Vector data extraction method, device, equipment and medium based on high-fidelity scene

Abstract

The present application relates to a vector data extraction method, device, equipment and medium based on a high-fidelity scene. The method includes: extracting planar terrain entities from a high-fidelity scene and constructing a static mesh; and identifying the planar terrain entities, obtaining geometric information and attribute information in the corresponding static mesh components according to the identification name of the planar terrain entity and the polygon union method based on triangle thinning processing, and storing them in an intermediate file; parsing the attribute information and geometric information in the intermediate file, calling the vector engine interface, and converting the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion, and then storing the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system. The use of this method can improve the deduction operation rate of the intelligent unmanned combat deduction system.

Description

Technical Field

[0001] The present application relates to the technical field of data extraction, and in particular to a method, device, equipment and medium for extracting vector data based on a high-fidelity scene. Background Art

[0002] In order to solve the problems that the entire intelligent unmanned deduction system is too dependent on the Unreal Engine platform, the deduction operation rate is slow, the deduction system does not meet the localization requirements, and the two-dimensional and three-dimensional maps of the deduction process cannot be updated in real time. The closure algorithm extraction based on the Bezier curve is to store the points of the static mesh of the entity as a point set, and rely on the point set to obtain the circumscribed polygon, and then perform Bezier curve fitting to obtain the final polygon outline to obtain vector data. The traditional polygon-by-polygon union algorithm obtains the union of the projected static mesh one by one, that is, randomly selects 2 polygons in the polygon set to merge, and the obtained process polygon is then merged with the remaining other polygon, and so on, and the traversal is repeated until all polygons are merged one by one to obtain the final result. The algorithm uses the spatial aggregation function SDO_AGGR_UNION of Oracle Spatial 11gRelease 2 and the geomunion() function of the spatial object relational database Post-GIS to store the polygon set to be merged in the spatial data table, and then merges row by row from top to bottom until all polygons are merged. The polygon grouping and merging rule divides the polygon set into n threads evenly, and then calculates the union of each set of polygons and then calculates the union of each set of polygons to get the result. This method divides the spatial data table into at least 16 or more. Compared with simply merging one by one, the time cost can be saved by more than half.

[0003] However, the current disadvantage is that although the closure algorithm based on the Bezier curve can calculate the circumscribed polygon by fitting, it is easy to form a large area for the arc-shaped and block-shaped parts, and the fit with the original polygon outline is not high; the traditional polygon union algorithm obtains the polygon union one by one, with low calculation efficiency and high memory usage; even if the polygon grouping and union method improves efficiency through grouping, it is easy to have nested polygons and more redundant nodes when projecting from a three-dimensional static mesh to two-dimensional data, which increases the complexity of subsequent merging. The entire intelligent unmanned combat simulation system is too dependent on the Unreal Engine platform, and the simulation calculation rate is low. Summary of the invention

[0004] Based on this, it is necessary to provide a vector data extraction method, device, equipment and medium based on high-fidelity scenarios that can improve the simulation calculation rate of the intelligent unmanned combat simulation system in response to the above-mentioned technical problems.

[0005] A vector data extraction method based on a high-fidelity scene, the method comprising:

[0006] Extracting planar ground object entities from a high-fidelity scene and constructing a static mesh; and marking the planar ground object entities, obtaining geometric information and attribute information in the corresponding static mesh components according to the identification name of the planar ground object entity and a polygon union method based on triangle thinning processing, and storing them in an intermediate file;

[0007] Parse the attribute information and geometric information in the intermediate file, call the vector engine interface, convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion, and then store the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0008] A vector data extraction device based on a high-fidelity scene, the device comprising:

[0009] The geometry and attribute information acquisition module is used to extract planar surface objects from high-fidelity scenes and construct static meshes; identify planar surface objects, and obtain the geometry and attribute information in the corresponding static mesh components according to the identification name of the planar surface objects and the polygon union method based on triangle thinning processing, and store them in the intermediate file;

[0010] The coordinate conversion module is used to parse the attribute information and geometric information in the intermediate file, call the vector engine interface, and convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion. The attribute information and geometric information are then stored in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0011] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0012] Extracting planar ground objects from high-fidelity scenes and constructing static meshes; marking planar ground objects, obtaining geometric information and attribute information in corresponding static mesh components according to the identification names of planar ground objects and the polygon union method based on triangle thinning, and storing them in intermediate files;

