Geographic entity monomerization model generation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and provides a geographic entity monomerization model generation method and device, equipment and a storage medium, and the method comprises the steps: determining a missing region and a key region based on an oblique photography model of a target region and an existing monomerization result of the target region; based on the oblique photography model of the target area and the point cloud data of the target area, monotonized reconstruction is carried out on the geographic entities in the missing area, and monotonized reconstruction is carried out on the geographic entities in the key area according to the field supplementary photography of the key area and the oblique photography model of the key area; determining a target monomerization result of the target area based on the first monomerization result, the second monomerization result and the existing monomerization result; and performing fusion processing on the target monomer result and the oblique photography model after scene finishing to obtain a geographic entity monomer model of the target area. According to the invention, the efficiency of monomerized model generation is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating a single model of a geographic entity. Background Art

[0002] In today's society, 3D data generation has been widely used in many fields. For example, the construction industry needs to use 3D data to design and plan construction projects, and virtual reality technology can be used to achieve visualization and interactive operations; game development also needs to use 3D data to create game scenes and characters to improve the realism and fluency of the game.

[0003] The real-life 3D model is a digital reconstruction of the physical world, such as topography, land cover, and buildings, that uses remote sensing mapping, big data, cloud computing, and intelligent perception to truly express the digital reconstruction of the physical world. 3D real-life modeling (oblique photography technology) is a high-tech technology that has gradually developed in the field of international photogrammetry in recent years. Compared with the vertical photography data collected by traditional aerial surveys, it can simultaneously obtain high-resolution 3D images at multiple different angles at the same location. After rigorous aerial triangulation and solution, it finally outputs a high-resolution oblique real-life 3D model with real textures.

[0004] In the traditional artificial monomer model method, 3D modeling software is mainly used for artificial modeling. A 3D model without texture is established based on the real-life 3D model, and then artificial mapping is performed to display the real texture information of the ground object. This method has the problem of low efficiency in model generation. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a method, device, equipment and storage medium for generating a single model of a geographic entity, thereby improving the efficiency of generating the single model.

[0006] In a first aspect, the present invention provides a method for generating a single model of a geographic entity, the method comprising the following steps: Obtaining an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; Based on the oblique photography model of the target area and the existing individualization results of the target area, determining the missing areas in the existing individualization results, and determining the key areas in the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

[0007] According to a method for generating a single-unit model of a geographic entity provided by the present invention, the geographic entity in the missing area is single-unit reconstructed based on the oblique photography model of the target area and the point cloud data of the target area to obtain a first single-unit result of the missing area, including: According to the point cloud data of the target area, updating the surface texture and individualized change area of ​​the geographic entity in the missing area, to obtain a third individualization result of the missing area; By reshooting the missing area in the field, the surface texture in the third individualization result of the missing area is updated to obtain the first individualization result of the missing area.

[0008] According to a method for generating a single-unit model of a geographic entity provided by the present invention, the geographic entities in the key area include important building models, sculpture models and widget models; the geographic entities in the key area are single-unit reconstructed according to the field supplementary shooting of the key area and the oblique photography model of the key area to obtain a second single-unit result of the key area, including: According to the field supplementary photography of the key area and the oblique photography model of the key area, the important building model in the key area is reconstructed in a monomeric manner to obtain a fourth monomeric result of the important building model; According to the field supplementary photography of the key area and the oblique photography model of the key area, the sculpture model in the key area is reconstructed in a monomeric manner to obtain a fifth monomeric result of the sculpture model; Using a python script, the widget model in the key area is subjected to displacement processing; Based on the fourth individualization result of the important building model, the fifth individualization result of the sculpture model and the small component model after displacement processing, the second individualization result of the key area is determined.

[0009] According to a method for generating a single-unit model of a geographic entity provided by the present invention, the single-unit reconstruction of the important building model in the key area is performed based on the field supplementary shooting of the key area and the oblique photography model of the key area to obtain a fourth single-unit result of the important building model, including: Constructing a model structure of the important building model based on the oblique photography model of the key area and the ground photographic image of the key area, and generating a plain model of the important building model; Texture mapping is performed based on the plain model of the important building model to obtain the fourth monomerization result of the key area.

[0010] According to a method for generating a geographic entity monomer model provided by the present invention, before fusing the target monomer result of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity monomer model of the target area, the method comprises: The oblique photography model of the target area is subjected to geographic scene decoration to obtain a decorated oblique photography model of the target area.

[0011] According to a method for generating a single geographic entity model provided by the present invention, the step of performing geographic scene decoration on the oblique photography model of the target area to obtain the decorated oblique photography model of the target area comprises: Using model modification software to perform a modification operation on the oblique photography model of the target area; Among them, the finishing processing operation includes at least one of the following: deleting isolated suspended objects in the oblique photography model of the target area; performing 3D hole repair on the oblique photography model of the target area; removing damaged vehicles in the oblique photography model of the target area; performing model adhesion processing on the oblique photography model of the target area and performing model distortion processing on the oblique photography model of the target area.

[0012] According to a method for generating a geographic entity singularization model provided by the present invention, the method of determining a target singularization result of the target area based on the first singularization result of the missing area, the second singularization result of the key area, and the existing singularization result of the target area includes: Determine an updated oblique photography model of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The updated oblique photography model of the target area is physically cut using the vector plane of the single ground object target to obtain the target individualization result of the target area.

[0013] According to a method for generating a geographic entity monomer model provided by the present invention, the target monomer result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain the geographic entity monomer model of the target area, including: Based on the target singulation result of the target area and the oblique photography model of the target area after scene decoration, the geographic entity singulation model of the target area is singulated and encoded to obtain the encoded geographic entity; The encoded geographic entities are stored accordingly according to a preset storage structure to obtain a single geographic entity model of the target area; the single geographic entity model of the target area is a result data block in OSGB format and OBJ format.

