Digital twinning-based oblique photography model scene element automatic separation method

Abstract

The invention provides an oblique photography model scene element automatic separation method based on digital twinning, and the method comprises the steps: scanning a whole oblique model scene, and obtaining the overall data of the scene; according to feature parameters set for a single inclination model in advance, the single inclination model conforming to the feature parameters is selected from the scene overall data, and the feature parameters comprise geometric features and color features of the single inclination model; and separating the selected single inclination model from the inclination model scene, exporting the separated single inclination model, and independently storing the separated single inclination model. Scene elements of the oblique photography model can be quickly separated, ground objects such as houses and trees can be really separated from oblique measurement scenes, and the edges of the ground objects are neat and attractive. Ground feature primitive information can be obtained, operations such as ray collision detection and distance calculation can be carried out, and business application requirements are met. And through an automatic processing flow, the processing efficiency and quality of the oblique photography model are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision and three-dimensional modeling, and in particular to a method for automatically separating scene elements of an oblique photography model based on digital twins, an automatic separation system for scene elements of an oblique photography model, an electronic device, and a computer-readable storage medium. Background Art

[0002] Oblique photography is an emerging high-tech in the field of international surveying and remote sensing. It uses multiple sensors on the same flight platform to simultaneously collect images from five different angles: vertical, front, left, right and rear. This technology can obtain rich texture information on the side of the object, and through efficient and automated 3D modeling technology, quickly build a true 3D space scene with accurate geographic location information of the object.

[0003] However, in digital twin applications, it is necessary to individually process objects such as houses and trees in oblique photography models in order to perform secondary editing of single elements. The individualization methods in the existing technology often have problems such as jagged boundaries of objects and inconsistent boundaries of objects at different accuracy levels, which cannot meet the actual application requirements. Summary of the invention

[0004] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a method for automatically separating scene elements of an oblique photography model based on digital twins is provided, the method being implemented by an electronic device, and the method comprising: S1, prepare the tilt model scene; S2, scanning the entire tilt model scene to obtain overall scene data; S3, according to the characteristic parameters pre-set for the single tilt model, selecting the single tilt model that meets the characteristic parameters from the overall scene data, wherein the characteristic parameters include geometric features and color features of the single tilt model; S4. Separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

[0005] Preferably, in step S4, after deriving the separated single tilt model, the method further comprises: The base model and the material map of the single tilted model are separated, an association relationship between the base model and the material map is established, and the model is output and saved.

[0006] Preferably, in step S3, the geometric features include three-dimensional geometric features of the single tilted model in a three-dimensional tilted photography space coordinate system, and the color features include color range values ​​of a plurality of color blocks on the single tilted model.

[0007] Preferably, in step S3, after selecting the single tilt model that meets the characteristic parameters pre-set for the single tilt model from the overall scene data, the method further comprises: Pre-constructing a feature template and configuring target parameters of corresponding features, wherein the feature template is configured with a corresponding feature matching algorithm; Inputting the selected characteristic parameters of each of the single tilt models into the characteristic template; The feature matching degree of each selected single tilt model is calculated based on the feature matching algorithm, and the single tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and outputted.

[0008] Preferably, the feature matching algorithm includes a geometric feature matching algorithm: , in: G is the geometric feature matching degree; They are the geometric characteristic parameters of the model: volume, surface area, and tilt angle; are the preset target geometric parameters respectively; are the sub-weights of the geometric features, α 1 +α 2 +α 3 =1; is the attenuation coefficient of the tilt angle difference; min() and max() represent the minimum and maximum values ​​respectively.

[0009] Preferably, the feature matching algorithm includes a color feature matching algorithm: , in: C is the color feature matching degree; Is the color feature parameter of the model: RGB color mean vector; is the preset target color mean vector; Represents Euclidean distance, normalized to [0,1]; is the color consistency of the block (calculated by histogram similarity); is the sub-weight of the color feature (β 1 +β 2=1).

[0010] Preferably, the method further comprises: A distributed file system is used to store the characteristic parameters of each single tilt model and the selected corresponding single tilt model, including: Saving the required characteristic parameters of the single tilt model to the master node of the distributed file system; The master node prepares a corresponding data node for the single tilt model to be separated according to the saved information. After the separated single tilt model is exported, the master node identifies the characteristic parameters of the separated single tilt model and stores them in the corresponding data node.

