A tilt photography model scene element automatic separation method based on digital twinning

Abstract

The application provides a kind of tilt photography model scene element automatic separation method based on digital twinning, obtains scene overall data by scanning entire the tilt model scene;According to the characteristic parameter set in advance for single tilt model, select the single tilt model that meets the characteristic parameter from the scene overall data, wherein the characteristic parameter includes the geometric feature and color feature of the single tilt model;The selected single tilt model is separated from the tilt model scene, and the separated single tilt model is exported and saved separately.Can quickly separate tilt photography model scene element, can realize the real separation of house, tree and other ground objects and tilt measurement scene, and the edge of ground object is neat and beautiful.Can obtain ground object graph element information, carry out ray collision detection, distance calculation and other operations, meet the business application demand.Through automatic processing process, improve the efficiency and quality of tilt photography model processing.

Description

Technical Field

[0001] This invention relates to the fields of computer vision and 3D modeling technology, and in particular to an automatic separation method for scene elements in a digital twin-based oblique photogrammetry model, as well as an automatic separation system, electronic device, and computer-readable storage medium for scene elements in an oblique photogrammetry model. Background Technology

[0002] Oblique photogrammetry is an emerging high-tech technique in the international field of surveying and remote sensing. It involves mounting multiple sensors on the same flight platform to simultaneously acquire images from five different angles: vertical, forward-looking, left-looking, right-looking, and backward-looking. This technology can obtain rich texture information from the sides of ground features and, through efficient and automated 3D modeling techniques, quickly construct true 3D spatial scenes with accurate geographic location information of objects.

[0003] However, in digital twin applications, it is necessary to individualize features such as houses and trees in the oblique photogrammetry model for secondary editing of individual elements. Existing individualization methods often suffer from problems such as jagged feature boundaries and inconsistencies in feature boundaries across different accuracy levels, failing to meet practical application requirements. Summary of the Invention

[0004] To address the technical problems existing in the prior art, the present invention provides the following technical solution:

[0005] On the one hand, a method for automatic separation of scene elements based on a digital twin oblique photogrammetry model is provided. This method is implemented by an electronic device and includes:

[0006] S1. Prepare the tilted model scene;

[0007] S2. Scan the entire tilted model scene to obtain overall scene data;

[0008] S3. Based on the feature parameters pre-set for a single tilt model, select the single tilt model that conforms to the feature parameters from the overall scene data, wherein the feature parameters include the geometric features and color features of the single tilt model;

[0009] S4. Separate the selected single tilt model from the tilt model scene, export the separated single tilt model and save it separately.

[0010] Preferably, in step S4, after deriving the separated individual tilt model, the following is further included:

[0011] The base model and material map of the single tilted model are separated, the relationship between the base model and the material map is established, and the result is output and saved.

[0012] Preferably, in step S3, the geometric features include the three-dimensional geometric features of the single tilted model in the three-dimensional oblique photogrammetry coordinate system, and the color features include the color range values ​​of several color blocks on the single tilted model.

[0013] Preferably, in step S3, after selecting the single tilt model that conforms to the feature parameters from the overall scene data according to the feature parameters pre-set for the single tilt model, the method further includes:

[0014] A feature template is pre-constructed and the target parameters of the corresponding features are configured, wherein the feature template is configured with a corresponding feature matching algorithm;

[0015] The feature parameters of each selected individual tilt model are input into the feature template;

[0016] The feature matching algorithm is used to calculate the feature matching degree of each selected individual tilt model, and the individual tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and output.

[0017] Preferably, the feature matching algorithm includes a geometric feature matching degree algorithm:

[0018] ,

[0019] in:

[0020] G represents the geometric feature matching degree;

[0021] These are the geometric feature parameters of the model: volume, surface area, and tilt angle.

[0022] These are the preset target geometric parameters;

[0023] These are the sub-weights of the geometric features, α1+α2+α3=1;

[0024] This is the attenuation coefficient for the difference in tilt angle;

[0025] min() and max() represent taking the minimum value and the maximum value, respectively.

