A data processing method and system applied to territorial space planning

Abstract

This invention relates to the field of data processing technology, and more particularly to a data processing method and system applied to land spatial planning. The method includes the following steps: acquiring regional images of the land planning area to obtain land planning area images, and generating dense point cloud data based on these images; constructing an overall model of the planning area using the generated dense point cloud data; identifying densely built areas in the overall model, pre-setting dense building nodes, and constructing a node network; classifying the nodes based on the land planning area images to obtain node classification data; performing restricted development area analysis on the node classification data based on the overall model and regional images, and using the node network to perform regional connectivity analysis; and performing land planning based on the restricted development areas and connectivity data to obtain a land spatial planning scheme. This invention uses data processing to achieve land planning, thereby increasing the rationality of planning and improving the efficiency of planning analysis.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing method and system for land spatial planning. Background Technology

[0002] Traditional land spatial planning methods rely primarily on two-dimensional maps and human experience, making it difficult to accurately assess complex three-dimensional spatial relationships and dynamic changes, resulting in a lack of scientific basis for planning schemes. Currently, the field of land spatial planning has applied some advanced technologies, such as Geographic Information Systems (GIS), remote sensing, 3D modeling, and various spatial analysis methods. GIS technology is mainly used for the management, analysis, and visualization of spatial data. Remote sensing technology can provide high-resolution imagery data for land use classification, vegetation cover monitoring, and other purposes. GIS technology has improved the efficiency and accuracy of planning to some extent. However, current technologies have some shortcomings: they lack the ability to analyze regional dynamic changes and cannot reflect and predict regional development trends in real time; regional 3D modeling and ecological analysis are insufficient, failing to fully consider the complex relationships between buildings, land use, and ecosystems; and there is a lack of refined analysis of densely built-up areas and nodal networks, leading to discrepancies between planning results and reality. Summary of the Invention

[0003] Therefore, it is necessary for the present invention to provide a data processing method and system for land spatial planning, in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a data processing method for land spatial planning includes the following steps:

[0005] Step S1: Acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain a 3D model of the planning area and a 3D model of the regional buildings; integrate the 3D model of the planning area and the 3D model of the regional buildings to obtain an overall model of the planning area.

[0006] Step S2: Identify densely built areas in the overall model of the planning area to obtain densely built areas; pre-set dense building nodes in the overall model of the planning area based on the densely built areas to obtain dense building nodes; construct a node network in the overall model of the planning area based on the dense building nodes to obtain a dense building network; classify the dense building nodes based on the land planning area image to obtain node classification data.

[0007] Step S3: Based on the overall model of the planning area and the land planning area image, perform restricted development area analysis on the node classification data to obtain the planned restricted development area; perform regional connectivity analysis on the overall model of the planning area based on the dense building network in the area to obtain the connectivity data of the planning area; and perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

[0008] This invention constructs a 3D model of the planning area and buildings by acquiring regional images and generating dense point cloud data, and finally integrates them into a unified overall model. The benefit of this step is that it elevates traditional 2D planning to a 3D level, enabling a more intuitive and detailed representation of landforms and spatial relationships, providing more accurate foundational data for subsequent analysis and planning. Compared to planning solely based on 2D maps, the 3D model more realistically reflects information such as surface undulations and building heights, avoiding planning deviations caused by missing information, thereby improving the scientific rigor and accuracy of the planning. Based on the overall model, densely built-up areas are identified, nodes are pre-defined, and networks are constructed. This allows planning to move beyond simply focusing on land parcels and delve into the building level, analyzing building density, distribution patterns, and interconnections. By constructing a node network, the urban spatial structure can be better understood, key nodes and important connection paths can be identified, providing more refined guidance for transportation planning and infrastructure construction, and laying the foundation for subsequent analysis of restricted development areas and connectivity analysis, ultimately improving the rationality and effectiveness of the planning. Restricted development area analysis and regional connectivity analysis are then conducted to ultimately generate a national land spatial planning scheme. By combining the overall model, node classification data, and regional images, factors such as topography, ecological environment, and building distribution can be considered more comprehensively. This allows for the scientific delineation of restricted development areas and the assessment of regional connectivity based on the node network, ensuring the rationality and feasibility of the planning scheme. This comprehensive analysis method effectively avoids the limitations of planning dominated by a single factor, enhancing the overall integrity and coordination of the plan.

[0009] Preferably, the present invention also provides a data processing system for land spatial planning, used to execute the data processing method for land spatial planning as described above, the data processing system for land spatial planning comprising:

[0010] The planning area model construction module is used to acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain the planning area 3D model and regional building 3D model; and integrate the planning area 3D model and regional building 3D model to obtain the overall planning area model.

[0011] The regional node setting module is used to identify densely built areas in the overall model of the planning area, thereby obtaining densely built areas; based on the densely built areas, it presets densely built nodes in the overall model of the planning area, thereby obtaining densely built nodes; based on the densely built nodes, it constructs a node network in the overall model of the planning area, thereby obtaining a densely built network; and based on the land planning area image, it classifies the densely built nodes, thereby obtaining node classification data.

[0012] The land spatial planning module is used to perform restricted development area analysis on node classification data based on the overall model of the planning area and the land planning area image to obtain the planned restricted development area; to perform regional connectivity analysis on the overall model of the planning area based on the dense building network of the area to obtain the connectivity data of the planning area; and to perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

[0013] In summary, this invention provides a data processing method and system for land spatial planning. The system comprises a planning area model construction module, an area node setting module, and a land spatial planning module. It can implement any data processing method for land spatial planning as described in this invention. The system utilizes the combined operations of computer programs running on each module to achieve any data processing method applicable to land spatial planning. The internal structure of the system collaborates with each other, which greatly reduces repetitive work and manpower input, and provides a faster and more accurate and efficient data processing process for land spatial planning, thereby simplifying the operation flow of the data processing system for land spatial planning. Attached Figure Description

[0014] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0015] Figure 1 This is a flowchart illustrating the steps of a data processing method for land spatial planning according to the present invention.

[0016] Figure 2 for Figure 1 A detailed flowchart of step S2;

[0017] Figure 3 for Figure 2 A detailed flowchart of step S25.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0021] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] To achieve the above objectives, please refer to Figures 1 to 3 This invention provides a data processing method for land spatial planning, comprising the following steps:

[0023] Step S1: Acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain a 3D model of the planning area and a 3D model of the regional buildings; integrate the 3D model of the planning area and the 3D model of the regional buildings to obtain an overall model of the planning area.

[0024] Step S2: Identify densely built areas in the overall model of the planning area to obtain densely built areas; pre-set dense building nodes in the overall model of the planning area based on the densely built areas to obtain dense building nodes; construct a node network in the overall model of the planning area based on the dense building nodes to obtain a dense building network; classify the dense building nodes based on the land planning area image to obtain node classification data.

[0025] Step S3: Based on the overall model of the planning area and the land planning area image, perform restricted development area analysis on the node classification data to obtain the planned restricted development area; perform regional connectivity analysis on the overall model of the planning area based on the dense building network in the area to obtain the connectivity data of the planning area; and perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

[0026] In the embodiments of this invention, please refer to Figure 1 The diagram shown illustrates the steps of the data processing method for land spatial planning according to the present invention. In this example, the data processing method for land spatial planning includes the following steps:

[0027] Step S1: Acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain a 3D model of the planning area and a 3D model of the regional buildings; integrate the 3D model of the planning area and the 3D model of the regional buildings to obtain an overall model of the planning area.

