Oblique photography three-dimensional earth surface model geological modeling system and method

Abstract

The invention relates to the technical field of three-dimensional geological modeling and geological mapping data processing, in particular to an oblique photography three-dimensional surface model geological modeling system and method, and the system comprises a data collection module, a scene construction module, a boundary line processing module, a geologic body modeling module, a profile linkage module and a result output module. The data acquisition module fuses the oblique photography image and topographic data, and generates a three-dimensional earth surface model through a motion recovery structure algorithm; the geologic body modeling module constructs a closed geologic body through implicit curved surface reconstruction and constrained triangulation; a profile linkage module calls a graph neural network to predict a stratigraphic intersection line trend, and realizes two-dimensional and three-dimensional real-time synchronization based on event driving and sparse voxel hash mapping; and the result output module executes data verification and generates a multi-dimensional geological report. According to the scheme, dependence of a third-party tool is eliminated, geological mapping efficiency is improved, and the problem of section linkage delay is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional geological modeling and geological mapping data processing, and in particular to a system and method for geological modeling of a three-dimensional surface model using oblique photography. Background Art

[0002] Oblique photogrammetry uses multi-angle oblique cameras to acquire high-resolution image data of the Earth's surface. The photogrammetry processing pipeline integrates the spatial coordinates and pixel information of overlapping images to construct a three-dimensional digital surface model. This model accurately reflects the surface morphology and texture details in a GIS environment, thereby supporting geological modeling. Based on the model's surface feature analysis and three-dimensional visualization, geographers deduce stratigraphic distribution and geological structural trends to optimize decision-making for resource exploration and environmental assessment.

[0003] Existing geological mapping relies on manual field surveying and two-dimensional drawing, resulting in a long data collection cycle and difficulty in fully expressing three-dimensional geological structures. Existing modeling software lacks the ability to natively support oblique photography models, forcing geologists to rely on third-party tools such as ArcGIS for data preprocessing and format conversion, resulting in a fragmented modeling process and complex operations. At the same time, the stratigraphic boundary fitting accuracy is insufficient and the profile cutting function lacks a dynamic feedback mechanism for the three-dimensional model. For example, when analyzing the outcrop boundaries of a certain area, it is necessary to switch software multiple times to correct the surface morphology, or it is impossible to synchronize the three-dimensional fault model in real time after editing the two-dimensional profile node, which significantly restricts the efficiency of geological interpretation. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a geological modeling system and method for a three-dimensional surface model using oblique photography to solve the problems of low geological mapping efficiency, reliance on third-party tools for three-dimensional modeling, and insufficient dynamic linkage of profile analysis.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: In a first aspect, the present invention provides a three-dimensional surface model geological modeling system for oblique photography, comprising: The data acquisition module acquires oblique photography images and terrain data, and generates a three-dimensional surface model using a structure-from-motion algorithm; A scene construction module receives the three-dimensional surface model, loads the model data, and dynamically renders the three-dimensional scene according to the spatial coordinates and lithologic properties; a boundary processing module, receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; A geological body modeling module receives the stratum boundary, generates a continuous stratum interface and topologically processes a closed geological body structure; A profile linkage module receives the closed geological body, cuts the closed geological body to generate a profile, and synchronizes the profile with the closed geological body in real time through event-driven operation; A result output module receives the closed geological body and attribute data, stores the data and exports standardized geological modeling results; Among them, the data acquisition module outputs the three-dimensional surface model to the scene construction module, the scene construction module outputs the visual scene data to the boundary processing module, the boundary processing module outputs the optimized stratum boundary to the geological body modeling module, the geological body modeling module outputs the closed geological body to the profile linkage module and the results output module, and the profile linkage module feeds back the profile modification event to the geological body modeling module in real time to trigger the three-dimensional model update.

[0006] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the data acquisition module: Generate initial point cloud data through dense matching of multi-view stereo algorithm; fusing the initial point cloud data, the digital elevation model, and the work area boundary to construct a three-dimensional surface model; The generated three-dimensional surface model is stored in blocks and the coordinate system is automatically converted.

[0007] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the scene construction module: After loading the three-dimensional surface model, switching the resolution of the model using a level of detail algorithm; parsing the lithologic attribute data and mapping the lithologic code to a color space; Based on the mapped lithology-color data distribution, the stratum lithology distribution thermodynamic map is displayed in real time.

[0008] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the boundary processing module: Using the three-dimensional surface model, aligning field measured points with an iterative closest point algorithm to generate corrected point cloud data; For the corrected point cloud data, a random sampling consensus algorithm is applied to remove abnormal nodes and generate an optimized point set; The optimized point set is used as surface fitting input, and a genetic algorithm is used to optimize and generate stratum boundaries.