[0026] Preferably, the feature matching algorithm includes a color feature matching degree algorithm:

[0027] ,

[0028] in:

[0029] C represents the color feature matching degree;

[0030] The color feature parameters of the model are: RGB color mean vectors;

[0031] The target color mean vector is preset;

[0032] This represents the Euclidean distance, normalized to [0,1].

[0033] To ensure color consistency across blocks (calculated using histogram similarity);

[0034] The sub-weights for color features are (β1+β2=1).

[0035] Preferably, the method further includes:

[0036] A distributed file system is used to store the feature parameters of each individual tilt model and the selected individual tilt model, including:

[0037] The required feature parameters of the single tilt model are saved to the master node of the distributed file system;

[0038] The master node prepares the corresponding data node for the single tilt model to be separated based on the saved information. After the single tilt model is separated, the master node identifies the feature parameters of the separated single tilt model and stores them in the corresponding data node.

[0039] On the other hand, an automatic scene element separation system for oblique photogrammetry models is provided. This system is applied to the automatic scene element separation method for oblique photogrammetry models based on digital twins. The system includes:

[0040] The acquisition module is used to acquire and prepare tilted model scenes;

[0041] The scanning module is used to scan the entire tilted model scene and obtain overall scene data;

[0042] The model feature selection module is used to select a single tilted model that conforms to the feature parameters set in advance for a single tilted model from the overall scene data, wherein the feature parameters include the geometric features and color features of the single tilted model;

[0043] The model element separation module is used to separate the selected individual tilted model from the tilted model scene, export the separated individual tilted model, and save it separately.

[0044] On the other hand, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions, wherein when executed by the processor, the computer-readable instructions implement any of the methods described above for automatic separation of scene elements in a digital twin-based oblique photogrammetry model.

[0045] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for automatic separation of scene elements in a digital twin-based oblique photogrammetry model.

[0046] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0047] This invention acquires overall scene data by scanning the entire tilted model scene; based on pre-defined feature parameters for each individual tilted model, it selects a single tilted model from the overall scene data that matches the feature parameters, including the geometric and color features of the single tilted model; the selected single tilted model is then separated from the tilted model scene, exported, and saved separately. This method enables rapid separation of elements from the tilted photogrammetry scene, achieving true separation of features such as houses and trees from the tilted measurement scene, with neat and aesthetically pleasing feature edges. It can acquire feature primitive information and perform operations such as ray collision detection and distance calculation, meeting business application needs. Through automated processing, it improves the efficiency and quality of tilted photogrammetry model processing. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of a method for automatic separation of scene elements based on a digital twin oblique photogrammetry model provided in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of the application process provided in the embodiments of the present invention;

[0051] Figure 3 This is a schematic diagram of a tilted model scene provided in an embodiment of the present invention;

[0052] Figure 4This is a schematic diagram of the features of an architectural model provided in an embodiment of the present invention (4a is geometric features, 4b is color features);

[0053] Figure 5 This is a schematic diagram of color blocks in a parking area provided in an embodiment of the present invention;

[0054] Figure 6 This is a schematic diagram of selecting vegetation in a scene based on color, provided by an embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram illustrating the separation of a single vegetation tilt model provided in an embodiment of the present invention;

[0056] Figure 8 This is a schematic diagram of the separation of a road model provided in an embodiment of the present invention;

[0057] Figure 9 This is a block diagram of an automatic scene element separation system for oblique photography models provided in an embodiment of the present invention;

[0058] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0060] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0061] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0062] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0063] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0064] This invention provides a method for automatic separation of scene elements based on a digital twin-based oblique photogrammetry model. This method can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart shown is for an automatic scene element separation method based on a digital twin oblique photogrammetry model. The processing flow of this method may include the following steps:

[0065] S1. Prepare the tilted model scene;

[0066] S2. Scan the entire tilted model scene to obtain overall scene data;

[0067] S3. Based on the feature parameters pre-set for a single tilt model, select the single tilt model that conforms to the feature parameters from the overall scene data, wherein the feature parameters include the geometric features and color features of the single tilt model;

[0068] S4. Separate the selected single tilt model from the tilt model scene, export the separated single tilt model and save it separately.