[0011] On the other hand, a system for automatically separating scene elements of an oblique photography model is provided, and the system is applied to a method for automatically separating scene elements of an oblique photography model based on digital twins, and the system comprises: A collection module, used to collect and prepare tilt model scenes; A scanning module, used for scanning the entire tilt model scene to obtain overall scene data; A model feature selection module, used for selecting the single tilt model that meets the feature parameters pre-set for the single tilt model from the overall scene data, wherein the feature parameters include geometric features and color features of the single tilt model; The model element separation module is used to separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

[0012] On the other hand, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the methods for automatically separating scene elements of an oblique photography model based on digital twins is implemented.

[0013] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for automatic separation of scene elements of oblique photography models based on digital twins.

[0014] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention obtains the overall scene data by scanning the entire oblique model scene; selects the single oblique model that meets the characteristic parameters pre-set for the single oblique model from the overall scene data, wherein the characteristic parameters include the geometric features and color features of the single oblique model; separates the selected single oblique model from the oblique model scene, derives the separated single oblique model and saves it separately. It is capable of quickly separating the oblique photography model scene elements, and can achieve the real separation of houses, trees and other objects from the oblique measurement scene, and the edges of the objects are neat and beautiful. It is capable of obtaining object primitive information, performing operations such as ray collision detection and distance calculation, and meeting business application requirements. Through the automated processing flow, the efficiency and quality of oblique photography model processing are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 It is a flow chart of a method for automatically separating scene elements of an oblique photography model based on digital twins provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of an application process provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a tilt model scene provided by an embodiment of the present invention; Figure 4 4a is a characteristic diagram of a building model provided by an embodiment of the present invention (4a is a geometric feature, 4b is a color feature); Figure 5 is a color block schematic diagram of a parking area provided by an embodiment of the present invention; Figure 6 is a schematic diagram of selecting vegetation in a scene according to color provided by an embodiment of the present invention; Figure 7 is a schematic diagram of separation of a single vegetation tilt model provided by an embodiment of the present invention; Figure 8 is a schematic diagram of separation of a road model provided by an embodiment of the present invention; Fig. 9 It is a block diagram of a system for automatically separating scene elements of an oblique photography model provided by an embodiment of the present invention; Fig.10 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0018] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0019] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0020] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0021] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0022] The embodiment of the present invention provides a method for automatically separating scene elements of an oblique photography model based on digital twins, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the method for automatically separating scene elements of the oblique photography model based on digital twins is shown. The processing flow of the method may include the following steps: S1, prepare the tilt model scene; S2, scanning the entire tilt model scene to obtain overall scene data; S3, according to the characteristic parameters pre-set for the single tilt model, selecting the single tilt model that meets the characteristic parameters from the overall scene data, wherein the characteristic parameters include geometric features and color features of the single tilt model; S4. Separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

[0023] The present invention proposes a method for separating scene elements of an oblique photography model, aiming to achieve the real separation of objects such as houses, vegetation, water surface, roads, etc. from the oblique measurement scene, and ensure that the edges of the objects are neat and beautiful, and can obtain the object primitive information, perform operations such as ray collision detection and distance calculation.

[0024] Combined with Figure 2 As shown in the figure, it is an application flow chart of the present invention. First, the user prepares the oblique photography model scene, as shown in the figure. Figure 3 The tilted model scene shown includes water surface, vegetation, and buildings.

[0025] Here, by setting characteristic parameters for the required (to be separated) single tilted model, the characteristic parameters include the geometric characteristics and color characteristics of the single tilted model. According to the set characteristic parameters, the tilted model scene is scanned and the single tilted model that meets the set characteristic parameters is selected, marked and exported.

[0026] Therefore, firstly, the geometric features and color features of the oblique photography model to be processed are obtained.

[0027] The geometric features include the three-dimensional geometric features of the single tilt model in the three-dimensional tilt photography space coordinate system, which is the elevation information of the model surface. The geometric features in the scene are some feature types obtained by calculating the spatial position of the model in the scene along the XYZ axis. Figure 4 The geometric features of the building model shown in 4a in the figure are the model of the boundary range of the height difference of more than 2 meters on the Z axis, and the model part with continuous planes. The building model that meets this part of the geometric features will be separated as a separate building model (a tilted model scene may contain several similar building models, such as Figure 3 Several buildings overlapping in the image).