[0014] In a second aspect, the present invention further provides a device for generating a single geographic entity model, the device comprising the following modules: An acquisition module is used to acquire an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; A generating module, for determining missing areas in the existing individualization results and determining key areas in the target area based on the oblique photography model of the target area and the existing individualization results of the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The fusion module is used to fuse the target individualization results of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity individualization model of the target area.

[0015] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating a single model of a geographic entity as described above is implemented.

[0016] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described XXXX methods.

[0017] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements a method for generating a single model of a geographic entity as described in any one of the above.

[0018] The method, device, equipment and storage medium for generating a single model of a geographic entity provided by the present invention first obtain an oblique photography model of a target area and an existing single result of the target area; the existing single result is a single model of a geographic entity of the target area generated within a preset historical time period; then, based on the oblique photography model of the target area and the existing single result of the target area, determine the missing area of ​​the existing single result, and determine the key area in the target area; further, based on the oblique photography model of the target area and the point cloud data of the target area, perform single reconstruction on the geographic entity in the missing area to obtain a first single result of the missing area, and based on the field supplementary shooting of the key area and the oblique photography model of the key area, perform single reconstruction on the geographic entity in the key area to obtain a second single result of the key area; based on the first single result of the missing area, the second single result of the key area and the existing single result of the target area, determine the target single result of the target area; then, fuse the target single result of the target area and the oblique photography model of the target area after scene decoration to obtain a single model of a geographic entity of the target area.

[0019] The present invention determines the missing areas and key areas of the existing individualized results based on the oblique photography model of the target area and the existing individualized results of the target area, and then performs individualized reconstruction on the missing areas, individualized reconstruction on the key areas, and refines the placement of the widget model to obtain the individualized results of the geographic entity of the target area. The individualized model of the geographic entity is finally generated in combination with the oblique photography model of the target area after scene decoration. The individualized processing of each region and the combination of the oblique photography model of the target area after scene decoration quickly generate a high-quality individualized model of the geographic entity, thereby improving the efficiency of individualized model generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of the method for generating a geographic entity monomer model provided by the present invention.

[0022] Figure 2 It is a schematic diagram of the principle of the method for generating a single model of a geographic entity provided by the present invention.

[0023] Figure 3 It is a structural schematic diagram of a device for generating a single geographic entity model provided by the present invention.

[0024] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0026] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally a class, and the number of objects is not limited. For example, the first node can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the front and back associated objects are in an "or" relationship.

[0027] Combine the following Figure 1-Figure 4 The invention describes a method, device, equipment and storage medium for generating a geographical entity monomer model.

[0028] Figure 1 It is a flow chart of the method for generating a geographic entity monomer model provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; Specifically, it should be noted that the execution subject of the present invention is an electronic device, which is used to improve the efficiency of generating a single model of a geographic entity.

[0029] First, obtain the oblique photography model of the target area and the existing individualization results of the target area, where the target area is the area where the geographic entity individualization model is to be generated. In the preparation stage, it is necessary to fully collect and organize the data, and after pre-processing operations such as conversion, form data that meet the needs of real-life three-dimensional construction. Among them, oblique photography model data such as three-dimensional scene models, aerial three-dimensional distortion-free images, and aerial three-dimensional data files. Oblique photography model data refers to the three-dimensional model data of geographic scenes obtained through oblique photography technology. Existing individualization results such as max and other three-dimensional formats can be obtained from historical databases.

[0030] The following is some key information about oblique photography model data: 1. Data format: The standard format for oblique photography data is OSGB format, which is a binary storage format with embedded linked texture data (.jpg). 2. The SGB data folder, a file with a .s3c suffix, and a metadata.xml file. The .s3c file is a project file and can be ignored; the Data folder stores three-dimensional data; the metadata.xml file stores coordinate system and coordinate value information. 3. Data acquisition: Oblique photography data can be obtained through some public channels, such as Cesium's official examples, S3Data star data management platform, Open Heritage 3D, OpenAerialMap (OAM), WingtraOne dataset, etc.

[0031] Based on the analysis of existing data in the target area, the existing results need to be converted and processed in accordance with data standards and then organized in a unified manner to form data that meets the needs of real-life three-dimensional construction.

[0032] Step 102: Based on the oblique photography model of the target area and the existing individualization results of the target area, determine the missing areas in the existing individualization results, and determine the key areas in the target area; Specifically, after obtaining the existing individualization results, the method of generating the individualization model of the geographic entity of the target area in this embodiment adopts the mode of incremental update + key area reconstruction.

[0033] First, identify the missing areas in the existing individualization results and the key areas in the target areas.

[0034] Among them, based on the oblique photography model of the target area and the existing individualization results of the target area, the missing areas of the existing individualization results, that is, the areas where the geographical entities that have not been individualized are located, can be determined.

[0035] Furthermore, key areas in the target area may be delineated and determined according to actual data requirements, for example, the area covered by core department A and the area covered by core department B.

[0036] Step 103: Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are individually reconstructed to obtain a first individualization result of the missing area, and based on the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are individually reconstructed to obtain a second individualization result of the key area; Specifically, the individual reconstruction process for the missing area is as follows: Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are individually reconstructed to obtain the first individualization result of the missing area. Among them, the point cloud data is generated by mounting a radar sensor while performing oblique photography, using the strong penetration of radar waves to synchronously generate the corresponding point cloud results (.las). It should be noted that since the shooting angle of the point cloud data result and the oblique photography 3D scene model result are similar, the time phase is the same, and the resolution of the point cloud data is low, it is only used as a reference material to supplement the texture of the covered area.