[0028] In this embodiment of the invention, aerial or satellite imagery parameters are determined according to planning requirements, and data is collected and preprocessed to generate an orthophoto map of the planning area. Then, high-density point cloud data is generated using the imagery, and the point clouds are classified based on the images to extract building point clouds. Next, the building point clouds are denoised, segmented, and simplified, and 3D models of terrain and buildings with realistic textures are constructed using the regional dense point cloud and building point clouds, respectively. Afterwards, feature points are extracted for matching and registration to accurately locate the building models within the 3D model of the planning area. Finally, the coordinate-transformed building models are merged with the terrain model to generate an overall model of the planning area containing terrain, buildings, and other elements.

[0029] Step S2: Identify densely built areas in the overall model of the planning area to obtain densely built areas; pre-set dense building nodes in the overall model of the planning area based on the densely built areas to obtain dense building nodes; construct a node network in the overall model of the planning area based on the dense building nodes to obtain a dense building network; classify the dense building nodes based on the land planning area image to obtain node classification data.

[0030] In this embodiment of the invention, building models are extracted from the overall model of the planning area, building density is calculated, and densely built areas are identified using region growing or density clustering algorithms. Then, the boundaries of each densely built area are extracted, and its center point is calculated. Next, nodes are preset at the center points according to predefined rules and fine-tuned based on regional characteristics. Afterward, the spatial relationships between nodes are analyzed, a node network is constructed using a network construction algorithm, and then optimized. Finally, based on the land planning area image, ecological environment indicators within the node's influence area are extracted, the nodes are ecologically evaluated, and the nodes are classified into high-ecological-value nodes and low-ecological-value nodes based on their ecological scores.

[0031] Step S3: Based on the overall model of the planning area and the land planning area image, perform restricted development area analysis on the node classification data to obtain the planned restricted development area; perform regional connectivity analysis on the overall model of the planning area based on the dense building network in the area to obtain the connectivity data of the planning area; and perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

[0032] In this embodiment of the invention, elevation data is extracted from the overall model of the planning area to generate a digital elevation model and a slope map. These are then overlaid and analyzed based on the buffer zones of high-ecological nodes and the slope map to obtain topographic change trend data. Ecological buffer zones are set according to node type and the sensitivity of the surrounding environment, and buffer zones of adjacent nodes are merged. Restricted development rules are formulated based on topographic change trends and ecological buffer zones, and restricted development areas are identified and marked using GIS. Regional connectivity is assessed using network analysis algorithms, and connectivity indices are calculated. Finally, based on the planned restricted development areas, connectivity data, regional resource and environmental carrying capacity, development potential, and functional positioning, the spatial layout is optimized, functional zones are divided, and scheme evaluation is conducted to ultimately obtain a national land spatial planning scheme.

[0033] This invention constructs a 3D model of the planning area and buildings by acquiring regional images and generating dense point cloud data, and finally integrates them into a unified overall model. The benefit of this step is that it elevates traditional 2D planning to a 3D level, enabling a more intuitive and detailed representation of landforms and spatial relationships, providing more accurate foundational data for subsequent analysis and planning. Compared to planning solely based on 2D maps, the 3D model more realistically reflects information such as surface undulations and building heights, avoiding planning deviations caused by missing information, thereby improving the scientific rigor and accuracy of the planning. Based on the overall model, densely built-up areas are identified, nodes are pre-defined, and networks are constructed. This allows planning to move beyond simply focusing on land parcels and delve into the building level, analyzing building density, distribution patterns, and interconnections. By constructing a node network, the urban spatial structure can be better understood, key nodes and important connection paths can be identified, providing more refined guidance for transportation planning and infrastructure construction, and laying the foundation for subsequent analysis of restricted development areas and connectivity analysis, ultimately improving the rationality and effectiveness of the planning. Restricted development area analysis and regional connectivity analysis are then conducted to ultimately generate a national land spatial planning scheme. By combining the overall model, node classification data, and regional images, factors such as topography, ecological environment, and building distribution can be considered more comprehensively. This allows for the scientific delineation of restricted development areas and the assessment of regional connectivity based on the node network, ensuring the rationality and feasibility of the planning scheme. This comprehensive analysis method effectively avoids the limitations of planning dominated by a single factor, enhancing the overall integrity and coordination of the plan.

[0034] Preferably, step S1 includes the following steps:

[0035] Step S11: Obtain regional images of the land planning area to obtain images of the land planning area;

[0036] In this embodiment of the invention, parameters such as the coverage, resolution, and image overlap of aerial or satellite imagery are determined based on the spatial scope and target accuracy requirements of land use planning. A high-resolution camera or sensor is mounted on a drone or satellite platform to collect data according to a preset flight path or shooting plan. The acquired raw image data undergoes preprocessing operations such as geometric correction, radiometric correction, stitching, and cropping to generate an orthophoto map of the land use planning area that meets the accuracy requirements.

[0037] Step S12: Generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data;

[0038] In this embodiment of the invention, preprocessed images of the land planning area are imported into point cloud generation software. Based on accuracy requirements and computer performance, various parameters for point cloud generation are set, such as image matching algorithms, point cloud density, and filtering parameters. The software is run to perform dense matching and point cloud generation, resulting in high-density point cloud data of the planning area. The generated point cloud data undergoes quality checks, including checks on point cloud density, accuracy, and completeness.

[0039] Step S13: Classify the dense point cloud data of the region based on the land planning area image to obtain the regional classified point cloud data;

[0040] In this embodiment of the invention, a suitable point cloud classification method is selected based on data characteristics and classification objectives, such as rule-based classification, random forest classification, and deep learning classification. According to the needs of land planning, the classification categories of the point cloud data are determined, such as buildings, vegetation, roads, and water bodies. Feature information of the point cloud data, such as point cloud height, intensity, normal vector, color, and geometric shape, is extracted to provide a basis for classification. For some classification methods, such as random forest and deep learning, it is necessary to train the classifier using existing labeled data. Using the selected classification method and the trained classifier, the dense point cloud data of the region is classified to obtain point cloud data of different categories of objects.

[0041] Step S14: Extract regional building point cloud data from the regional classification point cloud data to obtain regional building point cloud data;

[0042] In this embodiment of the invention, point cloud data labeled as "buildings" are filtered from the overall point cloud data based on the classification results using methods such as Boolean operations or spatial queries. For the filtered building point cloud data, algorithms such as statistical filtering and radius filtering are used to remove noisy point clouds caused by factors such as occlusion and reflection. For areas with multiple buildings, algorithms based on plane fitting, region growing, and cluster analysis are used to segment the building point cloud data into individual building point clouds. Algorithms such as triangular mesh simplification and voxelization simplification are used to simplify the segmented individual building point clouds, reducing the data volume, improving subsequent processing efficiency, and preserving the main geometric features of the buildings.

[0043] Step S15: Construct a 3D model of the regional terrain based on the regional dense point cloud data to obtain a 3D model of the planned area; construct a 3D model of the regional buildings based on the regional building point cloud data to obtain a 3D model of the regional buildings.