[0009] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the geological body modeling module: Obtaining the optimized stratum boundary and generating a continuous stratum interface by an implicit surface reconstruction algorithm; Based on the continuous stratum interface, constrained triangulation is used to construct the topological structure of the top surface and the bottom surface; After fusing the work area boundary data, the lateral annular surfaces are stitched together to generate a closed geological body.

[0010] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the profile linkage module: After receiving the geological body, a graph neural network is called to analyze the trend of the stratum intersection lines in the cut section; Based on the stratum intersection trend, an image segmentation algorithm is used to extract the cross-sectional structural features; When a profile editing event is detected, the three-dimensional geological body is updated in real time by combining the profile construction features through sparse voxel hash mapping.

[0011] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the achievement output module: After receiving the geological body and attribute data, executing a consistency check algorithm between the stratum interface and the terrain data and outputting the check result; Reading the lithology code library in the attribute data to parse lithology pattern data; generating a histogram based on the verification result and the lithologic pattern data; The histogram is integrated with the three-dimensional geological body model data to output a geological report with hyperlinks.

[0012] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the optimized point set generated by the boundary processing module is filtered out by a random sampling consensus algorithm to output a clean stratum boundary to the geological body modeling module; The geological body modeling module completes implicit surface reconstruction based on the clean stratum boundary and generates stratum interface curvature characteristic data; The formation interface curvature characteristic data is fed back to the genetic algorithm optimization link of the boundary processing module to dynamically adjust the surface fitting weight parameters.

[0013] Furthermore, in the oblique photography three-dimensional surface model geological modeling system of the present invention, a user drags a stratum boundary node in the two-dimensional section view of the section linkage module to trigger a topology reconstruction event captured by an event listener; The topology reconstruction event carries a node displacement vector, driving the geological body modeling module to call a sparse voxel hash mapping method to update the three-dimensional stratum interface; After the formation morphology is corrected in real time based on the cross-sectional structural features, the synchronization delay is controlled to the millisecond level.

[0014] In a second aspect, the present invention provides a method for geological modeling of a three-dimensional surface model using oblique photography, which is applied to the aforementioned three-dimensional surface model geological modeling system using oblique photography, and includes: Step 1: Obtain oblique photography images and terrain data, and generate a three-dimensional surface model using a structure-from-motion algorithm; Step 2: receiving the three-dimensional surface model, loading the model data, and dynamically rendering the three-dimensional scene according to the spatial coordinates and lithologic properties; Step 3: receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; Step 4, receiving the stratigraphic boundary, generating a continuous stratigraphic interface and topologically processing a closed geological body structure; Step 5: receiving the closed geological body, cutting the closed geological body to generate a cross-section, and synchronizing the cross-section with the closed geological body in real time through event-driven operation; Step 6: Receive the closed geological body and attribute data, store the data and derive standardized geological modeling results.

[0015] Beneficial effects of the present invention: The present invention directly generates a three-dimensional surface model in OSGB format through native fusion processing of oblique photography images and terrain data, replacing manual field mapping and compressing the data acquisition cycle; the built-in motion recovery structure algorithm and multi-view stereo matching engine realize the integrated processing from original images to three-dimensional models, skipping the format conversion link of third-party tools such as ArcGIS, and avoiding the fragmentation of modeling process; combining random sampling consensus algorithm with genetic optimization to automatically generate stratigraphic boundaries, significantly reducing the amount of manual correction operations; local incremental updates are achieved through sparse voxel hash mapping technology, and the event-driven mechanism feeds back the section node displacement to the three-dimensional geological body in real time. The millisecond-level synchronization delay breaks through the technical bottleneck of traditional two- and three-dimensional model separation and update, improving geological interpretation efficiency and model interaction experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0017] Figure 1 This is a flow chart of a method for geological modeling of a three-dimensional surface model using oblique photography provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The technical solutions provided by each embodiment of the present invention are described in detail below in conjunction with the drawings. In order to better understand the purpose of the present invention, the present invention is further described in detail below.

[0019] In a first aspect, the present invention provides a three-dimensional surface model geological modeling system for oblique photography, comprising: The data acquisition module acquires oblique photography images and terrain data, and generates a three-dimensional surface model using a structure-from-motion algorithm; A scene construction module receives the three-dimensional surface model, loads the model data, and dynamically renders the three-dimensional scene according to the spatial coordinates and lithologic properties; a boundary processing module, receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; A geological body modeling module receives the stratum boundary, generates a continuous stratum interface and topologically processes a closed geological body structure; A profile linkage module receives the closed geological body, cuts the closed geological body to generate a profile, and synchronizes the profile with the closed geological body in real time through event-driven operation; A result output module receives the closed geological body and attribute data, stores the data and exports standardized geological modeling results; Among them, the data acquisition module outputs the three-dimensional surface model to the scene construction module, the scene construction module outputs the visual scene data to the boundary processing module, the boundary processing module outputs the optimized stratum boundary to the geological body modeling module, the geological body modeling module outputs the closed geological body to the profile linkage module and the results output module, and the profile linkage module feeds back the profile modification event to the geological body modeling module in real time to trigger the three-dimensional model update.