[0037] For example, the latest oblique photography three-dimensional scene model results are used first, and the surface texture and changed areas of the original individualized results are updated with reference to the point cloud data. Finally, the surface texture is improved through field re-shooting to obtain the first individualized results of the missing areas.

[0038] Furthermore, the individualization reconstruction process for the key areas is as follows: based on the field supplementary shooting of the key areas and the oblique photography model of the key areas, the geographic entities in the key areas are individually reconstructed to obtain the second individualization results of the key areas. For example, the oblique photography results are preferentially used for texture mapping, combined with the field supplementary shooting for detailed texture processing.

[0039] Step 104: Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; Specifically, after updating the individualization results of the missing areas and the key areas, the target individualization results of the target area are further determined based on the first individualization results of the missing areas, the second individualization results of the key areas and the existing individualization results of the target areas.

[0040] For example, based on the oblique photography data of the pilot area, three-dimensional geographic entities are reconstructed to build a multi-scale urban-level basic geographic entity model covering the main urban area, including but not limited to: reconstruction of geographic entities such as buildings and ancillary facilities, roads and ancillary facilities, key buildings and key areas, and integration with geographic scenes.

[0041] Step 105: The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

[0042] Specifically, after obtaining the target individualization results of the target area, the target individualization results of the target area and the oblique photography model of the target area after scene decoration are further fused, such as flattening fusion, to avoid duplicate data, etc., and finally a geographic entity individualization model of the target area can be generated.

[0043] For example, based on the Mesh model data, the model monomer data of the newly added houses and buildings is produced. According to the needs of real-life 3D construction, the monomer fine expression of the houses and buildings is divided into 1 to 4 levels of models. Based on the monomer results of the oblique photography model, the corresponding houses and buildings in the Mesh model are flattened to facilitate the fusion of the oblique photography monomer model and the Mesh model data.

[0044] The three-dimensional geographic entities of the ancillary facilities of key roads are reconstructed based on the Mesh model data, including but not limited to: buildings and ancillary facilities, walls, roads, viaducts, overpasses, bus stops, pedestrian bridges, trees, green vegetation and other entities, as well as street lights, power facilities, trash cans, traffic lights, manhole covers, road signs and other urban components. Based on the individualization results of the oblique photography model, the corresponding models in the Mesh model are flattened to facilitate the fusion of the individualized model and the Mesh model data.

[0045] Optionally, the method also includes completing confidentiality processing for geographic scenarios and geographic entity data based on a cryptographic service platform, so that confidential data and sensitive information are removed, and confidentiality and sensitive content cannot be restored through technical means.

[0046] The method provided in this embodiment first obtains the oblique photography model of the target area and the existing individualization results of the target area; then, based on the oblique photography model of the target area and the existing individualization results of the target area, determines the missing areas of the existing individualization results, and determines the key areas in the target area; further, based on the oblique photography model of the target area and the point cloud data of the target area, performs individualization reconstruction on the geographic entities in the missing area to obtain a first individualization result of the missing area, and based on the field supplementary shooting of the key area and the oblique photography model of the key area, performs individualization reconstruction on the geographic entities in the key area to obtain a second individualization result of the key area; based on the first individualization result of the missing area, the second individualization result of the key area and the existing individualization result of the target area, determines the target individualization result of the target area; and then, fuses the target individualization result of the target area and the oblique photography model of the target area after scene decoration to obtain a geographic entity individualization model of the target area.

[0047] The present invention determines the missing areas and key areas of the existing individualized results based on the oblique photography model of the target area and the existing individualized results of the target area, and then performs individualized reconstruction on the missing areas, individualized reconstruction on the key areas, and refines the placement of the widget model to obtain the individualized results of the geographic entity of the target area. The individualized model of the geographic entity is finally generated in combination with the oblique photography model of the target area after scene decoration. The individualized processing of each region and the combination of the oblique photography model of the target area after scene decoration quickly generate a high-quality individualized model of the geographic entity, thereby improving the efficiency of individualized model generation.

[0048] According to a method for generating a single-unit model of a geographic entity provided by the present invention, based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entity in the missing area is reconstructed in a single unit to obtain a first single unit result of the missing area, including: According to the point cloud data of the target area, the surface texture and individualized change area of ​​the geographic entities in the missing area are updated to obtain the third individualization result of the missing area; By reshooting the missing area in the field, the surface texture in the third monomerization result of the missing area is updated to obtain the first monomerization result of the missing area.

[0049] Specifically, in some embodiments, the specific implementation process of performing individual reconstruction of the geographic entities in the missing area based on the oblique photography model of the target area and the point cloud data of the target area in step 103 to obtain the first individualization result of the missing area includes the following steps: First, based on the point cloud data of the target area, the surface texture and individualized change area of ​​the geographic entity in the missing area are updated to obtain the third individualized result of the missing area. Furthermore, through field reshooting of the missing area, the surface texture in the third individualized result of the missing area is updated to obtain the first individualized result of the missing area.

[0050] For example, the missing areas of the existing individualized results are reconstructed individually, with the modeling level of level 4. The building structure is reconstructed based on the results of the oblique photography 3D scene model, and the texture mapping is preferentially used for the use of aerial three-dimensional distortion-free images. For the missing parts of the surface texture, point cloud data can be used to supplement, and the areas with severe occlusion are updated after outdoor supplementary shooting and collection. The specific steps include: 1. Reconstructing the geometric structure of the building, refining the editing structure, texture mapping and optimization, and attribute association. The attribute association process is achieved in the following way: According to the agreed coding rules, the attributes of each natural building entity are edited, and each monomer model is given a unique identification code.