[0044] In this embodiment of the invention, dense point cloud data of a region is filtered to remove non-ground points such as vegetation and buildings, retaining only the ground point cloud data. A TIN model representing the terrain undulation is generated based on the ground point cloud data using the Delaunay triangulation algorithm. Texture mapping is performed on the TIN model using orthophotos or oblique imagery to generate a 3D terrain model with realistic colors and textures. Based on the processed building point cloud data, 3D point cloud models of buildings are constructed using algorithms such as Delaunay triangulation and Poisson reconstruction. The reconstructed building point cloud models are simplified and regularized, removing redundant details to generate concise and regular building models. Texture mapping is then performed on the simplified building models using orthophotos or oblique imagery to generate 3D building models with realistic colors and textures.

[0045] Step S16: Based on the regional building point cloud data, locate the building model of the 3D model of the planning area to obtain the building model location data;

[0046] In this embodiment of the invention, feature points, such as corner points and edge points, are extracted from building point cloud data and a 3D model of the planning area, and then matched using feature descriptors. Using the matched feature point pairs, algorithms such as singular value decomposition are employed to calculate a coarse transformation matrix of the building point cloud data relative to the 3D model of the planning area. Iterative nearest-point algorithms are then used to iteratively optimize the coarse registration results to obtain accurate building model positioning data.

[0047] Step S17: Based on the building model positioning data, integrate the regional building 3D model and the planning area 3D model to obtain the overall model of the planning area.

[0048] In this embodiment of the invention, the regional building 3D model is transformed according to the building model positioning data, and placed in the correct position on the planning area 3D model. The regional building 3D model after coordinate transformation is then merged with the planning area 3D model to generate an overall planning area model including terrain, buildings, and other elements.

[0049] This invention acquires regional images for land planning, laying the foundation for all subsequent analyses. High-resolution, high-quality regional images provide rich geographic information, including topography, vegetation cover, and land use types, providing essential data support for subsequent point cloud generation, 3D modeling, and various spatial analyses, ensuring the accuracy and scientific rigor of the planning. Generating dense point cloud data based on regional images transforms two-dimensional images into three-dimensional spatial data, providing richer spatial information. Dense point clouds can accurately represent the three-dimensional morphology and spatial distribution of features, providing a more refined data foundation for subsequent 3D modeling and analysis. Compared to traditional two-dimensional data, point cloud data can more accurately represent information such as surface undulations and building heights. Classifying regional dense point cloud data according to different feature types, such as buildings, vegetation, and ground, helps extract specific types of feature information from the point cloud data. For example, extracting building point clouds for building models and ground point clouds for terrain models improves data processing efficiency and accuracy. Extracting regional building point cloud data from the classified point cloud data provides specialized data for constructing detailed 3D building models. Extracting building point cloud data effectively removes interference from other terrain features, resulting in more accurate building model construction and a better reflection of the building's geometry, spatial location, and height. Regional dense point cloud data and regional building point cloud data are used to construct 3D models of the planning area and the area's buildings, respectively. This step transforms the point cloud data into a more intuitive and easily understood 3D model, clearly showcasing the topography and building distribution of the planning area, providing a more intuitive data foundation for subsequent model integration and spatial analysis. Based on the regional building point cloud data, the building models are precisely located within the 3D model of the planning area. This ensures accurate spatial relationships between the building and terrain models, providing precise location information for subsequent model integration and spatial analysis. Finally, the terrain and building models are merged to form a unified 3D scene, providing a more comprehensive and realistic representation of the overall appearance of the planning area.

[0050] Preferably, step S13 includes the following steps:

[0051] Step S131: Perform image semantic data segmentation on the land planning area image to obtain image semantic data;

[0052] In this embodiment of the invention, an image semantic segmentation model suitable for land planning scenarios is selected, such as U-Net, DeepLab, or PSPNet. An open-source pre-trained model can be chosen based on project requirements, or proprietary data can be used for model training and fine-tuning. The images of the land planning area are pre-processed, such as through image scaling and normalization, to adapt to the input requirements of the selected semantic segmentation model. The selected model is then used to perform semantic segmentation on the pre-processed images, predicting the semantic category of each pixel, such as buildings, roads, vegetation, or water bodies.

[0053] Step S132: Based on the image semantic data, perform semantic classification and image segmentation on the land planning area image to obtain image classification semantic segmentation data;

[0054] In this embodiment of the invention, adjacent pixels of the same category are grouped together to form different semantic regions based on the category label of each pixel in the image semantic data. Edge detection algorithms, such as the Canny operator, or contour extraction algorithms are used to extract the boundaries of each semantic region. The extracted region boundaries are converted into vector formats, such as polygons or line segments, and the semantic category information of each vector object is recorded. The vectorized semantic region data is overlaid with the original land planning area image to generate image classification semantic block data containing semantic category annotations.

[0055] Step S133: Based on the regional dense point cloud data, perform data mapping on the land planning area image to obtain point cloud mapping image data;

[0056] In this embodiment of the invention, by utilizing camera parameters, intrinsic and extrinsic parameters, dense point cloud data of a region is projected onto an image plane of a land planning area to obtain the corresponding pixel coordinates of each point cloud on the image. Point cloud information projected onto each pixel, such as 3D coordinates, color, and intensity, is extracted and stored at the corresponding pixel location to form point cloud mapping image data. For areas in the image without point cloud projection, interpolation algorithms, such as inverse distance weighted interpolation, can be used to fill in the gaps, thereby obtaining more complete point cloud mapping image data.

[0057] Step S134: Classify the point cloud region of the point cloud mapping image data according to the image classification semantic block data to obtain classified point cloud region data;

[0058] In this embodiment of the invention, point cloud mapping image data is spatially superimposed with image classification semantic block data, so that each pixel simultaneously contains point cloud information and semantic category label. Based on the semantic category label of each pixel, the point cloud mapping image data is segmented into different point cloud regions, and the point clouds within each region have the same semantic category.

[0059] Step S135: Based on the classified point cloud region data, perform point cloud classification and segmentation on the dense point cloud data of the region to obtain the classified point cloud data of the region.

[0060] In this embodiment of the invention, a point cloud index is established based on the point cloud information stored in each pixel of the point cloud mapping image data to quickly locate the original point cloud data corresponding to each pixel. The categorized point cloud region data is traversed, and based on the boundary information and semantic category label of each region, all point clouds within that region are found using the point cloud index, and these are segmented from the original dense point cloud data. The segmented point cloud data is stored as a new point cloud file, and a semantic category label is added to each point cloud, ultimately resulting in point cloud data categorized according to semantic categories.

[0061] This invention identifies different objects or regions in an image through this step and assigns a corresponding semantic label to each object or region. This semantic segmentation technique helps in understanding image content and provides foundational data for subsequent image classification and point cloud processing. Based on the image semantic data, image segmentation divides the image into multiple small blocks with specific semantic classifications. This segmentation technique can better handle complex images, providing more refined image information for subsequent point cloud data mapping and classification. Point cloud data is mapped to the image to generate a point cloud mapping image. Through point cloud mapping, point cloud data can be associated with image pixels, making the spatial location of the point cloud correspond to the image content, thus providing key information for subsequent point cloud classification and processing. Based on the image classification semantic segmentation data, point cloud regions are classified in the point cloud mapping image. This step classifies point cloud data according to the semantic information of the image, identifying different categories of spatial regions, such as buildings, vegetation, and roads, laying the foundation for subsequent point cloud segmentation and processing. Based on the classification results, dense point cloud data in different regions is segmented to obtain point cloud data of different categories. This step effectively separates different types of spatial data, providing a more refined and accurate point cloud dataset for subsequent spatial analysis, modeling, and applications.