[0020] The data acquisition module first acquires surface imagery using an unmanned aerial vehicle (UAV) equipped with a multi-angle oblique camera, integrating digital elevation models and work area boundary vector information. A structure-from-motion algorithm is used to resolve the image pose and generate a sparse point cloud. Multi-view stereo dense matching is then used to construct a high-density point cloud. The point cloud undergoes texture mapping to generate a 3D surface model in OSGB / S3C format. This is then stored in multi-scale blocks using a quadtree index, automatically converting between WGS84 / UTM / model coordinates. This module directly outputs the textured 3D surface model to the scene construction module, eliminating the need for format conversion in third-party tools like ArcGIS in traditional workflows.

[0021] After receiving the 3D surface model data, the scene construction module dynamically schedules model tiles based on a block loading mechanism. A level-of-detail algorithm automatically switches model resolution based on viewpoint distance, enabling real-time lightweight rendering. The module reads the chronostratigraphic information recorded in the lithology coding attribute table, associates it with a predefined lithology-color mapping table, and maps different lithology codes to the HSV color space. GPU parallel computing generates a lithology distribution heat map, which is overlaid on the 3D surface model to visualize the spatial distribution of geological lithologies. The module outputs visualization scene data containing spatial coordinates and lithology color mappings, providing an operational interface for capturing stratigraphic boundaries.

[0022] The boundary processing module uses the visualized scene data to launch an interactive boundary drawing tool on the 3D model surface. Using an iterative closest point algorithm, the field-measured GPS point cloud is aligned with the oblique photography model surface point cloud, correcting for spatial positioning deviations to generate corrected point cloud data. A random sampling consensus algorithm dynamically detects and removes outlier nodes that deviate from the trend line, outputting an optimized point set. A genetic algorithm is used to optimize the weights of NURBS surface control points, fitting and generating smooth, continuous stratigraphic boundaries and binding age codes to lithologic attributes. The optimized stratigraphic boundary data is then transferred to the geological body modeling module, replacing the traditional manual mapping method of collecting 2D drawings.

[0023] After receiving the stratigraphic boundary point set, the geological volume modeling module uses an implicit surface reconstruction algorithm to generate a continuous stratigraphic interface triangulation. Constrained Delaunay triangulation is used to establish the topological relationship between the stratigraphic top and bottom surfaces, integrating the work area boundary polygon data. Boolean operations are applied to trim redundant triangular facets and automatically stitch lateral rings to form a closed geological volume structure. The module outputs a binary mesh file containing XML metadata, supporting cross-project reuse of complex structures such as anticlines and synclines. The generated closed geological volume is then synchronously transmitted to the profile linkage module and the output module.

[0024] The Profile Linkage module performs arbitrary cuts on closed geological bodies and uses a graph neural network to analyze stratigraphic intersection trends along the profile direction. A U-Net image segmentation algorithm is used to identify fault traces and lithologic boundary features within the profile image. When a user drags a stratigraphic intersection node in the 2D profile view, an event listener captures the displacement vector and triggers a topology reconstruction event. Sparse voxel hash mapping technology is used to update the 3D geological interface triangulation in real time, maintaining topological consistency in the 2D and 3D models. Profile modification data is fed back to the geological modeling module in real time to drive model updates.

[0025] The output module verifies the elevation consistency of stratigraphic interfaces with topographic data, detecting and marking areas of spatial conflict between geological interfaces and the DEM. It parses pattern template data from the lithologic coding library and automatically populates histogram lithologic symbols. Verification results, histogram data, and 3D geological models are integrated to generate a PDF geological report with hyperlinks to the model. The work area directory and attribute library are linked together, and standardized data output in GRD grid and XYZ point cloud formats supports resource exploration and environmental assessment decision-making applications.

[0026] Specifically, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the data acquisition module: Generate initial point cloud data through dense matching of multi-view stereo algorithm; fusing the initial point cloud data, the digital elevation model, and the work area boundary to construct a three-dimensional surface model; The generated three-dimensional surface model is stored in blocks and the coordinate system is automatically converted.

[0027] Initial point cloud data is generated using a five-lens oblique camera to capture multi-angle surface images. Structure-from-motion algorithms are used to calculate image pose parameters, generating a sparse point cloud foundation. Based on multi-view stereo matching principles, pixel-level disparity calculations are performed between adjacent images. A semi-global matching algorithm is used to optimize depth map generation, gradually expanding the data into a high-density 3D point cloud. This point cloud retains the original image texture information, providing the geometric and textural foundation for constructing a 3D surface model.