[0051] Among them, the 3D model data can be divided into four levels of detail according to the different performance details: first-level model (fine model), second-level model (standard model), third-level model (simple model), and fourth-level model (block model). The classification table of real-life 3D monomer models is shown below1: Table 1:

[0052] The method provided in this embodiment performs individual reconstruction of geographic entities in the missing area based on the oblique photography model of the target area and the point cloud data of the target area, thereby achieving individual reconstruction of the missing area, facilitating the subsequent generation of an individual model of the geographic entities in the target area and improving model generation efficiency.

[0053] According to a method for generating a single-unit model of a geographic entity provided by the present invention, the geographic entities in the key area include important building models, sculpture models and widget models; the geographic entities in the key area are single-unit reconstructed according to the field supplementary shooting of the key area and the oblique photography model of the key area to obtain a second single-unit result of the key area, including: According to the field supplementary photography of the key areas and the oblique photography models of the key areas, the important building models in the key areas are reconstructed in a monomeric manner to obtain the fourth monomeric results of the important building models; According to the field supplementary photography of the key areas and the oblique photography model of the key areas, the sculpture model in the key areas is reconstructed in a monomeric manner to obtain the fifth monomeric result of the sculpture model; Through the Python script, the widget models in the key areas are displaced; Based on the fourth individualization results of the important architectural model, the fifth individualization results of the sculpture model and the small component model after displacement processing, the second individualization results of the key area are determined.

[0054] Specifically, in some embodiments, step 103 performs individual reconstruction of geographic entities in the key area based on the field supplementary photography of the key area and the oblique photography model of the key area, and the specific implementation process of obtaining the second individualization result of the key area includes the following steps: According to the field reshoots of key areas and the oblique photography models of key areas, the important building models in key areas are reconstructed in a monomeric manner to obtain the fourth monomeric results of the important building models. The modeling level is better than level 4. The building structure is reconstructed based on the results of the oblique photography 3D scene model. The texture mapping is preferentially performed using aerial triangulation distortion-free images. Point cloud data can be used to supplement the texture occlusion and missing parts. Areas with severe occlusion are updated after field reshoots. According to the actual situation of the scene, the small models of key roads and ancillary facilities are placed and textured. The sculpture models in the sculpture park are refined after manual reshoots and drone aerial photography. Simple geometric sculptures are created manually.

[0055] According to the field supplementary shooting of key areas and the oblique photography model of key areas, the sculpture models in key areas are reconstructed in monomers to obtain the fifth monomer results of the sculpture models. Based on the fourth monomer results of important architectural models, the fifth monomer results of sculpture models and the small parts model after displacement processing, the second monomer results of key areas are determined. The statues in the sculpture park are difficult to reconstruct in detail, with complex textures and insufficient basic data. At the beginning of the construction, we first conducted a field survey to find out the point coordinates, shape characteristics and surrounding environment of each statue, and then divided them according to the shape characteristics and surrounding environment: ① Statues with simple geometry and limited surrounding environment are not easy to carry out drone aerial photography due to low feature point extraction and correlation, and the oblique photography modeling effect is not good. We adopt the method of manual modeling and mapping; ② Statues with rich feature point extraction and open surrounding environment are processed by drone aerial photography and combined with manual video supplementary shooting to carry out close oblique photography fine three-dimensional modeling; ③ Models with complex structures are difficult to extract feature points and lack modeling details. In production, similar structure statue models are downloaded for editing and modification.

[0056] Through Python scripts, the small component models in key areas were displaced. As the statue was rich in details, it was very time-consuming to place it according to the point coordinates after the refined modeling was completed. We tried various methods and analyzed the data format. By writing Python scripts, we quickly realized the three-dimensional space rotation and translation of the three-dimensional statue model.

[0057] For example, by demarcating key areas, detailed model reconstruction and placement of small models are carried out, and the results of oblique photography are used for texture mapping, combined with field reshoots to process texture details.

[0058] The method provided in this embodiment performs individual reconstruction of the geographic entities in the key area based on the field supplementary shooting of the key area and the oblique photography model of the key area, and obtains the second individualization result of the key area, which facilitates the subsequent generation of the individualization model of the geographic entities in the target area and improves the model generation efficiency.

[0059] According to a method for generating a single-unit model of a geographic entity provided by the present invention, a single-unit reconstruction is performed on an important building model in a key area based on field supplementary shooting of the key area and an oblique photography model of the key area, and a fourth single-unit result of the important building model is obtained, including: Based on the oblique photography model of the key area and the ground photography images of the key area, the model structure of the important building model is constructed to generate the plain model of the important building model; Texture mapping is performed based on the plain models of important architectural models to obtain the fourth monomerization results of key areas.

[0060] Specifically, in some embodiments, step 103 performs monomer reconstruction on the important building model in the key area according to the field supplementary shooting of the key area and the oblique photography model of the key area, and obtains the fourth monomerization result of the important building model. The specific implementation process includes the following steps: First, the model structure of the important building model is constructed based on the oblique photography model of the key area and the ground photography image of the key area, and the plain model of the important building model is generated. For example, a large frame structure is first constructed according to the plan view and the section view, and then the external surface model is wrapped according to the internal frame, and the spline is extracted from the surface model to generate the external metal structure of the building, and then the plain model of the important building model is generated.