[0069] This invention proposes a method for separating scene elements in an oblique photogrammetry model, aiming to achieve true separation of features such as houses, vegetation, water surfaces, and roads from the oblique measurement scene, while ensuring neat and aesthetically pleasing edges of features. It can acquire feature primitive information and perform operations such as ray collision detection and distance calculation.

[0070] Combined with appendix Figure 2 The diagram shown is an application flowchart of the present invention. First, the user prepares an oblique photography model scene, as shown in the attached diagram. Figure 3 The tilted model scene shown includes water, vegetation, and buildings.

[0071] Here, by setting feature parameters for the required (to be separated) individual tilted models, including the geometric and color features of the individual tilted models, the tilted model scene is scanned according to the set feature parameters, and individual tilted models that meet the set feature parameters are selected, marked, and exported.

[0072] Therefore, the first step is to obtain the geometric and color features of the oblique photogrammetry model to be processed.

[0073] The geometric features include the three-dimensional geometric features of the single tilted model in the three-dimensional oblique photogrammetry coordinate system; these three-dimensional geometric features are essentially the elevation information of the model surfaces. Geometric features in the scene are derived by calculating the spatial position of the model along the XYZ axes within the scene, resulting in various feature types. For example... Figure 4The geometric features of the building model shown in 4a, the model within the boundary of a height difference of more than 2 meters on the Z-axis, and the model part with continuous planes, the building model that meets these geometric features will be separated as a separate building model (a tilted model scene may contain several such similar building models, such as...). Figure 3 Several buildings that overlap in the middle.

[0074] If the model needs to meet color characteristics, corresponding color characteristic parameters can be set. These color characteristics include the color range values ​​of several color blocks on the single tilted model. For example, the color of a block in a building model should also meet certain color range values. Only models that simultaneously meet both geometric and color characteristics can be used as the final separated model. Figure 4 The building model shown in 4b has its various blocks displaying corresponding colors. If the colors of each model block (referred to as color blocks) meet the preset color range value, then it is considered a qualified model and separated out.

[0075] For color features, if only the color features are satisfied, then the output should be a color block that satisfies the corresponding color features. For example... Figure 5 The parking area shown (if there are cars, then it needs to meet the following requirements: a model of an independent raised part under 2 meters on the Z-axis, with a length range of 2-5 meters and a width range of 1.3-1.9 meters, and also meet the characteristics of a single color block). When the color range value of a single color block meets the preset color characteristics, the scene model where this part of the parking area is located can be separated and output.

[0076] Therefore, by pre-setting the geometric and color features of the individual tilted models (such as buildings, roads, and water surfaces) to be separated, the selected buildings, trees, and other parts of the model can be separated from the tilted photogrammetry scene. Finally, the separated models are exported, and the separated tilted models are saved as separate data assets.

[0077] Preferably, in step S4, after deriving the separated individual tilt model, the following is further included:

[0078] The base model and material map of the single tilted model are separated, the relationship between the base model and the material map is established, and the result is output and saved.

[0079] To further refine the application of the separated elements, this section also separates the base model and material texture of each individual tilted model, establishes the relationship between the base model and the material texture, and outputs and saves the results. In this way, the base model and the material texture applied to each individual tilted model can be obtained. Specifically, this can be done in conjunction with model surface mapping technology (creating textures: First, you need to prepare a texture image, which can be a photo, painting, pattern, etc. Texture images can be obtained using graphics software or from the real world. The size of the texture image should match the size of the model or be appropriately scaled. Texture coordinate assignment: Assign texture coordinates to each surface point of the model. Texture coordinates are two-dimensional coordinates used to locate pixels on the texture image. A common texture coordinate system is the UV coordinate system, where U represents the horizontal coordinate and V represents the vertical coordinate. Usually, modeling software will automatically assign initial texture coordinates to the vertices of the model, but they can also be manually edited and adjusted for better results. Texture mapping: Map the texture image onto the surface of the model. In graphics software, the texture image can be loaded into the texture channel of the model's material, and the texture coordinates can be associated with the vertices of the model. When rendering the model, the computer will obtain the pixels at the corresponding positions on the texture image based on the texture coordinates and draw them onto the corresponding positions on the model's surface. Texture adjustment: Adjust the texture to achieve the desired effect).

