in the rural house construction basic data according to the suspected illegal location change area, and obtain the unrecorded building change area; Based on the unrecorded building change area, the construction activity type is identified and the scale is estimated to obtain the new rural house change detection result.

6. The remote sensing dynamic monitoring method for rural housing construction according to claim 5 is characterized in that: The method of comparing the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots includes: Extract the building location coordinates, building area, construction time and building type from the newly built farmhouse change detection results and construct a newly built farmhouse element information table; Perform spatial query and approval status search on homestead information records in the rural housing basic data based on the location coordinates in the newly built rural housing element information table to identify suspected areas of construction without approval; Perform deviation analysis on the building area and location information in the newly built rural housing element information table and the corresponding approved area and approved location in the rural housing basic data to identify suspected areas where small buildings are approved for construction and large buildings are approved for construction; Based on the location coordinates in the newly built rural housing element information table, the land use nature query and compliance judgment are performed on the national land space planning data in the rural housing basic data to identify the building locations within the cultivated land protection area, and then the suspected areas of construction without approval, the suspected areas of building large with small approval and building B with approval A, and the locations of buildings occupying cultivated land indiscriminately are classified and summarized to obtain areas of suspected illegal construction.

7. The remote sensing dynamic monitoring method for rural housing construction according to claim 1, characterized in that: The suspected illegal building images are sent to inspectors via mobile applications for on-site verification, and the illegal building verification confirmation results are obtained, including: Extracting location information and assigning tasks to the suspected illegal building spots to obtain a verification task list; Push the verification task list to the corresponding inspectors via the mobile application, and the mobile application provides a mobile verification work interface; Based on the mobile terminal verification work interface, the inspection personnel are guided to the suspected illegal building site to conduct on-site measurement and situation investigation, and obtain on-site verification data records; According to the on-site verification data records, the verification conclusion is determined and the results are uploaded through the mobile application to obtain the verification confirmation results of the illegal building.

8. The remote sensing dynamic monitoring method for rural housing construction according to claim 1 is characterized in that: The basic data of rural housing construction, the suspected illegal housing construction spots and the illegal housing construction verification and confirmation results are visually displayed in the preset cloud management platform, including: In a preset cloud management platform, the rural housing construction basic data is set as a base map layer, the suspected illegal housing construction spots are set as a monitoring layer, and the illegal housing construction verification and confirmation results are set as a disposal layer to obtain a display layer; Based on the display layer, interface layout design and interactive function configuration are performed in the cloud management platform to obtain a management interface, and the management interface is rendered with map distribution, and processing progress statistics and evaluation results are displayed to obtain a visual display result.

9. A remote sensing dynamic monitoring system for rural housing construction, characterized in that: Used to execute the rural house construction remote sensing dynamic monitoring method according to any one of claims 1 to 8, the rural house construction remote sensing dynamic monitoring system comprises: The data aggregation module is used to aggregate the basic information survey data of homesteads, the data on the registration and issuance of certificates for integrated real estate and land rights, the data on the existing illegally occupied farmland for housing construction, and the land space planning data to obtain the basic data on rural housing construction; A change detection module is used to perform change detection on the remote sensing image of the target monitoring area based on the rural housing construction basic data to obtain the change detection results of the newly built rural houses; A comparison module is used to compare the newly built rural housing change detection results with the approval information in the rural housing basic data to determine suspected illegal housing spots; The on-site verification module is used to send the suspected illegal building map to the inspection personnel through the mobile application for on-site verification and obtain the illegal building verification confirmation result; A visualization display module is used to visualize the basic data on rural house construction, the suspected illegal house construction spots and the illegal house construction verification and confirmation results in a preset cloud management platform, wherein spatial clustering analysis and monitoring frequency statistics are performed on the geographical location distribution of the suspected illegal house construction spots to obtain spatial activity trajectory data of illegal house construction; based on the illegal house construction spatial activity trajectory data, a spatial location-related monitoring parameter adjustment mechanism is established to obtain a full-coverage spatial repeated learning control law; according to the full-coverage spatial repeated learning control law, the monitoring focus and monitoring frequency of different geographical areas are adaptively adjusted to obtain an adaptive spatial monitoring and control scheme; the adaptive spatial monitoring and control scheme is applied to the visualization display update process of the cloud management platform to obtain an adaptively optimized visualization display result.

10. A computer device, characterized in that: The computer device includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the computer device to execute the rural house construction remote sensing dynamic monitoring method according to any one of claims 1 to 8.

Images