[0061] Then, texture mapping is performed based on the base model of the important building model to obtain the fourth monomerization result of the key area. After the structure is completed, it is necessary to paste the corresponding texture on this structure to make the map. The specific method is as follows: (1) Tiling the UV of the model that needs to be mapped. Repeat the pasting Figure 1 Generally used in repetitive structures such as concrete, stone, paint, and building facades, this texture UV grid uses Box UVW mapping according to the actual display ratio required, and repeats the texture in a tiling manner. Figure 1It is generally applied to window objects of architectural models. For night scenes, it is necessary to expand the UV grid of the second channel separately for glass curtain walls and glass models of general buildings, and lay them flat in the UV layout box. In the later 3D engine, use the Mask texture to filter its luminous effect. (2) Render and output the UV coordinate map, import it into Photoshop software to make a map texture, and finally paste it on the 3D model for effect display. After the structure and map are completed, export the model results in 3D data format suitable for display on platforms such as OSGB, OBJ, and MAX, that is, obtain the fourth monomerization results of the key areas.

[0062] The method provided in this embodiment first constructs the model structure of the important building model based on the oblique photography model of the key area and the ground photographic image of the key area, and generates a plain model of the important building model; then, texture mapping is performed based on the plain model of the important building model to obtain the fourth monomerization result of the key area, which is convenient for the subsequent generation of the geographic entity monomerization model of the target area and improves the model generation efficiency.

[0063] According to a method for generating a geographic entity monomer model provided by the present invention, before fusing the target monomer result of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity monomer model of the target area, the method includes: The oblique photography model of the target area is subjected to geographic scene dressing to obtain the dressed oblique photography model of the target area.

[0064] Specifically, in some embodiments, before step 105, the method further includes: performing geographic scene finishing on the oblique photography model of the target area to obtain a finished oblique photography model of the target area. The purpose of geographic scene finishing is to improve the accuracy and authenticity of the oblique photography model, so that it is more in line with the actual geographical environment, thereby meeting various application requirements, such as urban planning, disaster management, tourism and other fields. Through these finishing works, the quality and availability of the model data can be ensured, providing users with more accurate and reliable geographic information.

[0065] Geographic scene decoration mainly involves the following aspects: 1. Model modification: including structural modification and texture modification. Structural modification mainly corrects the model's suspended matter, distortion, graffiti, deformation, adhesion, holes and other problems. Texture modification mainly adjusts the model's color, brightness, contrast and texture blur, dislocation, distortion, deformation and other problems.

[0066] 2. Refined processing: Refine the generated 3D model according to specific needs, including texture mapping, surface smoothing, mapping, etc., to improve the quality and visual effect of the model.

[0067] 3. Model bug repair: Repair model bugs, uneven terrain, color changes and other problems in real-life 3D models.

[0068] 4. Texture geometry mismatch processing: Solve the problem of inconsistency between texture and geometric information in the model, and ensure that the texture of the model matches the geometric shape of the actual object.

[0069] 5. Improved refinement of important buildings: For important buildings, more refined model replacements are performed to improve the details and realism of the models.

[0070] 6. Joint air-ground control: To address the problem of uneven geometric accuracy in densely populated areas of urban high-rise buildings, an air-ground joint image control point optimization solution is adopted to conduct point accuracy analysis on the generated real-scene 3D model.

[0071] The method provided in this embodiment performs geographic scene decoration on the oblique photography model of the target area to obtain the decorated oblique photography model of the target area, and then fuses the decorated oblique photography model of the target area with the target individualization results to obtain a geographic entity individualization model with high data quality.

[0072] According to a method for generating a single geographic entity model provided by the present invention, a geographic scene decoration is performed on an oblique photography model of a target area to obtain the decorated oblique photography model of the target area, comprising: Use model modification software to perform trimming operations on the oblique photography model of the target area; Among them, the finishing processing operation includes at least one of the following: deleting isolated suspended objects in the oblique photography model of the target area; performing 3D hole repair on the oblique photography model of the target area; removing damaged vehicles in the oblique photography model of the target area; performing model adhesion processing on the oblique photography model of the target area and performing model distortion processing on the oblique photography model of the target area.

[0073] Specifically, in some embodiments, the specific implementation process of performing geographic scene decoration on the oblique photography model of the target area to obtain the decorated oblique photography model of the target area includes the following steps: The oblique photography model of the target area is shaped and processed using model modification software. Model modification software is mainly used for post-modification of the oblique photography 3D scene real-life model results, such as PIE-Modeler software. The main contents of the modification work include: 3D vulnerability repair, model distortion processing, texture loss repair, model adhesion processing, deletion of isolated suspended objects, removal of damaged vehicles and pedestrians on important roads, and single entity construction such as traffic lights at intersections.

[0074] Among them, 1) the overall requirements for geographic scene finishing: the model texture tone is consistent, uniform, and without mosaic marks; the model is clear and cannot have obvious deformation, holes, or be inconsistent with reality.

[0075] 2) Traffic: Manual processing is performed on the obstructed areas, and the linear model structure of the road and its ancillary facilities is consistent with the actual situation, and there should be no obvious unevenness or deformation. There should be no vehicles or pedestrians on the key roads, and no obvious unevenness.

[0076] 3) Independent objects: Check independent objects such as electric poles, light poles, communication poles, billboards with a diameter less than 0.5 meters or a thickness less than 0.5 meters, and directly delete the hanging parts.

[0077] 4) Vegetation: Vegetation models are generally not processed. The main purpose is to delete the independent and unsupported parts with a diameter of less than 1 meter, and make the rows of trees tend to be natural.

[0078] 5) Topography: truly reflects the terrain undulations, surface morphology, texture, color, texture and other characteristics.

[0079] 6) Others: Holes that are inconsistent with reality are not allowed on the model surface, such as water surface, glass curtain wall, etc., and need to be repaired.

[0080] 7) Fusion model: The detail hierarchy should be balanced with the monomer model of the reconstructed 3D model.