[0080] like Figure 6 The image shows a tilted model scene (tilted photograph). We now want to isolate the vegetation in the scene to form a single tilted model.

[0081] The goal is to isolate the vegetation in the scene and create individual tilted models. This is done by scanning the entire tilted model scene to obtain overall scene data, specifically the geometric and color information of each independent model within the tilted photogrammetry scene (e.g., the geometric and color data of several buildings). The specific steps are as follows:

[0082] I. Data Preprocessing and Scenario Analysis

[0083] Scene data standardization processing

[0084] The original oblique photogrammetry 3D model is formatted (e.g., converted to OSGB or S3MB format), and SuperMap iDesktop's oblique import function is used for data compression and anomaly repair to ensure model integrity and lightweight requirements.

[0085] High-precision point cloud and texture mapping data are generated through 3D reconstruction algorithms (such as bundle adjustment) to extract the geometric contours of independent objects such as buildings and roads in the scene.

[0086] Model individualization preprocessing

[0087] By employing dynamic individualization technology, a vector surface layer is overlaid with an oblique photogrammetry model, and each independent building is given a unique ID attribute, enabling rapid separation of the target model.

[0088] By using segmentation or algorithmic identification (such as morphological feature matching) to separate overlapping models in complex scenes, the redundancy of subsequent scans can be reduced.

[0089] II. Scan Path Optimization Design

[0090] Path planning strategy

[0091] Regional segmentation scanning: Divide the scene into grid areas based on the complexity of the scene, and prioritize scanning high-density building clusters or key features (such as main roads and landmark buildings). Administrators can set the planning logic for scanning tasks.

[0092] Multi-view collaborative scanning

[0093] A five-lens tilt camera is used to simultaneously acquire vertical and tilt view data, and the accuracy of geometric feature extraction is improved by multi-source data fusion technology (such as point cloud and BIM model overlay).

[0094] For complex building sides (such as glass curtain walls and concave-convex structures), a low-altitude supplementary shooting strategy is adopted, combined with vehicle-mounted LiDAR to supplement detailed texture information.

[0095] III. Geometric and Color Information Extraction

[0096] Geometric feature extraction

[0097] The system extracts parameters such as building height and volume through point cloud density analysis, and generates a geometric model of the building surface by combining it with a 3D mesh construction algorithm (such as Delaunay triangulation). At the same time, the system records the geometric parameters of the geometric model.

[0098] Spatial measurement tools (such as the "Object Operations" function of SuperMap iDesktop) are used to trim, cut holes, and add water surfaces to the model to optimize the integrity of geometric data.

[0099] Color information is collected synchronously.

[0100] During aerial photography, a high-resolution RGB sensor is used, combined with texture mapping technology to seamlessly integrate multi-angle images onto the surface of the geometric model, preserving realistic color details. Simultaneously, the system records the color values ​​of each color block within each model.

[0101] Multispectral data fusion technology is used to compensate for color deviations in areas with uneven lighting (such as shaded areas) to ensure color data consistency.

[0102] IV. Data Post-processing and Application

[0103] Lightweight and standardized output

[0104] CoPre2.0 software was used to solve and optimize the scanned data, compressing the model size to 30%-50% of the original data to meet the high-efficiency loading requirements of the web client.

[0105] It outputs standardized formats (such as S3MB and I3S) and supports seamless integration with BIM and GIS platforms to achieve integrated 2D and 3D management.

[0106] Anomaly detection and feedback mechanism

[0107] The scanned defect areas are marked by automated quality inspection tools (such as point cloud hole detection and texture loss alarm), triggering a local rescanning process.

[0108] The scanned data is reported to the backend for storage and used for subsequent model parameter analysis and separation of the corresponding model.