[0028] If the model needs to meet the color feature, the corresponding color feature parameters can also be set. The color feature includes the color range values ​​of several color blocks on the single tilted model. For example, the color of a block of a certain building model should also meet a certain color range value. Only models that meet both geometric features and color features can be used as the final separation model. Figure 4 The color of each block of the building model shown in 4b in FIG. 4 presents a corresponding color. If the color of each model block (referred to as color block) meets the preset color range value, it is regarded as a qualified model and separated.

[0029] As for the color feature, if the color feature is satisfied, then the color block that satisfies the corresponding color feature can be output. Figure 5The parking area shown (if there is a car, for example, it needs to meet the following requirements: an independent raised part model below 2 meters on the Z axis, with a length and width range of: 2-5 meters long; 1.3-1.9 meters wide, and then meet the characteristics of a single block of color). 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.

[0030] Therefore, by presetting the geometric features and color features of the individual oblique models (such as buildings, roads, water surfaces, etc.) that need to be separated in advance, the selected buildings, trees and other partial models can be separated from the oblique photography model scene. Finally, each separated model is exported and the separated oblique models are saved as separate data assets.

[0031] Preferably, in step S4, after deriving the separated single tilt model, the method further comprises: The base model and the material map of the single tilted model are separated, an association relationship between the base model and the material map is established, and the model is output and saved.

[0032] In order to further refine the application of separated elements, this part also separates the base model and material map of the separated single tilted model, establishes the association between the base model and the material map, and outputs and saves it. In this way, the base model of each single tilted model and the material map attached to it can be obtained. Specifically, it can be operated in conjunction with the model surface mapping technology (creating texture: 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, the model software automatically assigns initial texture coordinates to the vertices of the model, but they can also be manually edited and adjusted to achieve better results. Texture mapping: Map the texture image to the surface of the model. In graphics software, you can load the texture image into the texture channel of the model material and associate the texture coordinates with the vertices of the model. When rendering the model, the computer obtains the pixels at the corresponding positions on the texture image based on the texture coordinates, and draws them to the corresponding positions on the model surface. Texture adjustment: Adjust the texture to achieve the desired effect).

[0033] like Figure 6 The following figure shows an oblique model scene (oblique photography). Now we want to separate the vegetation in the scene to form a single oblique model.

[0034] Now we want to separate the vegetation in the scene and form a single oblique model. By scanning the entire oblique model scene, we can obtain the overall scene data, that is, obtain the geometric feature information and color information of each independent model in the oblique photography scene (such as the geometric data and color data of several buildings). For details, please refer to the following steps: 1. Data preprocessing and scene analysis Scene data standardization The original oblique photography 3D model is formatted uniformly (such as converted to OSGB or S3MB format), and the oblique storage function of SuperMap iDesktop is used to compress data and repair anomalies to ensure model integrity and lightweight requirements.

[0035] 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.

[0036] Model individualization preprocessing‌ By adopting dynamic singulation technology and superimposing oblique photography models on vector surface layers, each independent building is given a unique ID attribute, which enables rapid separation of the target model.

[0037] Use cutting and singulation or algorithm recognition (such as morphological feature matching) to separate overlapping models in complex scenes and reduce subsequent scanning redundancy.

[0038] 2. Scanning path optimization design Path planning strategy Regional block scanning: Divide the grid area according to the complexity of the scene, and give priority to scanning high-density buildings or key features (such as main roads and landmark buildings). The administrator can set the planning logic of the scanning task.

[0039] Multi-view collaborative scanning A five-lens tilt camera is used to synchronously collect vertical and oblique viewing angle data, and the accuracy of geometric feature extraction is improved through multi-source data fusion technology (such as superposition of point cloud and BIM model).

[0040] For the sides of complex buildings (such as glass curtain walls and concave and convex structures), a low-altitude supplementary shooting strategy is adopted, combined with the on-board lidar to supplement the detailed texture information.

[0041] 3. Geometry and Color Information Extraction Geometric feature extraction Through point cloud density analysis, building height, volume and other parameters are extracted, and combined with three-dimensional mesh construction algorithms (such as Delaunay triangulation) to generate a building surface geometric model. At the same time, the system will record the geometric parameters of the geometric model.

[0042] Use spatial measurement tools (such as the "object operation" function of SuperMap iDesktop) to perform model clipping, hole digging and water surface processing to optimize the integrity of geometric data.

[0043] Color information synchronous collection During the aerial photography process, a high-resolution RGB sensor is used, combined with texture mapping technology, to seamlessly fit multi-angle images to the surface of the geometric model, preserving the true color details. At the same time, the system records the color value of each color block in each model.