[0062] Preferably, step S2 includes the following steps:

[0063] Step S21: Identify densely built areas in the overall model of the planning area to obtain the densely built areas in the region;

[0064] Step S22: Locate the center of the densely built-up area to obtain the center point of the building area;

[0065] Step S23: Based on the center point of the building area, preset the dense building nodes of the overall model of the planning area to obtain the dense building nodes;

[0066] Step S24: Construct a node network for the overall model of the planning area based on dense building nodes to obtain a dense building network for the area;

[0067] Step S25: Classify the dense building nodes based on the land planning area image to obtain node classification data, which includes high-ecological nodes and low-ecological nodes.

[0068] As an embodiment of the present invention, reference Figure 2 As shown, Figure 1 A detailed flowchart of step S2 is shown below. In this embodiment, step S2 includes the following steps:

[0069] Step S21: Identify densely built areas in the overall model of the planning area to obtain the densely built areas in the region;

[0070] In this embodiment of the invention, all building models are extracted from the overall model of the planning area based on semantic information or geometric features. The planning area is divided into regular grids or an adaptive density clustering algorithm is used to count the number of buildings, their floor area, or volume within each grid or cluster, and to calculate the building density. A building density threshold is set based on planning requirements or empirical values ​​to distinguish between densely built and non-densely built areas. Based on the density threshold, a region growing algorithm or a density clustering algorithm is used to merge adjacent grids or clusters with densities exceeding the threshold, forming connected densely built areas.

[0071] Step S22: Locate the center of the densely built-up area to obtain the center point of the building area;

[0072] In this embodiment of the invention, the boundary of each densely built area is extracted using image processing or 3D model processing algorithms. Based on the area boundary, the center point of each densely built area is determined using methods such as geometric center calculation, centroid calculation, or minimum bounding box center calculation.

[0073] Step S23: Based on the center point of the building area, preset the dense building nodes of the overall model of the planning area to obtain the dense building nodes;

[0074] In this embodiment of the invention, node preset rules are formulated based on planning needs or experience. For example, one node is preset at the center point of each building area, or multiple nodes are preset according to the size and shape of the area. According to the preset rules, the nodes are placed at the center point of the building area, or fine-tuned according to the characteristics of the area, for example, the nodes are placed in locations with convenient transportation or near landmark buildings in the area.

[0075] Step S24: Construct a node network for the overall model of the planning area based on dense building nodes to obtain a dense building network for the area;

[0076] In this embodiment of the invention, the spatial relationships between nodes, such as distance, visibility, and accessibility, are analyzed to determine whether there are potential connections between nodes. Algorithms such as Delaunay triangulation, minimum spanning tree, and k-nearest neighbor graphs are used to construct a node network based on the connectivity between nodes, connecting related nodes. The constructed node network is then optimized according to the actual situation, for example, by deleting redundant edges, adding necessary edges, and adjusting node positions.

[0077] Step S25: Classify the dense building nodes based on the land planning area image to obtain node classification data, which includes high-ecological nodes and low-ecological nodes.

[0078] In this embodiment of the invention, the influence area of ​​each node is determined based on a preset search radius or other spatial division method, with each node as the center. Based on a land planning area image, ecological environment indicators within the node's influence area are extracted, such as vegetation coverage, water area, green space ratio, and air quality. Based on the extracted ecological indicators, methods such as the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation are used to evaluate the ecological environment of the node's influence area, calculating the ecological score for each node. Based on the node's ecological score, a classification threshold is set, dividing the nodes into high-ecological-value nodes and low-ecological-value nodes.

[0079] This invention analyzes the overall model of a planning area to identify densely built-up areas, a crucial observation for urban spatial layout. This step helps understand the development level and building distribution of the area, providing key information for subsequent planning and design. This is significant in optimizing urban space and infrastructure development. Centralizing densely built-up areas allows for the rapid determination of the area's geometric center or functional core, providing important reference points for subsequent functional analysis, traffic planning, and resource allocation, thus contributing to optimized urban spatial organization and improved urban operational efficiency. Pre-setting dense building nodes based on the area's central point does not simply abstract buildings as points, but rather simulates building density and distribution patterns based on the influence of the area's center, laying the foundation for building a more realistic and refined urban model. Constructing a dense building network based on these nodes does not simply connect individual nodes, but rather reveals the spatial connections between urban buildings through the network structure, providing an intuitive basis for analyzing urban structure, traffic flow, and information transmission, and contributing to a deeper understanding of the city's spatial organization and operational patterns. Classifying nodes based on regional images of national land planning, distinguishing between high-ecological-value nodes and low-ecological-value nodes, is not simply a spatial analysis, but rather incorporates ecological factors into the consideration. This allows for the assessment of the impact of urban construction on the ecological environment, providing data support for optimizing urban layout, improving urban ecological benefits, and promoting sustainable urban development.

[0080] Preferably, step S25 includes the following steps:

[0081] Step S251: Obtain the building density of dense building nodes to get the node building density data; preset the single building influence range of dense building nodes to get the single building influence range data.

[0082] Step S252: Calculate the influence range of dense building nodes based on the node building density data to obtain the node influence range data;

[0083] Step S253: Based on the node influence range data, perform ecological data retrieval on the influence range of the land planning area image to obtain the ecological data of the influence area;

[0084] Step S254: Compare the ecological data of the affected area with the preset ecological data of the area. If the ecological data of the affected area is greater than the preset ecological data of the area, the dense building node is marked as a high ecological node; if the ecological data of the affected area is less than or equal to the preset ecological data of the area, the dense building node is marked as a low ecological node.

[0085] As an embodiment of the present invention, reference Figure 3 As shown, Figure 2 A detailed flowchart of step S25 is shown below. In this embodiment, step S25 includes the following steps:

[0086] Step S251: Obtain the building density of dense building nodes to get the node building density data; preset the single building influence range of dense building nodes to get the single building influence range data.

[0087] In this embodiment of the invention, by utilizing existing building vector data or 3D models, the building area ratio within a certain range around each dense building node is statistically analyzed. For example, the building area ratio of a circular area with a radius of 500 meters centered on the node is used to obtain the node building density data. Based on urban planning regulations or empirical values, the influence range of a single building on the surrounding environment is preset. For example, the influence range of a building with a height of 30 meters can be set as a circular area with a radius of 100 meters.

[0088] Step S252: Calculate the influence range of dense building nodes based on the node building density data to obtain the node influence range data;

[0089] In this embodiment of the invention, the preset single building influence range of each node is superimposed according to the building density of that node. For example, if the building density of a node is 30%, the radius of the single building influence range is reduced to 0.3 times, which is taken as the actual influence range of that node. Considering the actual situation, the superimposed influence range is modified. For example, the boundary of the influence range is adjusted according to the blocking effect of elements such as roads and green spaces on the influence range.

[0090] Step S253: Based on the node influence range data, perform ecological data retrieval on the influence range of the land planning area image to obtain the ecological data of the influence area;

[0091] In this embodiment of the invention, ecological and environmental indicator data, such as the normalized difference vegetation index (NDVI), surface temperature, and impervious surface ratio, are extracted from images of land use planning areas and raster data is generated. Based on the influence range data of each node, the extracted ecological data is cropped to obtain the ecological data within the influence area of ​​each node. As needed, statistical analysis is performed on the ecological data within the influence area, such as calculating the average normalized difference vegetation index, maximum surface temperature, and impervious surface ratio, to obtain the comprehensive ecological indicators for the influence area of ​​each node.