[0109] Based on the above approach, the scene is first scanned to obtain its color information. Then, according to a pre-inputted range of green values, the green vegetation in the scene is selected. Finally, the selected vegetation is separated to form... Figure 7 The single tilted model shown. For example... Figure 8 The roads shown can be selected and separated using preset geometric features.

[0110] Therefore, this method can separate major elements in a scene into individual elements, facilitating flexible use in various scenarios. This solution enables true separation of features such as houses, vegetation, water surfaces, and roads from the tilt measurement scene, ensuring neat and aesthetically pleasing feature edges. It also allows for the acquisition of feature primitive information and the performance of operations such as ray collision detection and distance calculation.

[0111] When separating the models, such as Figure 6 As shown, it contains several building models or vegetation, so when separated, it will output several corresponding individual tilted models (such as...). Figure 7 (Multiple vegetation types are shown). In order to select a single tilt model that meets the user's satisfaction, this section also designs a model that performs feature matching calculations based on the feature parameters set in the model and outputs a model whose feature matching degree meets the user's requirements.

[0112] Preferably, in step S3, after selecting the single tilt model that conforms to the feature parameters from the overall scene data according to the feature parameters pre-set for the single tilt model, the method further includes:

[0113] A feature template is pre-constructed and the target parameters of the corresponding features are configured, wherein the feature template is configured with a corresponding feature matching algorithm;

[0114] The feature parameters of each selected individual tilt model are input into the feature template;

[0115] The feature matching algorithm is used to calculate the feature matching degree of each selected individual tilt model, and the individual tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and output.

[0116] In the backend system, a "feature template" is pre-built. The geometric parameters and / or color parameters of each selected individual tilt model can be read through the feature template. The feature matching degree algorithm configured accordingly is used to calculate the feature matching degree of each individual tilt model and output the individual tilt model corresponding to the maximum feature matching degree.

[0117] In this way, the desired model can be extracted from several individual tilted building models and used for subsequent operations (such as ray collision detection and distance calculation). It can also be used to rank models by feature matching degree and output the top-ranked models.

[0118] The following will provide a method for calculating geometric feature matching degree and color feature matching degree. The corresponding algorithm can be scheduled and used according to the user's selection requirements for the corresponding individual tilt model.

[0119] Preferably, the feature matching algorithm includes a geometric feature matching degree algorithm:

[0120] ,

[0121] in:

[0122] G represents the geometric feature matching degree;

[0123] These are the geometric feature parameters of the model: volume, surface area, and tilt angle.

[0124] These are the preset target geometric parameters;

[0125] These are the sub-weights of the geometric features, α1+α2+α3=1;

[0126] This is the attenuation coefficient for the difference in tilt angle;

[0127] min() and max() represent taking the minimum value and the maximum value, respectively.

[0128] Preferably, the feature matching algorithm includes a color feature matching degree algorithm:

[0129] ,

[0130] in:

[0131] C represents the color feature matching degree;

[0132] The color feature parameters of the model are: RGB color mean vectors;

[0133] The target color mean vector is preset;

[0134] This represents the Euclidean distance, normalized to [0,1].

[0135] To ensure color consistency across blocks (calculated using histogram similarity);

[0136] The sub-weights for color features are (β1+β2=1).

[0137] The algorithm steps are as follows:

[0138] First, data preprocessing, including feature extraction:

[0139] Geometric feature extraction:

[0140] Calculate the geometric feature parameters of each candidate model, including volume, surface area aspect ratio, curvature distribution, tilt angle, etc.

[0141] Color feature extraction:

[0142] Calculate the color feature parameters for each candidate model, including color mean, color variance, dominant color distribution, and color consistency of blocks;

[0143] Secondly, input the data:

[0144] The feature parameters (3D geometric data (point cloud or mesh) and corresponding block color data (RGB or HSV)) of each individual tilted model selected from the tilted model scene are input into the corresponding template;

[0145] Finally, based on the feature matching algorithm in the corresponding template, the feature parameters of the selected single tilt model are calculated and the corresponding feature matching degree is calculated. The single tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and output.