[0028] To construct a 3D surface model, the initial point cloud data was spatially overlaid with the digital elevation model. Gaussian filtering was used to eliminate point cloud noise and match terrain elevation trends. A vector file of the work area boundary was loaded, and the point cloud elevation data was fused with the terrain data using the Kriging spatial interpolation algorithm to generate a continuous surface. A topologically connected triangular mesh was constructed based on the Poisson surface reconstruction principle. The model was mapped using image texture coordinates, and the resulting 3D surface model was output in the georeferenced OSGB format.

[0029] Model Storage and Coordinate Conversion: A spatial octree is used to partition the 3D surface model, dividing it into spatial tiles based on a preset resolution threshold. Tiles of varying scales are organized using a pyramidal hierarchical storage structure, and a tile spatial index file is created to record spatial location metadata. The coordinate conversion engine is used to parse the model's built-in coordinate system parameters. Using the seven-parameter Bursa transformation model, automatic conversion between WGS84 geodetic coordinates, UTM projected coordinates, and the local model coordinate system is achieved, supporting cross-coordinate system data access.

[0030] Specifically, the oblique photography three-dimensional surface model geological modeling system of the present invention, the scene construction module: After loading the three-dimensional surface model, switching the resolution of the model using a level of detail algorithm; parsing the lithologic attribute data and mapping the lithologic code to a color space; Based on the mapped lithology-color data distribution, the stratum lithology distribution thermodynamic map is displayed in real time.

[0031] Dynamic model resolution management: After loading a 3D surface model in OSGB format, a level-of-detail algorithm is used to adaptively switch model resolution based on the spatial relationship between the viewpoint and the model surface. As the viewpoint distance increases, low-resolution model tiles are automatically dispatched to replace high-precision tiles; as the viewpoint approaches the surface, the high-precision tiles are switched in reverse. A quadtree spatial index structure is used to manage model tile files at different levels, and frustum clipping is used to remove model data outside the field of view. This process utilizes GPU instanced rendering technology to achieve a smooth transition in model accuracy, ensuring visual quality while optimizing video memory usage.

[0032] Lithologic attribute data parsing accesses an attribute database linking geological age to lithology. This database stores stratigraphic unit age codes (e.g., P1 for the Permian) and lithologic codes (e.g., T003 for sandstone). Regular expressions are used to parse the attribute field structure and extract the mapping between lithologic codes and spatial coordinates. The HSV color space conversion model is used to map lithologic codes to predetermined hue ranges, where hue corresponds to lithologic category, saturation reflects lithologic purity, and lightness correlates to stratigraphic age. A lookup table is then created to convert lithologic codes to color vectors, providing the data foundation for 3D scene colorization.

[0033] Real-time lithologic heatmap generation spatially overlays color mapping results with vertex data of a 3D surface model, interpolating lithologic color values ​​onto the model surface via a fragment shader. A Gaussian kernel density estimation algorithm is used to calculate lithologic density per unit area, dynamically adjusting color transparency and brightness based on the density. Screen-space ambient occlusion enhances the visual depth of terrain relief, ultimately generating a heatmap reflecting the spatial distribution of lithologic features within the 3D scene. This heatmap updates in real time with changing viewing angles, enabling geologists to intuitively analyze regional lithologic distribution patterns.

[0034] Specifically, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the boundary processing module: Using the three-dimensional surface model, aligning field measured points with an iterative closest point algorithm to generate corrected point cloud data; For the corrected point cloud data, a random sampling consensus algorithm is applied to remove abnormal nodes and generate an optimized point set; The optimized point set is used as surface fitting input, and a genetic algorithm is used to optimize and generate stratum boundaries.

[0035] Dynamic model resolution control: After loading the 3D surface model, a level-of-detail algorithm is used to manage model accuracy based on the distance between the viewpoint and the model surface. When the viewpoint is far from the target area, low-resolution model tiles are dispatched; when the viewpoint approaches, high-precision tiles are switched. Model data at different levels is organized using a quadtree spatial index, and tiles within the visible range are dynamically loaded using frustum clipping. GPU instanced rendering technology is used to achieve a smooth transition in model accuracy, maintaining visual quality while optimizing system resource usage.

[0036] Lithologic attribute data conversion reads an attribute database linking geological time and lithologic characteristics and analyzes the mapping between stratigraphic age codes and lithologic codes. The HSV color model is used to convert lithologic codes into visual parameters: hue corresponds to lithologic type, saturation indicates the purity of lithologic components, and lightness correlates to stratigraphic age sequence. A lookup table is created to convert lithologic codes to HSV vectors, generating color space mapping rules that provide the data basis for 3D model surface coloring.