[0081] The method provided in this embodiment uses model modification software to perform finishing operations on the oblique photography model of the target area, thereby improving the accuracy and authenticity of the oblique photography model, making it more consistent with the actual geographical environment, and facilitating the subsequent generation of a geographic entity monomer model of the target area. The monomer model has higher model accuracy.

[0082] According to a method for generating a geographic entity unitization model provided by the present invention, based on the first unitization results of the missing area, the second unitization results of the key area and the existing unitization results of the target area, a target unitization result of the target area is determined, including: Based on the first individualization results of the missing areas, the second individualization results of the key areas, and the existing individualization results of the target areas, an updated oblique photography model of the target areas is determined; The vector surface of the single object target is used to physically cut the oblique photography model of the updated target area to obtain the target individualization result of the target area.

[0083] Specifically, in some embodiments, step 104 may be implemented by the following steps: Based on the first individualization result of the missing area, the second individualization result of the key area and the existing individualization result of the target area, an updated oblique photography model of the target area is determined.

[0084] Furthermore, the vector plane of the individual ground object target can be used to physically cut the updated oblique photography model of the target area to obtain the target individualization result of the target area, and then the target individualization result of the target area.

[0085] Among them, singularization means turning each object that we want to manage separately into a separate entity that can be selected. These entities can be displayed in different colors (highlighted), have additional attributes, and can be queried and counted. 3D model singularization is to construct geographic entities into independent objects in 3D form through the processing of geographic scenes such as oblique photography 3D models and laser point clouds, which can be independently expressed, attached with attributes, and queried, counted, and analyzed.

[0086] The singulation method adopted in this embodiment is logical singulation. Logical singulation includes vector cutting singulation and vector marking singulation. Vector cutting singulation uses the vector surface of the single object to physically cut the overall model to achieve singulation. Vector marking singulation achieves the effect of selecting a single three-dimensional model by clicking the attributes of the vector layer on the two-dimensional surface. In the present invention, the vector surface of each object is used to cut the overall model, and each independent object is obtained by cutting. Then, the association is performed in three dimensions to separate the geographic entities (such as buildings, roads, trees, etc.) from the overall three-dimensional model and construct them into independent objects that can be managed and operated separately.

[0087] The method provided in this embodiment uses logical singulation to singulate the oblique photography model of the updated target area to generate a geographic entity singulated model with high generation efficiency.

[0088] According to a method for generating a geographic entity monomer model provided by the present invention, a target monomer result of a target area and an oblique photography model of the target area after scene decoration are fused to obtain a geographic entity monomer model of the target area, including: Based on the target individualization results of the target area and the oblique photography model of the target area after scene decoration, the geographic entity individualization model of the target area is individualized and encoded to obtain the encoded geographic entity; The encoded geographic entities are stored accordingly according to a preset storage structure to obtain a single geographic entity model of the target area; the single geographic entity model of the target area is a result data block in OSGB format and OBJ format.

[0089] Specifically, in some embodiments, step 105 may be implemented by the following steps: After obtaining the results of geographic entity singulation, the results of geographic entity singulation and the updated oblique photography model of the target area can be flattened and fused to obtain the final geographic entity singulation model.

[0090] The scene fusion and output requirements include the following: the monomer model is a complete geometric body as a single modeling object, and each geographic entity model forms a separate OSGB format file; the monomer building model produced based on oblique photogrammetry requires the building structure to be flat and finally presented as a regular surface 3D model. The number of texture maps should be reduced as much as possible, and automatic map merging should be performed to reduce data redundancy, etc.

[0091] First, the geographic entity singularization model of the target area can be singularized and encoded based on the target singularization results of the target area and the oblique photography model of the target area after scene decoration to obtain the encoded geographic entity. Further, the encoded geographic entity is stored correspondingly according to the preset storage structure to obtain the geographic entity singularization model of the target area; the geographic entity singularization model of the target area is a result data block in OSGB format and OBJ format.

[0092] For example, the three-dimensional monomer model and the decorated three-dimensional scene model are compressed and fused. The three-dimensional terrain scene result of the fusion data output should be consistent with the storage structure during distribution. The folder contains the Data folder and configuration file (.XML) for storing the result data blocks (.OSGB and .OBJ); the monomer model of the building and the component-level sketch model are split into monomers and encoded and stored to meet the service needs of free splicing and customization of the scene.

[0093] The method provided in this embodiment performs equalization and fusion processing on the three-dimensional monomer model and the finished three-dimensional scene model to form a final geographic entity monomer model. The generation efficiency of the geographic entity monomer model is relatively high.

[0094] Figure 2 It is a schematic diagram of the principle of the method for generating a geographical entity monomer model provided by the present invention, such as Figure 2 As shown, the method includes the following: First, the existing data within the test area are collected and sorted, including existing individual results, oblique photography results, and point cloud results.

[0095] Then, for the missing areas, the existing individualization results are reconstructed by field reshooting; the key areas are reconstructed by individualization (including supplementing the real texture of the urban component sketch model), and the urban component sketches include at least one of the following: national flags, flower beds, trees, trash cans, fences, street lights, bus stops, traffic lights, traffic signs, etc.; the three-dimensional entities are individualized.

[0096] Furthermore, the oblique photography results are subjected to geographic scene finishing: 3D holes, model distortion, texture loss, model adhesion, isolated suspended objects, and pedestrian / vehicle removal.

[0097] Furthermore, based on the results of individualization of three-dimensional entities and the results of geographical scene decoration, flattened and fused results are obtained.