[0013] Parse the attribute information and geometric information in the intermediate file, call the vector engine interface, and convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geospatial coordinate conversion. Then store the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0014] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0015] Extracting planar ground objects from high-fidelity scenes and constructing static meshes; marking planar ground objects, obtaining geometric information and attribute information in corresponding static mesh components according to the identification names of planar ground objects and the polygon union method based on triangle thinning, and storing them in intermediate files;

[0016] Parse the attribute information and geometric information in the intermediate file, call the vector engine interface, and convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geospatial coordinate conversion. Then store the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0017] The above-mentioned vector data extraction method, device, equipment and medium based on high-fidelity scenes, this application reduces the data processing burden of individual soldier behavior decision analysis by making analysis and decision based on the extracted vector data on the localized platform, and the vector data memory is smaller than the three-dimensional entity model information, which promotes the localization process of the system and thus improves the computing speed. On the other hand, it ensures the real-time synchronization update of the two-dimensional and three-dimensional maps. The extracted vector data provides basic analysis data for the two-dimensional and three-dimensional maps, ensuring the Figure 1 It optimizes business processes such as 2D and 3D collaborative mapping, reduces time-consuming operations caused by map asynchrony, and improves overall data processing efficiency. At the same time, it provides the system with complete geographic spatial data support, realizes 2D and 3D linkage, and innovates 2D and 3D map synchronization update methods, avoiding the problems of traditional methods, optimizing processing procedures and display effects, and ultimately improving the computing speed of the deduction system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a vector data extraction method based on a high-fidelity scene in one embodiment;

[0019] Figure 2 A schematic diagram of a technical route in an embodiment;

[0020] Figure 3 A schematic diagram of a scene object in an embodiment; Figure 3 (a) represents the scene map, Figure 3 (b) Represents the static mesh image corresponding to the ground object;

[0021] Figure 4 A schematic diagram of grid vertex coordinate information storage in another embodiment;

[0022] Figure 5 A comparison diagram of polygons before and after merging in one embodiment; Figure 5(a) shows the image before polygon merging. Figure 5 (b) shows the graph after polygons are merged;

[0023] Figure 6 A comparison diagram of the extraction results before and after in one embodiment; Figure 6 (a) shows a sample image of a highly realistic 3D scene. Figure 6 (b) shows the result of two-dimensional vector data extraction;

[0024] Figure 7 A schematic diagram of storing geometric information of a ShapeFile file in an embodiment;

[0025] Figure 8 is a schematic diagram of a vector data extraction device based on a high-fidelity scene in an embodiment;

[0026] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] In one embodiment, Figure 1 As shown, a vector data extraction method based on a high-fidelity scene is provided, comprising the following steps:

[0029] Step 102, extracting planar ground object entities from the high-fidelity scene and constructing a static mesh; and identifying the planar ground object entities, obtaining geometric information and attribute information in the corresponding static mesh component according to the identification name of the planar ground object entity and the polygon union method based on triangle thinning processing, and storing them in an intermediate file.

[0030] A high-fidelity scene refers to a highly realistic virtual environment created using an Unreal Engine (such as Unreal Engine, UE for short), which is very close to the real world in terms of visual effects, physical simulation, lighting, and texture.

[0031] Vector data of surface features such as buildings, vegetation, water systems, and obstacles are extracted from highly realistic virtual scenes and updated to the battlefield environment database in real time to supplement and improve battlefield environment data resources, providing vector data resource support for battlefield environment calculation and analysis, real-time synchronous updating of two- and three-dimensional maps, etc.