[0037] The lithologic distribution heatmap generation process overlays color mapping results onto the 3D surface model. The fragment shader in the graphics rendering pipeline then interpolates the lithologic color values ​​onto the model's triangles. A kernel density estimation algorithm is used to analyze the lithologic distribution frequency per unit area, dynamically adjusting color transparency and brightness based on the density value. Screen-space ambient occlusion technology is also incorporated to enhance the visual depth of undulating terrain, ultimately generating a heatmap reflecting the spatial distribution characteristics of lithologic features. This heatmap updates in real time with changing viewing angles, enabling geologists to intuitively identify lithologic distribution patterns within 3D scenes.

[0038] Specifically, the oblique photography three-dimensional surface model geological modeling system of the present invention, the geological body modeling module: Obtaining the optimized stratum boundary and generating a continuous stratum interface by an implicit surface reconstruction algorithm; Based on the continuous stratum interface, constrained triangulation is used to construct the topological structure of the top surface and the bottom surface; After fusing the work area boundary data, the lateral annular surfaces are stitched together to generate a closed geological body.

[0039] Continuous Stratum Interface Generation obtains optimized stratigraphic boundary point cloud data and processes the discrete point set using an implicit surface reconstruction algorithm. Local surface patches are fitted using the moving least squares principle, and adjacent patches are connected using radial basis function interpolation to generate a smooth, continuous stratigraphic interface triangulated mesh. This process preserves geological structural features within the stratigraphic boundary, such as the anticline axis or fault plane geometry, resulting in a three-dimensional surface structure that conforms to geological laws.

[0040] The topology of the top and bottom surfaces is constructed based on a continuous triangulated mesh of the stratigraphic interface, extracting the vertex set of the interface boundary as a constraint. A constrained Delaunay triangulation algorithm is applied to generate a topologically connected triangular facet network within the stratigraphic interface. Triangle quality is optimized using the minimum angle maximization criterion to construct the topological structure of the stratigraphic top and bottom surfaces. This topological network records vertex-edge-face adjacency relationships, providing a mathematical foundation for expressing spatial relationships in geological volumes.

[0041] To generate a closed geological volume, load the work area boundary vector polygon data and project it onto the horizontal datum plane of the stratigraphic interface. A polygon clipping algorithm is used to cut redundant triangular facets around the stratigraphic interface, aligning the interface boundary with the work area boundary. A boundary stitching algorithm is used to generate lateral triangular facets along the cut edges, connecting the top and bottom faces to form a closed annular side surface. Vertex normal consistency is used to correct the triangular facet orientation, ultimately outputting a closed geological volume mesh model with a complete bounding box.

[0042] Specifically, the oblique photography three-dimensional surface model geological modeling system of the present invention, the profile linkage module: After receiving the geological body, a graph neural network is called to analyze the trend of the stratum intersection lines in the cut section; Based on the stratum intersection trend, an image segmentation algorithm is used to extract the cross-sectional structural features; When a profile editing event is detected, the three-dimensional geological body is updated in real time by combining the profile construction features through sparse voxel hash mapping.

[0043] After receiving a closed geological mesh model, the stratigraphic intersection trend prediction system generates a geological profile along the user-specified cutting direction. A graph neural network model is used to construct a cross-sectional structure graph, with stratigraphic intersection nodes as graph vertices and topological connections between nodes as edges. Graph convolution operations aggregate the geological attributes of neighboring nodes to learn the spatial correlation between stratigraphic strike and dip. The system then outputs stratigraphic intersection extension trend predictions for uncovered areas, assisting in the construction of complete geological profiles.

[0044] Structural feature extraction for profiles is based on stratigraphic intersection trend data and uses an encoder-decoder image segmentation algorithm to process profile images. The encoder extracts multi-scale features such as fault lines and lithologic boundaries from the profile images through convolutional layers. The decoder fuses shallow texture information with deep semantic features to output pixel-level structural zoning results. Morphological optimization of the segmentation results is performed using prior geological knowledge to generate a structural feature map that annotates the relationships between fault traces and lithologic contacts.

[0045] Real-time 3D geological body updates establish an event monitoring mechanism to capture user interactions on 2D sections. When a stratigraphic intersection node drag event is detected, the node displacement vector and associated structural feature data are extracted. Sparse voxel hash mapping is used to locate the affected areas of the 3D geological body, and triangulation is performed only on the local voxel blocks. A parallel computation pipeline is used to update stratigraphic interface vertex coordinates, preserving the topology of unmodified areas. The 3D scene engine synchronously refreshes the visualization results, providing instant feedback on 2D and 3D linkage.