[0092] Step S254: Compare the ecological data of the affected area with the preset ecological data of the area. If the ecological data of the affected area is greater than the preset ecological data of the area, the dense building node is marked as a high ecological node; if the ecological data of the affected area is less than or equal to the preset ecological data of the area, the dense building node is marked as a low ecological node.

[0093] In this embodiment of the invention, based on planning objectives or relevant standards, preset threshold values ​​for desired ecological and environmental indicators for the region are established, such as a normalized average vegetation index greater than 0.6 and a maximum surface temperature below 35 degrees Celsius. The ecological data of the area affected by each node is compared with the corresponding preset regional ecological data to determine whether the node has reached the expected ecological and environmental level. Based on the comparison results, nodes that meet the preset ecological indicators are marked as high-ecological-level nodes, and nodes that do not meet them are marked as low-ecological-level nodes.

[0094] This invention lays the data foundation for calculating the actual impact range of each node by acquiring the building density of nodes and the preset impact range of individual buildings. Presetting the impact range of individual buildings allows for consideration of factors such as building type, height, and surrounding environment, making the analysis more realistic. Correcting the impact range of individual buildings based on the node building density yields more accurate node impact range data, avoiding the crude approach of simply treating all nodes as having the same impact range, thus making the analysis results more reliable. Based on the node impact range data, ecological data for corresponding areas in the land planning area image can be accurately retrieved, avoiding the inefficient practice of large-scale ecological data analysis of the entire area, improving the efficiency and accuracy of data processing. By comparing the ecological data of the impact area with the preset regional ecological data, the degree of impact of each node on its surrounding ecological environment can be determined. Nodes with impact area ecological data higher than the preset value are marked as high-ecological nodes, indicating that the ecological environment quality around the node is relatively good; conversely, those with lower impact area ecological data are marked as low-ecological nodes. This provides a reference for urban planning, linking urban building density with ecological environment data, offering a new perspective and method for assessing the impact of urban development on the ecological environment, and contributing to the coordinated development of urban construction and the ecological environment.

[0095] Preferably, step S253 includes the following steps:

[0096] Step S2531: Perform geographic model registration on the land planning area image to obtain the regional model-registered image;

[0097] In this embodiment of the invention, several pairs of corresponding control points are selected on the land planning area image and geographic reference data, such as topographic maps and orthophotos. The control points should be clearly identifiable, evenly distributed, and have high positioning accuracy. Based on the distribution and number of control points, a suitable geometric transformation model is selected, such as affine transformation, polynomial transformation, or projection transformation. Using the selected control points and transformation model, the optimal transformation parameters are calculated to spatially align the land planning area image with the geographic reference data. Based on the calculated transformation parameters, the land planning area image is resampled and converted to the same coordinate system and resolution as the geographic reference data to obtain a regional model registration image.

[0098] Step S2532: Mark the influence range of the region model registration image based on the node influence range data to obtain the influence region marked image;

[0099] In this embodiment of the invention, the node influence range data is transformed from its original coordinate system to the coordinate system of the region model registration image. The transformed node influence range vector data is rasterized to generate a binary image with the same resolution as the region model registration image, wherein pixels within the influence range have a value of 1, and pixels outside the range have a value of 0. The rasterized node influence range image is then overlaid with the region model registration image to obtain an influence region marker image.

[0100] Step S2533: Extract ecological image features from the marked images of the affected areas to obtain ecological image feature data;

[0101] In this embodiment of the invention, image bands sensitive to the ecological environment, such as near-infrared, red, and blue bands, are selected based on the research objectives and data characteristics. Using the selected bands, characteristic indicators reflecting the ecological environment are calculated, such as the normalized difference vegetation index (NDVI), enhanced vegetation index (EDI), soil-regulated vegetation index (SRI), and ratio vegetation index (RRI). The calculated characteristic indicators are stored as new image bands, generating image data containing multiple ecological image features.

[0102] Step S2534: Based on the ecological image feature data, perform data mapping on the marked image of the affected area to obtain the feature data mapping image;

[0103] In this embodiment of the invention, ecological image feature data is cropped based on the influence area marker image to obtain feature data within the influence area of ​​each node. The feature data of all node influence areas are then stitched together to generate a new feature data mapping image. Pixels in the feature data mapping image that do not belong to any node influence area are filled with background, for example, with a value of 0.

[0104] Step S2535: Perform ecological data retrieval on the influence range of the feature data mapping image to obtain ecological data of the influence area.

[0105] In this embodiment of the invention, regional statistical analysis is performed on the feature data mapping image based on the boundary of the influence range of each node. For example, the average, maximum, minimum, and standard deviation of each ecological image feature within the influence area of ​​each node are calculated. The statistical results are then organized into tables or other data structures to obtain the ecological data of the influence area of ​​each node.

[0106] This invention performs geographic model registration on regional images for land planning, essentially aligning two-dimensional images with a real geographic coordinate system. This provides a precise spatial reference for subsequent spatial analysis and data extraction, ensuring the accuracy and reliability of the analysis results. Marking the influence range of the registered regional images based on node influence range data is equivalent to visualizing the abstract node influence range onto a map, providing a clear spatial scope for subsequent accurate extraction of ecological data and avoiding invalid analysis of irrelevant areas. Extracting ecological image features from the marked influence area images is equivalent to identifying and extracting key information related to the ecological environment, such as vegetation cover, water area, and soil type, providing quantifiable ecological indicators for subsequent analysis and making the assessment results more objective and comparable. Mapping the marked influence area images based on ecological image feature data is equivalent to combining the extracted ecological indicators with geospatial information to form a visualized ecological data layer, providing an intuitive visual presentation for subsequent analysis and facilitating the identification and analysis of the ecological characteristics of different regions. Retrieving ecological data within the influence range of a node from a feature-mapped image is equivalent to accurately extracting ecological data within the node's influence range from the data layer. This provides direct data evidence for subsequent assessments of the node's impact on the ecological environment, making the assessment results more convincing. By combining image processing technology with geographic information system technology, accurate extraction of ecological data within the node's influence range is achieved, providing crucial data support for urban planning and ecological environmental protection.

[0107] Preferably, step S3 includes the following steps:

[0108] Step S31: Based on the overall model of the planning area, perform terrain change overlay analysis on the high ecological nodes to obtain terrain change trend data;

[0109] In this embodiment of the invention, elevation data is extracted from the overall model of the planning area to generate a digital elevation model (DEM). Based on the DEM data, spatial analysis algorithms are used to calculate the terrain slope and generate a slope map. A circular buffer zone is generated, centered on a high-ecological-node and according to a preset buffer radius. The high-ecological-node buffer zone and the slope map are spatially overlaid and analyzed to statistically analyze the slope change trend within the buffer zone, such as calculating the average slope, maximum slope, and slope change rate, and generating terrain change trend data.

[0110] Step S32: Based on the land planning area image, set up ecological buffer zones for high-ecological nodes and low-ecological nodes to obtain node ecological buffer zone data;

[0111] In this embodiment of the invention, different ecological buffer radii are set according to the node type, including high-ecological-value nodes or low-ecological-value nodes, and the sensitivity of the surrounding environment. For example, the buffer radius of high-ecological-value nodes can be set to be larger. Circular, elliptical, or other shaped buffers are generated around the node according to the set buffer radius. Buffers of adjacent nodes can be merged according to actual conditions to avoid overlapping or excessive fragmentation of buffers.