[0146] For example, for buildings, you can calculate only the geometric feature matching degree. Calculate the geometric feature matching degree for each selected individual tilt model of a building, output the individual tilt model of the building with the highest geometric feature matching degree, and save it.

[0147] If further filtering based on building color blocks is required, the color feature matching degree of each selected individual building tilt model can be calculated, and the average of the matching degree with the corresponding geometric features can be calculated. Finally, the individual building tilt model with the largest average value can be selected and saved.

[0148] Therefore, it is possible to export the required single tilt model based on user definition.

[0149] Preferably, the method further includes:

[0150] A distributed file system is used to store the feature parameters of each individual tilt model and the selected individual tilt model, including:

[0151] The required feature parameters of the single tilt model are saved to the master node of the distributed file system;

[0152] The master node prepares the corresponding data node for the single tilt model to be separated based on the saved information. After the single tilt model is separated, the master node identifies the feature parameters of the separated single tilt model and stores them in the corresponding data node.

[0153] The distributed file system, HDFS, consists of master nodes (management nodes) and data nodes (storage nodes). Therefore, this section utilizes HDFS to separately store the exported individual skew models and their characteristics, facilitating subsequent management and categorized application of each individual skew model. Specifically:

[0154] This technical solution uses a distributed file system to store and manage the feature parameters and corresponding model files of each individual tilted model (such as an architectural model drawing). The system mainly consists of a distributed file system, a master node, data nodes, and model management and export modules.

[0155] Setting up a distributed file system

[0156] Choose a suitable distributed file system (such as Hadoop HDFS, Ceph, etc.) and build and configure it according to system requirements.

[0157] Ensure that the distributed file system has high availability, high throughput, and data fault tolerance.

[0158] Feature parameters are saved to the master node.

[0159] When a single tilt model needs to be stored, the feature parameters of that model are extracted first.

[0160] Feature parameters may include geometric information, texture information, material information, etc. of the model.

[0161] The extracted feature parameters are saved to the master node of the distributed file system in a specific format (such as JSON, XML, or binary format).

[0162] The master node is responsible for receiving and storing these characteristic parameters, and recording their storage location and related information.

[0163] Prepare data nodes

[0164] The master node prepares the corresponding data nodes for the individual tilt models to be separated based on the saved feature parameter information.

[0165] Data nodes are nodes in a distributed file system used to store actual data; they are responsible for storing the original files or processed files of the model.

[0166] The master node selects a suitable data node to store the model file to be exported based on factors such as the system's load balancing strategy and data node capacity.

[0167] Export and store the separated model

[0168] The model management and export module is responsible for exporting individual tilt models to specific file formats (such as OBJ, FBX, COLLADA, etc.).

[0169] The exported model files are transferred to the previously prepared data nodes for storage.

[0170] During storage, data nodes ensure the integrity and consistency of file data.

[0171] Feature parameters are stored in the corresponding data nodes.

[0172] After the model file is successfully stored, the master node identifies and extracts the previously saved feature parameters.

[0173] The master node associates these feature parameters with the model file and stores them on the previously prepared data nodes, or in the same or associated location as the model file.

[0174] When storing, feature parameters can be associated with model files in the form of metadata to facilitate subsequent retrieval and use.

[0175] Specifically, it can be understood and implemented in conjunction with the HDFS system architecture.

[0176] This technical solution utilizes a distributed file system to store and manage the feature parameters and corresponding model files of a single tilt model, thereby achieving efficient storage, retrieval, and use of model data.

[0177] Figure 9 This is a block diagram of an automatic scene element separation system for an oblique photogrammetry model, illustrated according to an exemplary embodiment. This system is used in a method for automatic scene element separation based on digital twin-based oblique photogrammetry models. (Refer to...) Figure 9 The system includes:

[0178] The acquisition module is used to acquire and prepare tilted model scenes;

[0179] The scanning module is used to scan the entire tilted model scene and obtain overall scene data;

[0180] The model feature selection module is used to select a single tilted model that conforms to the feature parameters set in advance for a single tilted model from the overall scene data, wherein the feature parameters include the geometric features and color features of the single tilted model;

[0181] The model element separation module is used to separate the selected individual tilted model from the tilted model scene, export the separated individual tilted model, and save it separately.