[0046] Specifically, the oblique photography three-dimensional surface model geological modeling system of the present invention, the achievement output module: After receiving the geological body and attribute data, executing a consistency check algorithm between the stratum interface and the terrain data and outputting the check result; Reading the lithology code library in the attribute data to parse lithology pattern data; generating a histogram based on the verification result and the lithologic pattern data; The histogram is integrated with the three-dimensional geological body model data to output a geological report with hyperlinks.

[0047] After receiving the closed geological mesh model and terrain data, the data consistency check detects elevation differences between the stratum interface vertices and the digital elevation model through spatial overlay analysis. A constrained Delaunay triangulation is used to construct the spatial topological relationship between the stratum interface and the terrain, and the vertical distance from the interface vertex to the terrain surface is calculated. Areas exceeding a preset threshold are marked as elevation conflicts, and verification results are generated, including the coordinates of the conflicting locations and the deviation values. This process ensures the spatial consistency of the geological model and the surface topography.

[0048] Lithology pattern data parsing reads the lithology code library from the attribute database and matches the lithology codes with predefined pattern templates. A vector graphics parsing algorithm is used to convert the pattern templates into fill path data in SVG format, preserving the geometric characteristics and proportional relationships of the lithology symbols. A mapping table is established from lithology codes to vector patterns, providing standardized graphic resources for filling lithology symbols in bar charts.

[0049] Histogram generation determines the vertical layering structure of the histogram based on the stratigraphic sequence information from the verification results. Based on the lithologic pattern data, vector lithologic symbols are populated in the corresponding stratigraphic intervals. A red, semi-transparent warning layer is overlaid on elevation conflict markers to highlight data anomalies through visual contrast. An automatic layout algorithm is used to adjust the bar width and legend position, generating a standardized histogram that complies with geological mapping standards.

[0050] The integrated geological report output spatially associates histograms with 3D geological models, embedding 3D model spatial coordinates at the stratigraphic locations within the histograms. Using a PDF document engine, the report includes verification results, lithologic legends, and hyperlinks to model coordinates. The output includes a comprehensive geological report with text descriptions, 2D charts, and quick access to the 3D model. It also supports one-click jumps to the corresponding 3D scene view of the geological body.

[0051] Specifically, in the oblique photography three-dimensional surface model geological modeling system of the present invention, the optimized point set generated by the boundary processing module is filtered out by a random sampling consensus algorithm, and then the clean stratum boundary is output to the geological body modeling module; The geological body modeling module completes implicit surface reconstruction based on the clean stratum boundary and generates stratum interface curvature characteristic data; The formation interface curvature characteristic data is fed back to the genetic algorithm optimization link of the boundary processing module to dynamically adjust the surface fitting weight parameters.

[0052] Clean Stratum Boundary Generation applies a random sampling consensus algorithm to the optimized point set output by the boundary processing module, performing a secondary filtering. By iteratively sampling subsets of the point set and evaluating the consistency of the inlier distribution, noise points that deviate from the trend line are removed. The plane equation is optimized using the least median square criterion, retaining valid data points within the confidence interval. The resulting spatially continuous point set, consistent with geological structural patterns, is then output to form clean stratigraphic boundary data free of outliers.

[0053] After receiving clean stratigraphic boundaries, the geological modeling module uses an implicit surface reconstruction algorithm to generate a smooth and continuous stratigraphic interface. The Gaussian and mean curvatures of each interface vertex are calculated using differential geometry algorithms to analyze the surface's concavity and convexity, as well as its degree of curvature. The distribution of curvature extreme points and the curvature gradient are extracted to quantify the spatial geometric properties of stratigraphic fold morphology and fault turning points, generating a curvature feature dataset containing a curvature scalar field and principal curvature directions.

[0054] Dynamic adjustment of genetic algorithm parameters feeds data on formation interface curvature characteristics into the genetic algorithm optimization phase of the boundary processing module. Geometric constraints within the curvature characteristics are analyzed, and a fitness function is constructed to evaluate the quality of surface fitting. The genetic algorithm's selection pressure coefficient is dynamically adjusted based on changes in the curvature gradient, increasing the weight of control points in areas with significant curvature variations. An adaptive mutation operator is used to optimize the distribution density of control points, ensuring that the subsequent formation boundary fitting process prioritizes the geological structural characteristics of areas with high curvature.

[0055] Specifically, in the oblique photography three-dimensional surface model geological modeling system of the present invention, a user drags a stratum boundary node in the two-dimensional section view of the section linkage module to trigger a topology reconstruction event captured by an event listener; The topology reconstruction event carries a node displacement vector, driving the geological body modeling module to call a sparse voxel hash mapping method to update the three-dimensional stratum interface; After the formation morphology is corrected in real time based on the cross-sectional structural features, the synchronization delay is controlled to the millisecond level.