[0112] Step S33: Based on terrain change trend data and buffer zone data, mark the restricted development areas in the overall model of the planning area to obtain the planned restricted development areas;

[0113] In this embodiment of the invention, development restriction rules are formulated based on terrain change trend data and ecological buffer zone data. For example, development and construction activities are prohibited in areas with slopes greater than a certain value or in areas located within high ecological node buffer zones. Using the spatial query and overlay analysis functions of a geographic information system, the development restriction rules are applied to the overall model of the planning area to identify all areas that meet the development restriction conditions. The identified restricted development areas are marked, for example, by using color differentiation or adding annotation information to the overall model of the planning area.

[0114] Step S34: Perform regional connectivity analysis on the overall model of the planning area based on the dense building network in the area to obtain connectivity data of the planning area;

[0115] In this embodiment of the invention, a suitable network analysis algorithm, such as shortest path analysis, service area analysis, or network connectivity analysis, is selected to evaluate the connectivity of a region. Network analysis parameters, such as analysis radius, impedance factor, and connectivity indices, are set according to the analysis objectives and actual conditions. Using the selected network analysis algorithm and parameter settings, connectivity indices between nodes or regions within the planning area are calculated, such as distance, time, and cost.

[0116] Step S35: Based on the planning restriction development area and the connectivity data of the planning area, conduct land planning on the overall model of the planning area to obtain the land space planning scheme.

[0117] In this embodiment of the invention, spatial layout is optimized based on connectivity data of restricted development areas and planned areas. For example, construction land planning avoids restricted development areas, and transportation network construction is strengthened to improve regional connectivity. Based on the region's resource and environmental carrying capacity, development potential, and functional positioning, the planned area is divided into different functional zones, such as ecological protection zones, agricultural development zones, and urban construction zones. The formulated land spatial planning scheme is evaluated, for example, through environmental impact assessments and socio-economic benefit assessments.

[0118] This invention, through topographic change overlay analysis of high-ecological-value nodes, can identify topographic change trends, such as slope and altitude, providing a basis for subsequent delineation of restricted development areas. This avoids large-scale development and construction in ecologically sensitive areas, effectively protecting the ecological environment. Setting up ecological buffer zones of different sizes for high-ecological-value and low-ecological-value nodes reflects the principle of differentiated protection, providing stronger protection to areas with high ecological value and allowing moderate development to areas with relatively low ecological value, thus balancing the needs of ecological protection and urban development. Based on topographic change trend data and ecological buffer zone data, restricted development areas can be accurately delineated, such as areas with steep slopes and high ecological value, and these can be removed from the developable areas, preventing damage to the ecological environment at the source and ensuring regional ecological security. By conducting connectivity analysis of dense building networks in the region, urban development axes and ecological corridors can be identified, providing a reference for subsequent optimization of urban spatial layout. This ensures that urban planning considers inter-regional connections and creates an efficient and highly functional urban network, avoiding disorderly urban expansion and promoting harmonious coexistence between the city and nature. Land use planning based on restricted development areas and regional connectivity data can formulate more scientific and rational land use schemes. Incorporating ecological factors as an important consideration in territorial spatial planning provides new ideas and methods for formulating more scientific and rational planning schemes, which helps promote sustainable urban development.

[0119] Preferably, step S31 includes the following steps:

[0120] Step S311: Obtain historical terrain data for high-ecological-value nodes to obtain historical terrain data for the nodes;

[0121] In this embodiment of the invention, by clearly defining the spatial range of the required historical terrain data, and centering on high-ecological nodes, appropriate buffer zones, time spans, and resolutions are determined to select suitable data sources. Historical terrain data is obtained from reliable data sources, such as publicly available topographic maps, historical remote sensing imagery, and LiDAR data. The acquired historical terrain data undergoes preprocessing, such as coordinate system transformation, geometric correction, and data format conversion, to ensure data consistency and accuracy.

[0122] Step S312: Perform temporal segmentation based on the node's historical terrain data to obtain the node's temporal terrain data;

[0123] In this embodiment of the invention, historical terrain data is segmented by selecting appropriate time intervals based on research objectives and data characteristics, for example, using 5 years, 10 years, or other time intervals as a period. Centered on high-ecological-nodes, the historical terrain data for each time period is cropped according to a preset buffer range, resulting in terrain data for each node in different time periods. The cropped node historical terrain data is then organized chronologically to form node temporal terrain data, for example, stored as multi-temporal DEM data or point cloud data.

[0124] Step S313: Construct a temporal terrain model from the node temporal terrain data to obtain the node temporal terrain model;

[0125] In this embodiment of the invention, a suitable temporal terrain model construction method is selected based on the data type and accuracy requirements, such as a TIN-based model, a raster-based model, or a point cloud-based model. Model parameters are set according to the data characteristics and modeling method, such as grid size, interpolation method, and model accuracy. Using the selected modeling method and parameter settings, the temporal terrain data of each node is modeled, generating a sequence of three-dimensional models that reflects the changes in the terrain of that node over time.

[0126] Step S314: Perform temporal overlay analysis on the overall model of the planning area based on the node temporal terrain model to obtain the temporal evolution terrain model;

[0127] In this embodiment of the invention, the temporal terrain model of each node is registered with the overall model of the planning area to ensure that they are in the same spatial reference frame. Based on the time series, the temporal terrain model of each node is fused with the overall model of the planning area to generate a temporal evolution terrain model containing multiple time nodes. Model stitching, data fusion, and other methods can be used to ensure the integrity and continuity of the model.

[0128] Step S315: Analyze the changing trends of high-ecological nodes based on the temporal evolution terrain model to obtain terrain change trend data.

[0129] In this embodiment of the invention, a time-series evolution terrain model is used, employing methods such as the difference method and trend analysis, to analyze terrain changes in high-ecological-node areas, including changes in elevation, slope, and volume. Statistical analysis is performed on the detected terrain changes, such as calculating the rate of change, direction of change, and magnitude of change, and the trends of terrain change are identified, such as erosion, deposition, and stabilization.

[0130] This invention lays the foundation for analyzing topographic change by collecting historical topographic information of high ecological nodes. By acquiring data from different periods, planners can understand the topographic evolution of the region. Historical topographic data includes geomorphic changes, hydrological patterns, and land use patterns, providing valuable background information for subsequent analysis and decision-making. It helps identify patterns and trends in topographic change. Through time-series analysis, planners can discover significant topographic changes and assess their potential impacts on ecosystems and the environment. This approach provides a powerful tool for understanding the dynamic changes in topography within urban areas. Models are created based on time-series segmented data to visualize and quantify topographic change. Time-series topographic models can demonstrate the changes and evolution of topographic features over different periods. This model provides a direct visual reference for subsequent analysis and comparison. By overlaying the time-series topographic model with a holistic model of the planning area, the impact of topographic change on urban space can be analyzed. This step reveals how topographic change affects ecological nodes, flow patterns, and regional connectivity. It helps make decisions that take topographic change factors into account, such as flood control, land use, and infrastructure planning. Based on time-series topographic evolution models, analyzing topographic change trends in high-ecological-node areas, such as slope and elevation changes, can predict future topographic evolution directions and provide more forward-looking guidance for delineating restricted development zones. For example, areas expected to experience severe soil erosion can be designated as restricted development zones. By analyzing historical topographic data and incorporating the time dimension into topographic analysis, more scientific and forward-looking decision support can be provided for land spatial planning.

[0131] Preferably, step S32 includes the following steps:

[0132] Step S321: Obtain node ecological data for high-ecological nodes and low-ecological nodes to obtain node ecological data; based on the node ecological data, initially set the node ecological buffer for high-ecological nodes and low-ecological nodes to obtain the initial node ecological buffer.