[0182] Please refer to the steps outlined above to understand the functions and interactions of each module; further details will not be provided here.

[0183] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 10 As shown, the electronic device may include the above-mentioned Figure 9 The oblique photography model scene element automatic separation system is shown. Optionally, the electronic device 410 may include a first processor 2001.

[0184] Optionally, the electronic device 410 may also include a memory 2002 and a transceiver 2003.

[0185] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0186] The following is combined Figure 10 A detailed description of each component of electronic device 410 is provided below:

[0187] The first processor 2001 is the control center of the electronic device 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0188] Optionally, the first processor 2001 can perform various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0189] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 10 CPU0 and CPU1 are shown in the diagram.

[0190] In a specific implementation, as one example, the electronic device 410 may also include multiple processors, for example... Figure 10 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0191] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0192] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and be connected via the interface circuit of the electronic device 410. Figure 10 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0193] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0194] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 10 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0195] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected via the interface circuit of the electronic device 410. Figure 10 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0196] It should be noted that, Figure 10 The structure of the electronic device 410 shown does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0197] Furthermore, the technical effects of the electronic device 410 can be referenced from the technical effects of the automatic separation method of scene elements based on digital twin oblique photography model described in the above method embodiments, and will not be repeated here.

[0198] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0199] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0200] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0201] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0202] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0203] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0204] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0205] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, systems, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0206] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0207] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0208] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0209] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0210] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for automatic separation of scene elements in an oblique photogrammetry model based on digital twins, characterized in that, The method includes: S1. Prepare the tilted model scene; S2. Scan the entire tilted model scene to obtain overall scene data; Steps S1-S2 are as follows: (1) Data preprocessing and scenario analysis Scene data standardization processing The original oblique photogrammetry 3D model was formatted and SuperMap iDesktop's oblique import function was used for data compression and anomaly repair to ensure model integrity and lightweight requirements. High-precision point cloud and texture mapping data are generated through 3D reconstruction algorithms to extract the geometric contours of independent objects such as buildings and roads in the scene; Model individualization preprocessing By employing dynamic individualization technology, a vector surface layer is overlaid with an oblique photogrammetry model, and each independent building is given a unique ID attribute, enabling rapid separation of the target model; By using segmentation or algorithms to identify and separate overlapping models in complex scenes, the redundancy of subsequent scans can be reduced; (2) Scanning path optimization design Path planning strategy Regional segmentation scanning: Divide the scene into grid regions based on scene complexity, and prioritize scanning high-density building clusters or key features; Multi-view collaborative scanning A five-lens tilt camera is used to simultaneously acquire vertical and tilt view data, and multi-source data fusion technology is used to improve the accuracy of geometric feature extraction. (3) Extraction of geometric and color information Geometric feature extraction The system extracts building height and volume parameters through point cloud density analysis, and generates a geometric model of the building surface by combining it with a 3D mesh construction algorithm. At the same time, the system records the geometric parameters of the geometric model. Spatial measurement tools were used to trim, drill holes, and add water features to the model, thereby optimizing the integrity of the geometric data. Color information is collected synchronously. During aerial photography, a high-resolution RGB sensor is used, combined with texture mapping technology to seamlessly attach multi-angle images to the surface of the geometric model, preserving real color details. At the same time, the system records the color values ​​of each color block in each model. Multispectral data fusion technology is used to compensate for color deviations in areas with uneven lighting to ensure color data consistency; (4) Data post-processing and application Lightweight and standardized output CoPre2.0 software was used to solve and optimize the scanned data, compressing the model size to 30%-50% of the original data to meet the high-efficiency loading requirements of the web client; It outputs standardized formats, supports seamless integration with BIM and GIS platforms, and enables integrated 2D and 3D management. Anomaly detection and feedback mechanism The automated quality inspection tool detects point cloud voids and uses texture loss alarm markers to scan defective areas, triggering a local rescanning process. The scanned data is reported to the backend for storage and used for subsequent model parameter analysis and separation of the corresponding model; based on the above method, the major elements in the scene are separated into individual elements; S3. Based on the feature parameters pre-set for a single tilt model, select the single tilt model that conforms to the feature parameters from the overall scene data. The feature parameters include the geometric features and color features of the single tilt model. The geometric features include volume, surface area, aspect ratio, curvature distribution, and tilt angle. The color features include the model's color mean, color variance, dominant color distribution, and block color consistency. A feature template is pre-constructed and the target parameters of the corresponding features are configured. The feature template is configured with a corresponding feature matching algorithm, including a geometric feature matching degree algorithm and a color feature matching degree algorithm. The feature parameters of each selected individual tilt model are input into the feature template; Based on the feature matching algorithm, the feature matching degree of each selected individual tilt model is calculated, and the individual tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and output. The individual tilt model corresponding to the maximum feature matching degree is: the color feature matching degree of the individual tilt model is calculated, and the average value is calculated with the corresponding geometric feature matching degree. Finally, the individual tilt model with the largest average value is selected. S4. Separate the selected single tilt model from the tilt model scene, export the separated single tilt model and save it separately.