[0056] Topology reconstruction events are captured within the human-computer interface of the 2D cross-section view, using a node displacement capture mechanism based on mouse event monitoring. When the user drags a stratigraphic boundary node, the graphical interface system records the screen coordinate displacement in real time and inversely calculates the 3D spatial displacement vector using the view matrix and projection matrix. The event listener encapsulates the displacement data into a topology reconstruction event object containing the node ID, displacement direction, and displacement amount, and pushes it to the event processing queue of the geological modeling module.

[0057] Upon receiving a topology reconstruction event, the sparse voxel hash map updating geobody modeling module locates the affected local region of the 3D geobody using the sparse voxel hash table. The displacement vector is decomposed into normal and tangential components, and the vertex positions are adjusted within the voxel block using the Laplace coordinate offset algorithm. Local triangulation is performed only on the voxel blocks within the displacement's impact radius, preserving the topology of the unmodified areas. A parallel computation pipeline is used to update the vertex buffer data of the affected voxel blocks, enabling incremental updates of the 3D stratigraphic interface.

[0058] Real-time stratigraphic morphology corrections, combined with structural feature data extracted by the profile linkage module, constrain the displacement area for geological plausibility. Curvature continuity and stratigraphic thickness constraints are used to optimize vertex distribution within the neighborhood of the moving node. A local parameterized surface fitting algorithm is used to smoothly transition modified boundaries, ensuring that the updated 3D stratigraphic interface maintains consistent geological structural characteristics. Through rendering frame rate control and computing resource scheduling, the system reduces the end-to-end latency from model update to visualization to millisecond response times.

[0059] See also Figure 1 In a second aspect, the present invention provides a method for geological modeling of a three-dimensional surface model using oblique photography, which is applied to the aforementioned three-dimensional surface model geological modeling system using oblique photography, and includes: Step 1: Obtain oblique photography images and terrain data, and generate a three-dimensional surface model using a structure-from-motion algorithm; Step 2: receiving the three-dimensional surface model, loading the model data, and dynamically rendering the three-dimensional scene according to the spatial coordinates and lithologic properties; Step 3: receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; Step 4, receiving the stratigraphic boundary, generating a continuous stratigraphic interface and topologically processing a closed geological body structure; Step 5: receiving the closed geological body, cutting the closed geological body to generate a cross-section, and synchronizing the cross-section with the closed geological body in real time through event-driven operation; Step 6: Receive the closed geological body and attribute data, store the data and derive standardized geological modeling results.

[0060] This method establishes a unified 3D surface model base through native fusion processing of oblique photography and terrain data. A structure-from-motion algorithm directly generates a textured model in OSGB format, replacing traditional manual field mapping data collection methods. The boundary processing module integrates an iterative closest point algorithm to align measured point clouds, combined with a random sampling consensus algorithm to automatically remove outliers, reducing manual correction operations by over 90%. A genetic algorithm optimizes the surface fitting process, enabling the automatic generation and attribute binding of stratigraphic boundaries, shortening the geological mapping cycle.

[0061] The data acquisition module features an embedded multi-view stereo dense matching and coordinate conversion engine, enabling integrated processing from raw imagery to 3D surface models. It employs a block storage strategy and quadtree indexing to manage model tiles, natively supporting cross-platform calls in OSGB / S3C formats. The scene construction module directly loads the block model and associates it with a lithologic attribute library. Using a level-of-detail algorithm, it dynamically adjusts model accuracy, bypassing the format conversion and preprocessing steps typically required by third-party tools like ArcGIS, ensuring a consistent modeling workflow.

[0062] The cross-section linkage module combines geological body cutting operations with graph neural network prediction to establish a stratigraphic intersection trend analysis model. An event-driven mechanism captures 2D cross-section node displacement vectors and locates affected areas in the 3D model through sparse voxel hash mapping. Incremental triangulation is performed on localized voxel blocks, incorporating structural features to constrain geometric deformation. Topology update data is fed back to the geological body modeling module in real time, with end-to-end synchronization latency kept to milliseconds, breaking through the technical bottleneck of traditional software that requires separate updates of 2D and 3D models.

Claims

1. The three-dimensional surface model geological modeling system of oblique photography is characterized by: include: The data acquisition module acquires oblique photography images and terrain data, and generates a three-dimensional surface model using a structure-from-motion algorithm; A scene construction module receives the three-dimensional surface model, loads the model data, and dynamically renders the three-dimensional scene according to the spatial coordinates and lithologic properties; a boundary processing module, receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; A geological body modeling module receives the stratum boundary, generates a continuous stratum interface and topologically processes a closed geological body structure; A profile linkage module receives the closed geological body, cuts the closed geological body to generate a profile, and synchronizes the profile with the closed geological body in real time through event-driven operation; A result output module receives the closed geological body and attribute data, stores the data and exports standardized geological modeling results; Among them, the data acquisition module outputs the three-dimensional surface model to the scene construction module, the scene construction module outputs the visual scene data to the boundary processing module, the boundary processing module outputs the optimized stratum boundary to the geological body modeling module, the geological body modeling module outputs the closed geological body to the profile linkage module and the results output module, and the profile linkage module feeds back the profile modification event to the geological body modeling module in real time to trigger the three-dimensional model update.