[0032] Normally, there is no need to identify entities in the Unreal Engine, which results in the entities in the scene not containing the attribute information of the objects. Therefore, various objects need to be classified and identified before extraction. On the other hand, the Unreal Engine is based on the relative coordinate system (world coordinate system), while traditional geospatial data in real space are mostly displayed in the WGS84 coordinate system. Therefore, when the geospatial data is output, coordinate conversion or map registration is required. Before extracting vector data from a highly realistic virtual scene, common objects need to be classified and coded. The classification is shown in Table 1:

[0033] Table 1

[0034]

[0035] Therefore, the technical route for this application to achieve vector data extraction in high-fidelity scenes is as follows: Figure 2 As shown in the figure, the surface objects in the high-fidelity scene are extracted and static meshes are constructed, which accurately focuses on key data and avoids redundant processing of a large amount of irrelevant data. Figure 3 As shown, Figure 3 (a) represents the scene map, Figure 3 (b) represents the static mesh image corresponding to the object. The addition of object identification makes the data classification clear, which is convenient for subsequent rapid retrieval and call. Compared with the traditional polygon union algorithm, the polygon union method based on triangle thinning can effectively reduce the amount of data. Through reasonable thinning processing, unnecessary details are removed, the data structure is simplified, and the complexity of data processing is reduced when obtaining the geometry and attribute information of the corresponding static mesh component, thereby improving the calculation rate. Figure 4 Schematic diagram of mesh vertex coordinate information storage.

[0036] Step 104, parse the attribute information and geometric information in the intermediate file, call the vector engine interface, convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion, and then store the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0037] Through geospatial coordinate conversion, the local coordinate system (relative coordinate system) in the high-fidelity scene is converted into a projection coordinate system (WGS84 projection coordinate system), and the attribute information and geometric information are stored in the format of a geographic file (ShapeFile). The ShapeFile file includes .shp files (coordinate information (X, Y)), .dbf files (attribute information: feature type), .cpg files (encoding information: UTF-8), and .prj files (projection type, projection parameter settings). ShapeFile can load, display, and query geographic elements through the interface of open source GIS software, call the vector engine interface for geospatial coordinate conversion, and convert the local coordinate system into a projection coordinate system, making the interaction of data between different systems and modules smoother, avoiding the complex conversion and data mismatch caused by inconsistent coordinates. Storing attribute information and geometric information in the format of geographic files facilitates the call of the intelligent unmanned deduction system. The standardized data storage format allows the system to quickly locate and read the required data, reducing the time for data reading and parsing, thereby improving the computing speed. Figure 5 This is a comparison chart before and after polygon merging; Figure 5 (a) shows the image before polygon merging. Figure 5 (b) shows the graph after polygons are merged; Figure 6 This is a comparison chart before and after the extraction results; Figure 6 (a) shows a sample image of a highly realistic 3D scene. Figure 6 (b) shows the result of two-dimensional vector data extraction; Figure 7 Schematic diagram of storage of geometry information of ShapeFile files.

[0038] Current research focuses on building high-fidelity scenes from two-dimensional vector data. The present invention proposes for the first time to extract vector data from high-fidelity scenes, realize the extraction of geospatial data from high-fidelity scenes, provide more complete geospatial data resource support for intelligent unmanned confrontation deduction systems, realize the behavior decision-making of individual soldiers based on vector data analysis, and visualize the decision results in three-dimensional scenes. In a two-dimensional and three-dimensional linkage manner, the overall system deduction rate is improved, which is beneficial to the promotion of the localization of the later system; and for the first time, from the perspective of extracting vector data from high-fidelity scenes, the synchronous update of two-dimensional and three-dimensional maps is realized to ensure the consistency of two-dimensional and three-dimensional maps. This application constructs an efficient system from data extraction, processing to storage, providing high-quality data resources for the system. It gets rid of the excessive dependence on the Unreal Engine platform, making the system operation more autonomous and controllable. It provides a reliable data basis for the real-time synchronous update of two-dimensional and three-dimensional maps and the calculation and analysis of battlefield environment, optimizes the operation process of various businesses in the system, and comprehensively improves the deduction operation rate of the intelligent unmanned combat deduction system.

[0039] At the same time, the vector data extracted from the highly realistic scenes can be used for analysis and decision-making on the domestic platform, and the information memory is smaller than that of the three-dimensional solid model of the same level. Therefore, the behavioral decision-making analysis of a single soldier can get rid of the dependence on the Unreal Engine, promote the localization process of the system, and improve the computing speed of the deduction system; the extraction of vector data of highly realistic scenes can ensure the real-time synchronization update of the later two-dimensional vector map and the three-dimensional high-realistic scene map, ensure the consistency of the two-dimensional and three-dimensional maps, and provide basic analysis data for two-dimensional and three-dimensional collaborative mapping and other businesses; the extraction of vector data of highly realistic scenes can supplement and improve the battlefield environment data resources, and provide vector data resource support for battlefield environment calculation and analysis, real-time synchronization update of two-dimensional and three-dimensional maps, etc.