2. The method for automatic separation of scene elements based on oblique photogrammetry model according to claim 1, characterized in that, In step S4, after deriving the separated individual tilt model, the following is also included: The base model and material map of the single tilted model are separated, the relationship between the base model and the material map is established, and the result is output and saved.

3. The method for automatic separation of scene elements based on oblique photogrammetry model according to claim 1, characterized in that, In step S3, the geometric features include the three-dimensional geometric features of the single tilted model in the three-dimensional oblique photogrammetry coordinate system, and the color features include the color range values ​​of several color blocks on the single tilted model.

4. The method for automatic separation of scene elements based on oblique photogrammetry model according to claim 1, characterized in that, The feature matching algorithm includes a geometric feature matching degree algorithm: ， in: G represents the geometric feature matching degree; These are the geometric feature parameters of the model: volume, surface area, and tilt angle. These are the preset target geometric parameters; These are the sub-weights of the geometric features, α1+α2+α3=1; This is the attenuation coefficient for the difference in tilt angle; min() and max() represent taking the minimum value and the maximum value, respectively.

5. The method for automatic separation of scene elements in an oblique photogrammetry model based on digital twins according to claim 1, characterized in that, The feature matching algorithm includes a color feature matching degree algorithm: ， in: C represents the color feature matching degree; The color feature parameters of the model are: RGB color mean vectors; The target color mean vector is preset; This represents the Euclidean distance, normalized to [0,1]. To ensure color consistency across blocks; Let β1 be the sub-weight of the color feature, where β1 + β2 = 1.

6. The method for automatic separation of scene elements in an oblique photogrammetry model based on digital twins according to claim 1, characterized in that, The method further includes: A distributed file system is used to store the feature parameters of each individual tilt model and the selected individual tilt model, including: The required feature parameters of the single tilt model are saved to the master node of the distributed file system; The master node prepares the corresponding data node for the single tilt model to be separated based on the saved information. After the single tilt model is separated, the master node identifies the feature parameters of the separated single tilt model and stores them in the corresponding data node.

7. An automatic scene element separation system for oblique photogrammetry models, wherein the automatic scene element separation system for oblique photogrammetry models is used to implement the automatic scene element separation method for oblique photogrammetry models based on digital twins as described in any one of claims 1-6, characterized in that, The system includes: The acquisition module is used to acquire and prepare tilted model scenes; The scanning module is used to scan the entire tilted model scene and obtain overall scene data; The model feature selection module is used to select a single tilted model that conforms to the feature parameters set in advance for a single tilted model from the overall scene data, wherein the feature parameters include the geometric features and color features of the single tilted model; The model element separation module is used to separate the selected individual tilted model from the tilted model scene, export the separated individual tilted model, and save it separately.

8. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 6.

Images