[0098] The method provided in this embodiment performs individual processing and reconstruction of high-resolution tilted real-scene 3D models, constructs individual geographic scenes and 3D entities, improves the semantic attributes of 3D entities, constructs the association between 2D and 3D geographic entities, realizes 2D and 3D consistent expression, and explores the method of "one code, multiple states" expression of geographic entities. It is of great significance to perform confidentiality technology processing on geographic scenes and 3D entities and realize a wider range of 3D applications.

[0099] The following is a description of a device for generating a single geographic entity model provided by the present invention. The device for generating a single geographic entity model described below and the method for generating a single geographic entity model described above can be referred to in correspondence with each other.

[0100] Figure 3 Schematic diagram of the structure of the device for generating the geographical entity monomer model provided by the present invention, such as Figure 3 As shown, the device 300 for generating a single geographic entity model includes an acquisition module 310, a generation module 320 and a fusion module 330; wherein: The acquisition module 310 is used to acquire the oblique photography model of the target area and the existing individualization results of the target area; the existing individualization results are the geographic entity individualization models of the target area generated within a preset historical time period; A generating module 320, for determining missing areas in the existing individualization results and determining key areas in the target area based on the oblique photography model of the target area and the existing individualization results of the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The fusion module 330 is used to fuse the target individualization result of the target area and the oblique photography model of the target area after scene decoration to obtain a geographic entity individualization model of the target area.

[0101] The device provided in this embodiment includes an acquisition module 310, a generation module 320 and a fusion module 330. First, the acquisition module 310 acquires the oblique photography model of the target area and the existing individualization results of the target area; then, the generation module 320 determines the missing areas of the existing individualization results and determines the key areas in the target area based on the oblique photography model of the target area and the existing individualization results of the target area; further, based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are individually reconstructed to obtain the first individualization results of the missing area, and according to the field supplementary shooting of the key area and the oblique photography model of the key area, the geographic entities in the key area are individually reconstructed to obtain the second individualization results of the key area; based on the first individualization results of the missing area, the second individualization results of the key area and the existing individualization results of the target area, the target individualization results of the target area are determined; then, the fusion module 330 fuses the target individualization results of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity individualization model of the target area.

[0102] The present invention determines the missing areas and key areas of the existing individualized results based on the oblique photography model of the target area and the existing individualized results of the target area, and then performs individualized reconstruction on the missing areas, individualized reconstruction on the key areas, and refines the placement of the widget model to obtain the individualized results of the geographic entity of the target area. The individualized model of the geographic entity is finally generated in combination with the oblique photography model of the target area after scene decoration. The individualized processing of each region and the combination of the oblique photography model of the target area after scene decoration quickly generate a high-quality individualized model of the geographic entity, thereby improving the efficiency of individualized model generation.

[0103] According to a device 300 for generating a geographical entity monomer model provided by the present invention, the generating module 320 is specifically used for: According to the point cloud data of the target area, updating the surface texture and individualized change area of ​​the geographic entity in the missing area, to obtain a third individualization result of the missing area; By reshooting the missing area in the field, the surface texture in the third individualization result of the missing area is updated to obtain the first individualization result of the missing area.

[0104] According to a device 300 for generating a single geographic entity model provided by the present invention, the geographic entities in the key area include important building models, sculpture models and widget models; the generating module 320 is specifically used for: According to the field supplementary photography of the key area and the oblique photography model of the key area, the important building model in the key area is reconstructed in a monomeric manner to obtain a fourth monomeric result of the important building model; According to the field supplementary photography of the key area and the oblique photography model of the key area, the sculpture model in the key area is reconstructed in a monomeric manner to obtain a fifth monomeric result of the sculpture model; Using a python script, the widget model in the key area is subjected to displacement processing; Based on the fourth individualization result of the important building model, the fifth individualization result of the sculpture model and the small component model after displacement processing, the second individualization result of the key area is determined.

[0105] According to a device 300 for generating a single geographic entity model provided by the present invention, the generating module 320 is further used for: Constructing a model structure of the important building model based on the oblique photography model of the key area and the ground photographic image of the key area, and generating a plain model of the important building model; Texture mapping is performed based on the plain model of the important building model to obtain the fourth monomerization result of the key area.

[0106] According to a device 300 for generating a single geographic entity model provided by the present invention, the generating module 320 is further used for: The oblique photography model of the target area is subjected to geographic scene decoration to obtain a decorated oblique photography model of the target area.

[0107] According to a device 300 for generating a single geographic entity model provided by the present invention, the generating module 320 is further used for: Using model modification software to perform a modification operation on the oblique photography model of the target area; Among them, the finishing processing operation includes at least one of the following: deleting isolated suspended objects in the oblique photography model of the target area; performing 3D hole repair on the oblique photography model of the target area; removing damaged vehicles in the oblique photography model of the target area; performing model adhesion processing on the oblique photography model of the target area and performing model distortion processing on the oblique photography model of the target area.

[0108] According to a device 300 for generating a single geographic entity model provided by the present invention, the generating module 320 is further used for: Determine an updated oblique photography model of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The updated oblique photography model of the target area is physically cut using the vector plane of the single ground object target to obtain the target individualization result of the target area.

[0109] According to a device 300 for generating a geographic entity monomer model provided by the present invention, the fusion module 330 is specifically used for: Based on the target singulation result of the target area and the oblique photography model of the target area after scene decoration, the geographic entity singulation model of the target area is singulated and encoded to obtain the encoded geographic entity; The encoded geographic entities are stored accordingly according to a preset storage structure to obtain a single geographic entity model of the target area; the single geographic entity model of the target area is a result data block in OSGB format and OBJ format.