[0133] In this embodiment of the invention, ecological and environmental data, such as land use type, vegetation cover, water distribution, species diversity, and ecosystem service functions, are collected around high-ecological-value nodes and low-ecological-value nodes. Data sources may include remote sensing imagery, field surveys, and ecological and environmental databases. Based on the ecological value assessment results of the nodes, different initial ecological buffer radii are set. For example, nodes with higher ecological value should have larger initial buffer radiuses.

[0134] Step S322: Map node ecological data to the land planning area image based on node ecological data to obtain a node ecological data image;

[0135] In this embodiment of the invention, node ecological data from different sources and in different formats are converted, for example, to raster data, to ensure that the data can be overlaid and analyzed spatially. All node ecological data are uniformly projected onto the same coordinate system and resolution as the land planning area image. The processed node ecological data is mapped onto the land planning area image to generate thematic layers containing node ecological information, such as land use type maps, vegetation cover maps, and water body distribution maps.

[0136] Step S323: Perform node ecological feature data analysis on the node ecological data images to obtain node ecological feature data, including node hydrological data and node biodiversity data;

[0137] In this embodiment of the invention, hydrological characteristics of the area surrounding the node are analyzed based on water body distribution maps, DEM data, etc., such as the distribution of rivers, lakes, and wetlands, water system connectivity, and water conservation capacity, to obtain node hydrological data. Biodiversity characteristics of the area surrounding the node are analyzed based on land use type maps, vegetation cover maps, species distribution data, etc., such as species richness, number of endemic species, and habitat types, to obtain node biodiversity data.

[0138] Step S324: Conduct a node ecological sensitivity assessment based on node hydrological data and node biodiversity data to obtain node ecological sensitivity assessment data;

[0139] In this embodiment of the invention, a node ecological sensitivity assessment index system is constructed based on the characteristics of the study area and planning objectives, selecting key indicators that reflect hydrological and biodiversity characteristics. The weights of each indicator are determined using methods such as the analytic hierarchy process (AHP) and expert scoring to reflect their contribution to ecological sensitivity. Using the selected indicators, weights, and node ecological characteristic data, methods such as weighted summation and fuzzy comprehensive evaluation are employed to calculate the ecological sensitivity score of each node, classifying them into different levels, such as high-sensitivity areas, medium-sensitivity areas, and low-sensitivity areas.

[0140] Step S325: Based on the node's ecological sensitivity assessment data, perform buffer expansion processing on the node's initial ecological buffer zone to obtain the expanded ecological buffer zone;

[0141] In this embodiment of the invention, buffer zone expansion rules are formulated based on the node ecological sensitivity assessment results. For example, different expansion distances or expansion ratios can be set according to the sensitivity level; the higher the sensitivity, the greater the expansion. Using GIS spatial analysis tools, the initial ecological buffer zone of the node is expanded according to the set expansion rules. The expansion method can be simple buffer zone analysis, or it can employ cost-distance analysis, corridor analysis, and other methods to better consider the influence of factors such as topography and hydrology.

[0142] Step S326: Perform regional data integration on the initial ecological buffer zone and the extended ecological buffer zone of the node to obtain the node ecological buffer zone data.

[0143] In this embodiment of the invention, data from the initial ecological buffer and the extended ecological buffer of a node are merged to generate a layer containing information about all buffers. Attribute information is added to the merged buffer layer, such as node number, buffer type (including initial or extended buffer), and ecological sensitivity level.

[0144] This invention acquires node ecological data and sets initial ecological buffer zones for nodes based on this data, reflecting a differentiated protection approach for nodes with different ecological values ​​and providing a foundation for subsequent refined adjustments. Mapping node ecological data onto a land planning area image visualizes the abstract data, providing an intuitive basis for subsequent spatial analysis and feature extraction. Analyzing the node ecological data image extracts key ecological characteristic data, such as hydrological and biodiversity data, providing quantitative indicators for assessing node ecological sensitivity, making the assessment results more objective and comparable. Based on indicators such as hydrological and biodiversity data, ecological sensitivity assessment of nodes can identify areas with more fragile ecosystems requiring key protection, providing a basis for buffer zone expansion. Expanding the initial ecological buffer zone based on the node ecological sensitivity assessment data reflects strengthened protection of ecologically sensitive areas, which can more effectively mitigate the negative impacts of urban development on the ecological environment. Integrating the initial and expanded ecological buffer zones forms the final node ecological buffer zone data, providing important ecological constraint boundaries for land spatial planning and ensuring coordination between urban development and ecological protection. This provides a comprehensive framework for urban planning, balancing the needs of ecological protection and urban development. The integrated data can be used to formulate land use strategies, design green spaces, and implement ecological protection measures, thereby promoting the harmonious coexistence of cities and the natural environment. It enables the refined setting of ecological buffer zones, providing technical support for constructing a national spatial pattern that balances urban development and ecological security.

[0145] Preferably, the present invention also provides a data processing system for land spatial planning, used to execute the data processing method for land spatial planning as described above, the data processing system for land spatial planning comprising:

[0146] The planning area model construction module is used to acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain the planning area 3D model and regional building 3D model; and integrate the planning area 3D model and regional building 3D model to obtain the overall planning area model.

[0147] The regional node setting module is used to identify densely built areas in the overall model of the planning area, thereby obtaining densely built areas; based on the densely built areas, it presets densely built nodes in the overall model of the planning area, thereby obtaining densely built nodes; based on the densely built nodes, it constructs a node network in the overall model of the planning area, thereby obtaining a densely built network; and based on the land planning area image, it classifies the densely built nodes, thereby obtaining node classification data.

[0148] The land spatial planning module is used to perform restricted development area analysis on node classification data based on the overall model of the planning area and the land planning area image to obtain the planned restricted development area; to perform regional connectivity analysis on the overall model of the planning area based on the dense building network of the area to obtain the connectivity data of the planning area; and to perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

[0149] In summary, this invention provides a data processing method and system for land spatial planning. The system comprises a planning area model construction module, an area node setting module, and a land spatial planning module. It can implement any data processing method for land spatial planning as described in this invention. The system utilizes the combined operations of computer programs running on each module to achieve any data processing method applicable to land spatial planning. The internal structure of the system collaborates with each other, which greatly reduces repetitive work and manpower input, and provides a faster and more accurate and efficient data processing process for land spatial planning, thereby simplifying the operation flow of the data processing system for land spatial planning.