[0040] In the above-mentioned vector data extraction method based on high-fidelity scenes, this application reduces the data processing burden of individual soldier behavior decision analysis by making analysis and decision based on the extracted vector data on the localized platform, and the vector data memory is smaller than the three-dimensional entity model information, which promotes the localization process of the system and thus improves the computing speed. On the other hand, it ensures the real-time synchronization update of the two-dimensional and three-dimensional maps. The extracted vector data provides basic analysis data for the two-dimensional and three-dimensional maps, ensuring the accuracy of the map. Figure 1 It optimizes business processes such as 2D and 3D collaborative mapping, reduces time-consuming operations caused by map asynchrony, and improves overall data processing efficiency. At the same time, it provides the system with complete geographic spatial data support, realizes 2D and 3D linkage, and innovates 2D and 3D map synchronization update methods, avoiding the problems of traditional methods, optimizing processing procedures and display effects, and ultimately improving the computing speed of the deduction system.

[0041] In one embodiment, obtaining geometric information and attribute information in a corresponding static mesh component according to the identification name of the planar feature entity includes:

[0042] Read the model mesh vertex coordinate data (X, Y, Z) and store it in json format. Each static mesh component forms a corresponding coordinate data (X, Y, Z) file;

[0043] Remove the height information of each Static Mesh component and only keep the 2D coordinates (X, Y) of the Static Mesh component.

[0044] Perform a preliminary thinning process by projecting the Static Mesh component onto a grid plane, removing the triangles contained inside;

[0045] The algorithm for finding the union of polygonal patches after thinning is used to obtain the final polygon target vertex set and store it in an intermediate file.

[0046] In one embodiment, the attribute information is stored in the intermediate file according to the type of the planar surface feature entity; the types of the planar surface feature entity include buildings, obstacles, vegetation, water systems and roads.

[0047] In one embodiment, the algorithm for obtaining the final polygon target vertex set by performing the union of the polygon patches after the thinning process includes:

[0048] According to the fixed step size, the entire polygonal face is divided into several small areas. The polygonal boundaries participating in the operation in the small areas are decomposed into a series of directed line segments in a certain direction and a data structure is constructed to record the directed line segments and the polygons to which they belong. Starting from the bottom of the polygon, a virtual scan line is moved upward in the vertical direction to update the active edge table; the intersection and line segment information recorded in the active edge table during the scanning process is used to construct the polygonal boundaries after the union; for the fused polygons in each area, the intersection is calculated again to obtain the merged polygons in the entire area and obtain the final polygon target vertex set.

[0049] In one embodiment, starting from the bottom of the polygon, a virtual scan line is moved upward in a vertical direction to update the active edge table, including:

[0050] When the scan line encounters the starting point of a directed line segment, the directed line segment is placed in an "active edge table"; the active edge table is sorted according to the x-coordinate of the intersection with the scan line, and is used to record all line segments that intersect with the current scan line;

[0051] As the scan line moves, when the scan line encounters the intersection of two line segments, it is necessary to update the relevant information of the two line segments in the active edge table and re-sort the active edge table.

[0052] In one embodiment, the geographic file includes a coordinate information file, an attribute information file, a coding information file, and a projection type file.

[0053] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0054] In one embodiment, Figure 8As shown, a vector data extraction device based on a high-fidelity scene is provided, including: a geometry information and attribute information acquisition module 802 and a coordinate conversion module 804, wherein:

[0055] The geometry information and attribute information acquisition module 802 is used to extract planar surface objects from the high-fidelity scene and construct a static mesh; and to identify the planar surface objects, and to obtain the geometry information and attribute information in the corresponding static mesh components according to the identification name of the planar surface objects and the polygon union method based on triangle thinning processing, and store them in an intermediate file;

[0056] The coordinate conversion module 804 is used to parse the attribute information and geometric information in the intermediate file, call the vector engine interface, and convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion. Then, the attribute information and geometric information are stored in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