[0110] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communications interface 420 and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the method for generating a geographic entity monomer model, which method includes: Obtaining an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; Based on the oblique photography model of the target area and the existing individualization results of the target area, determining the missing areas in the existing individualization results, and determining the key areas in the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

[0111] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0112] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for generating a geographic entity monomer model provided by the above methods, the method comprising: Obtaining an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; Based on the oblique photography model of the target area and the existing individualization results of the target area, determining the missing areas in the existing individualization results, and determining the key areas in the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

[0113] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the method for generating a single model of a geographic entity provided by the above methods, the method comprising: Obtaining an oblique photography model of a target area and an existing individualization result of the target area; the existing individualization result is a geographic entity individualization model of the target area generated within a preset historical time period; Based on the oblique photography model of the target area and the existing individualization results of the target area, determining the missing areas in the existing individualization results, and determining the key areas in the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

[0114] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a single geographic entity model, characterized in that: include: Obtaining an oblique photography model of a target area and existing individualization results of the target area; The existing individualization results are individualization models of geographic entities of the target area generated within a preset historical time period; Based on the oblique photography model of the target area and the existing individualization results of the target area, determining the missing areas in the existing individualization results, and determining the key areas in the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain a geographic entity individualization model of the target area.

2. The method for generating a geographic entity monomer model according to claim 1, characterized in that: The step of reconstructing the geographic entities in the missing area based on the oblique photography model of the target area and the point cloud data of the target area to obtain a first individualization result of the missing area includes: According to the point cloud data of the target area, the surface texture and the individualized change area of ​​the geographical entity in the missing area are updated to obtain a third individualization result of the missing area; By reshooting the missing area in the field, the surface texture in the third individualization result of the missing area is updated to obtain the first individualization result of the missing area.

3. The method for generating a geographic entity monomer model according to claim 1, characterized in that: The geographical entities in the key area include important building models, sculpture models and small component models; the geographical entities in the key area are singularly reconstructed based on the field supplementary shooting of the key area and the oblique photography model of the key area to obtain the second singularization result of the key area, including: According to the field supplementary photography of the key area and the oblique photography model of the key area, the important building model in the key area is reconstructed in a monomeric manner to obtain a fourth monomeric result of the important building model; According to the field supplementary photography of the key area and the oblique photography model of the key area, the sculpture model in the key area is reconstructed in a monomeric manner to obtain a fifth monomeric result of the sculpture model; Using a python script, the widget model in the key area is subjected to displacement processing; Based on the fourth individualization result of the important building model, the fifth individualization result of the sculpture model and the small component model after displacement processing, the second individualization result of the key area is determined.

4. The method for generating a geographic entity monomer model according to claim 1, characterized in that: The step of performing monomer reconstruction on the important building model in the key area according to the field supplementary shooting of the key area and the oblique photography model of the key area to obtain a fourth monomerization result of the important building model includes: Constructing a model structure of the important building model based on the oblique photography model of the key area and the ground photographic image of the key area, and generating a plain model of the important building model; Texture mapping is performed based on the plain model of the important building model to obtain the fourth monomerization result of the key area.

5. The method for generating a geographic entity monomer model according to claim 1, characterized in that: Before fusing the target individualization result of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity individualization model of the target area, the method includes: The oblique photography model of the target area is subjected to geographic scene decoration to obtain a decorated oblique photography model of the target area.

6. The method for generating a geographic entity monomer model according to claim 5, characterized in that: The step of performing geographic scene finishing on the oblique photography model of the target area to obtain the finished oblique photography model of the target area includes: Using model modification software to perform a modification operation on the oblique photography model of the target area; Among them, the finishing processing operation includes at least one of the following: deleting isolated suspended objects in the oblique photography model of the target area; performing 3D hole repair on the oblique photography model of the target area; removing damaged vehicles in the oblique photography model of the target area; performing model adhesion processing on the oblique photography model of the target area and performing model distortion processing on the oblique photography model of the target area.

7. The method for generating a geographic entity monomer model according to claim 5, characterized in that: The determining of the target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area and the existing individualization result of the target area includes: Determine an updated oblique photography model of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The updated oblique photography model of the target area is physically cut using the vector plane of the single ground object target to obtain the target individualization result of the target area.

8. The method for generating a geographical entity monomer model according to claim 1, characterized in that: The target individualization result of the target area and the oblique photography model of the target area after scene decoration are fused to obtain the geographic entity individualization model of the target area, including: Based on the target singulation result of the target area and the oblique photography model of the target area after scene decoration, the geographic entity singulation model of the target area is singulated and encoded to obtain the encoded geographic entity; The encoded geographic entities are stored accordingly according to a preset storage structure to obtain a single geographic entity model of the target area; the single geographic entity model of the target area is a result data block in OSGB format and OBJ format.

9. A device for generating a single model of a geographic entity, characterized in that: include: An acquisition module, used to acquire an oblique photography model of a target area and existing individualization results of the target area; The existing individualization results are individualization models of geographic entities of the target area generated within a preset historical time period; A generating module, for determining missing areas in the existing individualization results and determining key areas in the target area based on the oblique photography model of the target area and the existing individualization results of the target area; Based on the oblique photography model of the target area and the point cloud data of the target area, the geographic entities in the missing area are singularly reconstructed to obtain a first singularization result of the missing area, and according to the field supplementary photography of the key area and the oblique photography model of the key area, the geographic entities in the key area are singularly reconstructed to obtain a second singularization result of the key area; Determine a target individualization result of the target area based on the first individualization result of the missing area, the second individualization result of the key area, and the existing individualization result of the target area; The fusion module is used to fuse the target individualization results of the target area and the oblique photography model of the target area after scene decoration to obtain the geographic entity individualization model of the target area.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating a single model of a geographic entity as described in any one of claims 1 to 7 is implemented.

Images