2. The oblique photography 3D surface model geological modeling system according to claim 1, characterized in that: The data acquisition module: Generate initial point cloud data through dense matching of multi-view stereo algorithm; fusing the initial point cloud data, the digital elevation model, and the work area boundary to construct a three-dimensional surface model; The generated three-dimensional surface model is stored in blocks and the coordinate system is automatically converted.

3. The oblique photography 3D surface model geological modeling system according to claim 2, characterized in that: The scene building blocks: After loading the three-dimensional surface model, switching the resolution of the model using a level of detail algorithm; parsing the lithologic attribute data and mapping the lithologic code to a color space; Based on the mapped lithology-color data distribution, the stratum lithology distribution thermodynamic map is displayed in real time.

4. The oblique photography 3D surface model geological modeling system according to claim 3, characterized in that: The boundary processing module: Using the three-dimensional surface model, aligning field measured points with an iterative closest point algorithm to generate corrected point cloud data; For the corrected point cloud data, a random sampling consensus algorithm is applied to remove abnormal nodes and generate an optimized point set; The optimized point set is used as surface fitting input, and a genetic algorithm is used to optimize and generate stratum boundaries.

5. The oblique photography 3D surface model geological modeling system according to claim 4, characterized in that: The geological body modeling module: Obtaining the optimized stratum boundary and generating a continuous stratum interface by an implicit surface reconstruction algorithm; Based on the continuous stratum interface, constrained triangulation is used to construct the topological structure of the top surface and the bottom surface; After fusing the work area boundary data, the lateral annular surfaces are stitched together to generate a closed geological body.

6. The oblique photography 3D surface model geological modeling system according to claim 5, characterized in that: The profile linkage module: After receiving the geological body, a graph neural network is called to analyze the trend of the stratum intersection lines in the cut section; Based on the stratum intersection trend, an image segmentation algorithm is used to extract the cross-sectional structural features; When a profile editing event is detected, the three-dimensional geological body is updated in real time by combining the profile construction features through sparse voxel hash mapping.

7. The oblique photography 3D surface model geological modeling system according to claim 6, characterized in that: The achievement output module: After receiving the geological body and attribute data, executing a consistency check algorithm between the stratum interface and the terrain data and outputting the check result; Reading the lithology code library in the attribute data to parse lithology pattern data; generating a histogram based on the verification result and the lithologic pattern data; The histogram is integrated with the three-dimensional geological body model data to output a geological report with hyperlinks.

8. The oblique photography 3D surface model geological modeling system according to claim 7, characterized in that: The optimized point set generated by the boundary processing module is filtered out by a random sampling consensus algorithm, and then the clean stratum boundary is output to the geological body modeling module; The geological body modeling module completes implicit surface reconstruction based on the clean stratum boundary and generates stratum interface curvature characteristic data; The formation interface curvature characteristic data is fed back to the genetic algorithm optimization link of the boundary processing module to dynamically adjust the surface fitting weight parameters.

9. The oblique photography 3D surface model geological modeling system according to claim 6, characterized in that: The user drags a stratum boundary node in the two-dimensional section view of the section linkage module, triggering a topology reconstruction event captured by the event listener; The topology reconstruction event carries a node displacement vector, driving the geological body modeling module to call a sparse voxel hash mapping method to update the three-dimensional stratum interface; After the formation morphology is corrected in real time based on the cross-sectional structural features, the synchronization delay is controlled to the millisecond level.

10. A method for geological modeling of a three-dimensional surface model using oblique photography, applied to a geological modeling system for a three-dimensional surface model using oblique photography according to any one of claims 1 to 9, characterized in that: include: Step 1: Obtain oblique photography images and terrain data, and generate a three-dimensional surface model using a structure-from-motion algorithm; Step 2: receiving the three-dimensional surface model, loading the model data, and dynamically rendering the three-dimensional scene according to the spatial coordinates and lithologic properties; Step 3: receiving the visual scene data from the scene construction module, registering the field measurement points with the three-dimensional surface model, and optimizing the collected stratum boundaries; Step 4, receiving the stratigraphic boundary, generating a continuous stratigraphic interface and topologically processing a closed geological body structure; Step 5: receiving the closed geological body, cutting the closed geological body to generate a cross-section, and synchronizing the cross-section with the closed geological body in real time through event-driven operation; Step 6: Receive the closed geological body and attribute data, store the data and derive standardized geological modeling results.

Images