[0057] For the specific definition of the vector data extraction device based on high-fidelity scenes, please refer to the definition of the vector data extraction method based on high-fidelity scenes above, which will not be repeated here. Each module in the above-mentioned vector data extraction device based on high-fidelity scenes can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0058] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vector data extraction method based on a high-fidelity scene is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0059] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0060] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0061] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0062] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vector data extraction method based on a high-fidelity scene, characterized in that: The method comprises: Extracting planar ground object entities from a high-fidelity scene and constructing a static mesh; and marking the planar ground object entities, obtaining geometric information and attribute information in the corresponding static mesh components according to the identification name of the planar ground object entity and a polygon union method based on triangle thinning processing, and storing them in an intermediate file; Parse the attribute information and geometric information in the intermediate file, call the vector engine interface, convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion, and then store the attribute information and geometric information in the format of the geographic file to facilitate the intelligent unmanned deduction system to call; According to the identification name of the planar object entity, the geometric information and attribute information in the corresponding static mesh component are obtained, including: Read the model mesh vertex coordinate data (X, Y, Z) and store it in json format. Each static mesh component forms a corresponding coordinate data (X, Y, Z) file; Remove the height information of each Static Mesh component and only keep the 2D coordinates (X, Y) of the Static Mesh component. Perform a preliminary thinning process by projecting the Static Mesh component onto a grid plane, removing the triangles contained inside; The algorithm for finding the union of polygonal patches after thinning is used to obtain the final polygon target vertex set and store it in an intermediate file.

2. The method according to claim 1, characterized in that The method further comprises: The attribute information is stored in an intermediate file according to the type of the surface feature entity; the type of the surface feature entity includes buildings, obstacles, vegetation, water systems and roads.

3. The method according to claim 1, characterized in that The algorithm for finding the union of polygonal patches after thinning is used to obtain the final polygon target vertex set, including: According to the fixed step size, the entire polygonal face is divided into several small areas, and the polygonal boundaries participating in the operation in the small areas are decomposed into a series of directed line segments according to a certain direction, and a data structure is constructed to record the directed line segments and the polygons to which they belong. Starting from the bottom of the polygon, a virtual scan line is moved upward in the vertical direction to update the active edge table; the intersection and line segment information recorded in the active edge table during the scanning process is used to construct the polygonal boundaries after the union; for the fused polygons in each area, the intersection is calculated again to obtain the merged polygons in the entire area and obtain the final polygon target vertex set.

4. The method according to claim 3, characterized in that Starting from the bottom of the polygon, move a virtual scan line upward in the vertical direction to update the active edge table, including: When the scan line encounters the starting point of a directed line segment, the directed line segment is placed in an "active edge table"; the active edge table is sorted according to the x-coordinates of the intersection with the scan line, and is used to record all line segments that intersect with the current scan line; As the scan line moves, when the scan line encounters the intersection of two line segments, it is necessary to update the relevant information of the two line segments in the active edge table and re-sort the active edge table.

5. The method according to claim 1, characterized in that The geographic file includes a coordinate information file, an attribute information file, a coding information file and a projection type file.

6. A vector data extraction device based on a high-fidelity scene, characterized in that: The device comprises: The module for acquiring geometric information and attribute information is used to extract planar surface objects from a high-fidelity scene and construct a static mesh; and to identify the planar surface objects, and to obtain geometric information and attribute information in the corresponding static mesh component according to the identification name of the planar surface object entity and the polygon union method based on triangle thinning processing, and store them in an intermediate file; wherein, the module for acquiring geometric information and attribute information in the corresponding static mesh component according to the identification name of the planar surface object entity comprises: reading the model mesh vertex coordinate data (X, Y, Z) and storing it in json format, and each static mesh component forms a corresponding coordinate data (X, Y, Z) file; removing the height information of each static mesh component and retaining only the two-dimensional coordinates (X, Y) of the static mesh component; performing preliminary thinning processing by projecting the static mesh component onto a grid plane and removing the triangular facets contained inside; performing a union algorithm on the polygon facets after the thinning processing to obtain the final polygon target vertex set and store it in an intermediate file; The coordinate conversion module is used to parse the attribute information and geometric information in the intermediate file, call the vector engine interface, convert the local coordinate system in the high-fidelity scene into a projection coordinate system through geographic space coordinate conversion, and then store the attribute information and geometric information in the format of the geographic file for easy calling by the intelligent unmanned deduction system.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images