[0150] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A data processing method for land spatial planning, characterized in that, Includes the following steps: Step S1: Obtain regional images of the land planning area to obtain the land planning area image; Dense point cloud data of the planning area is generated by generating dense point cloud data of the area based on the land planning area image; a three-dimensional model is constructed based on the dense point cloud data of the planning area image to obtain a three-dimensional model of the planning area and a three-dimensional model of the buildings in the area; the three-dimensional model of the planning area and the three-dimensional model of the buildings in the area are integrated to obtain an overall model of the planning area. Step S2: Identify densely built areas in the overall model of the planning area to obtain the densely built areas in the region; Based on the densely built areas in the region, the dense building nodes are pre-set in the overall model of the planning area to obtain the dense building nodes. Based on the dense building nodes, a node network is constructed for the overall model of the planning area to obtain the regional dense building network. Based on the regional images of land planning, the nodes of dense buildings are classified to obtain node classification data; Step S3: Based on the overall model of the planning area and the image of the land planning area, perform restricted development area analysis on the node classification data to obtain the planned restricted development areas; Based on the dense building network in the region, a regional connectivity analysis is performed on the overall model of the planning area to obtain connectivity data for the planning area; Based on the planning restricted development areas and connectivity data of the planning areas, a land use planning scheme is obtained by performing land use planning on the overall model of the planning areas; Step S3 is as follows: Step S31: Based on the overall model of the planning area, perform terrain change overlay analysis on the high ecological nodes to obtain terrain change trend data; Step S32: Based on the land planning area image, set up ecological buffer zones for high-ecological nodes and low-ecological nodes to obtain node ecological buffer zone data; Step S33: Based on terrain change trend data and buffer zone data, mark the restricted development areas in the overall model of the planning area to obtain the planned restricted development areas; Step S34: Perform regional connectivity analysis on the overall model of the planning area based on the dense building network in the area to obtain connectivity data of the planning area; Step S35: Based on the planning restriction development area and the connectivity data of the planning area, conduct land planning on the overall model of the planning area to obtain the land space planning scheme.

2. The data processing method for land spatial planning according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain regional images of the land planning area to obtain images of the land planning area; Step S12: Generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; Step S13: Classify the dense point cloud data of the region based on the land planning area image to obtain the regional classified point cloud data; Step S14: Extract regional building point cloud data from the regional classification point cloud data to obtain regional building point cloud data; Step S15: Construct a 3D model of the regional terrain based on the regional dense point cloud data to obtain a 3D model of the planned area; construct a 3D model of the regional buildings based on the regional building point cloud data to obtain a 3D model of the regional buildings. Step S16: Based on the regional building point cloud data, locate the building model of the 3D model of the planning area to obtain the building model location data; Step S17: Based on the building model positioning data, integrate the regional building 3D model and the planning area 3D model to obtain the overall model of the planning area.

3. The data processing method for land spatial planning according to claim 2, characterized in that, Step S13 includes the following steps: Step S131: Perform image semantic data segmentation on the land planning area image to obtain image semantic data; Step S132: Based on the image semantic data, perform semantic classification and image segmentation on the land planning area image to obtain image classification semantic segmentation data; Step S133: Based on the regional dense point cloud data, perform data mapping on the land planning area image to obtain point cloud mapping image data; Step S134: Classify the point cloud region of the point cloud mapping image data according to the image classification semantic block data to obtain classified point cloud region data; Step S135: Based on the classified point cloud region data, perform point cloud classification and segmentation on the dense point cloud data of the region to obtain the classified point cloud data of the region.

4. The data processing method for land spatial planning according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Identify densely built areas in the overall model of the planning area to obtain the densely built areas in the region; Step S22: Locate the center of the densely built-up area to obtain the center point of the building area; Step S23: Based on the center point of the building area, preset the dense building nodes of the overall model of the planning area to obtain the dense building nodes; Step S24: Construct a node network for the overall model of the planning area based on dense building nodes to obtain a dense building network for the area; Step S25: Classify the dense building nodes based on the land planning area image to obtain node classification data, which includes high-ecological nodes and low-ecological nodes.

5. The data processing method for land spatial planning according to claim 4, characterized in that, Step S25 includes the following steps: Step S251: Obtain the building density of dense building nodes to get the node building density data; preset the single building influence range of dense building nodes to get the single building influence range data. Step S252: Calculate the influence range of dense building nodes based on the node building density data to obtain the node influence range data; Step S253: Based on the node influence range data, perform ecological data retrieval on the influence range of the land planning area image to obtain the ecological data of the influence area; Step S254: Compare the ecological data of the affected area with the preset ecological data of the area. If the ecological data of the affected area is greater than the preset ecological data of the area, the dense building node is marked as a high ecological node; if the ecological data of the affected area is less than or equal to the preset ecological data of the area, the dense building node is marked as a low ecological node.

6. The data processing method for land spatial planning according to claim 5, characterized in that, Step S253 includes the following steps: Step S2531: Perform geographic model registration on the land planning area image to obtain the regional model-registered image; Step S2532: Mark the influence range of the region model registration image based on the node influence range data to obtain the influence region marked image; Step S2533: Extract ecological image features from the marked images of the affected areas to obtain ecological image feature data; Step S2534: Based on the ecological image feature data, perform data mapping on the marked image of the affected area to obtain the feature data mapping image; Step S2535: Perform ecological data retrieval on the influence range of the feature data mapping image to obtain ecological data of the influence area.

7. The data processing method for land spatial planning according to claim 1, characterized in that, Step S31 includes the following steps: Step S311: Obtain historical terrain data for high-ecological-value nodes to obtain historical terrain data for the nodes; Step S312: Perform temporal segmentation based on the node's historical terrain data to obtain the node's temporal terrain data; Step S313: Construct a temporal terrain model from the node temporal terrain data to obtain the node temporal terrain model; Step S314: Perform temporal overlay analysis on the overall model of the planning area based on the node temporal terrain model to obtain the temporal evolution terrain model; Step S315: Analyze the changing trends of high-ecological nodes based on the temporal evolution terrain model to obtain terrain change trend data.

8. The data processing method for land spatial planning according to claim 1, characterized in that, Step S32 includes the following steps: Step S321: Obtain node ecological data for high-ecological nodes and low-ecological nodes to obtain node ecological data; based on the node ecological data, initially set the node ecological buffer for high-ecological nodes and low-ecological nodes to obtain the initial node ecological buffer. Step S322: Map node ecological data to the land planning area image based on node ecological data to obtain a node ecological data image; Step S323: Perform node ecological feature data analysis on the node ecological data images to obtain node ecological feature data, including node hydrological data and node biodiversity data; Step S324: Conduct a node ecological sensitivity assessment based on node hydrological data and node biodiversity data to obtain node ecological sensitivity assessment data; Step S325: Based on the node's ecological sensitivity assessment data, perform buffer expansion processing on the node's initial ecological buffer zone to obtain the expanded ecological buffer zone; Step S326: Perform regional data integration on the initial ecological buffer zone and the extended ecological buffer zone of the node to obtain the node ecological buffer zone data.

9. A data processing system for land spatial planning, characterized in that, For performing the data processing method for land spatial planning as described in claim 1, the data processing system for land spatial planning includes: The planning area model construction module is used to acquire regional images of the land planning area to obtain the land planning area image; generate dense point cloud data based on the land planning area image to obtain regional dense point cloud data; construct a 3D model based on the regional dense point cloud data of the land planning area image to obtain the planning area 3D model and regional building 3D model; and integrate the planning area 3D model and regional building 3D model to obtain the overall planning area model. The regional node setting module is used to identify densely built areas in the overall model of the planning area, thereby obtaining densely built areas; based on the densely built areas, it presets densely built nodes in the overall model of the planning area, thereby obtaining densely built nodes; based on the densely built nodes, it constructs a node network in the overall model of the planning area, thereby obtaining a densely built network; and based on the land planning area image, it classifies the densely built nodes, thereby obtaining node classification data. The land spatial planning module is used to perform restricted development area analysis on node classification data based on the overall model of the planning area and the land planning area image to obtain the planned restricted development area; to perform regional connectivity analysis on the overall model of the planning area based on the dense building network of the area to obtain the connectivity data of the planning area; and to perform land planning on the overall model of the planning area based on the planned restricted development area and the connectivity data of the planning area to obtain the land spatial planning scheme.

Images