[0044] For areas with uneven lighting (such as shadow-covered areas), multi-spectral data fusion technology is used to compensate for color deviation and ensure color data consistency.

[0045] 4. Data Post-processing and Application Lightweight and standardized output‌ Use the CoPre2.0 software to solve and optimize the scanned data, compressing the model volume to 30%-50% of the original data to meet the efficient loading requirements of the Web end.

[0046] Output standardized formats (such as S3MB, I3S), support seamless connection with BIM and GIS platforms, and realize 2D and 3D integrated management.

[0047] Anomaly detection and feedback mechanism‌ Use automated quality inspection tools (such as point cloud hole detection and texture missing alarm) to mark scan defect areas and trigger the local rescanning process.

[0048] The scanned data is reported to the background for storage and used for subsequent model parameter analysis and separation of the corresponding models.

[0049] Based on the above ideas, we first scan the scene to obtain the color information in the scene. According to the pre-entered green range value, we select the green vegetation in the scene. Then we separate the selected plant parts to form the following Figure 7 A single tilt model is shown. Figure 8 The roads shown can be selected and separated by preset geometric features, etc.

[0050] Therefore, this method can separate the major elements in the scene into a single element. It is convenient to use it flexibly in various scenes. Through this solution, it is possible to truly separate objects such as houses, vegetation, water surface, roads, etc. from the tilt measurement scene, and ensure that the edges of the objects are neat and beautiful. It is possible to obtain the information of the object primitives, and perform operations such as ray collision detection and distance calculation.

[0051] When separating the models, Figure 6As shown, it contains several building models or vegetation, so when separated, several corresponding single tilt models will be output (such as Figure 7 In order to select a single tilt model that satisfies the user, this department also designs a model that performs feature matching calculations based on the feature parameters set by the model and outputs a model whose feature matching degree meets the user's requirements.

[0052] Preferably, in step S3, after selecting the single tilt model that meets the characteristic parameters pre-set for the single tilt model from the overall scene data, the method further comprises: Pre-constructing a feature template and configuring target parameters of corresponding features, wherein the feature template is configured with a corresponding feature matching algorithm; Inputting the selected characteristic parameters of each of the single tilt models into the characteristic template; The feature matching degree of each selected single tilt model is calculated based on the feature matching algorithm, and the single tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and outputted.

[0053] In the background system, a "feature template" is pre-constructed, through which the geometric parameters and / or color parameters of each selected single tilt model can be traversed and read, and the feature matching degree of each single tilt model can be calculated through the corresponding configured feature matching algorithm, and the single tilt model corresponding to the maximum feature matching degree can be output.

[0054] In this way, the model required by the user can be separated from several single tilted models of a building and put into subsequent use (for ray collision detection, distance calculation, etc.). It is also possible to sort the feature matching degree and output the top models.

[0055] The following will provide a method for calculating the geometric feature matching degree and the color feature matching degree. According to the user's selection requirements for the corresponding single tilt model, the corresponding algorithm can be scheduled for use.

[0056] Preferably, the feature matching algorithm includes a geometric feature matching algorithm: , in: G is the geometric feature matching degree; They are the geometric characteristic parameters of the model: volume, surface area, and tilt angle; are the preset target geometric parameters respectively; are the sub-weights of the geometric features, α 1 +α2 +α 3 =1; is the attenuation coefficient of the tilt angle difference; min() and max() represent the minimum and maximum values ​​respectively.

[0057] Preferably, the feature matching algorithm includes a color feature matching algorithm: , in: C is the color feature matching degree; Is the color feature parameter of the model: RGB color mean vector; is the preset target color mean vector; Represents Euclidean distance, normalized to [0,1]; is the color consistency of the block (calculated by histogram similarity); is the sub-weight of the color feature (β 1 +β 2 =1).

[0058] The algorithm steps are as follows: First, data preprocessing and feature extraction: ‌Geometric feature extraction‌: Calculate the geometric feature parameters of each candidate model, including volume, surface area length, width and height ratio, curvature distribution, tilt angle, etc. ‌Color feature extraction‌: Calculate the color feature parameters of each candidate model, including color mean, color variance, main color distribution, block color consistency, etc.; Second, input the data: Inputting the characteristic parameters (three-dimensional geometric data (point cloud or mesh) and corresponding block color data (RGB or HSV)) of each single tilt model selected from the tilt model scene into the corresponding template; Finally, the feature parameters of the selected single tilt model are calculated based on the feature matching algorithm in the corresponding template, and the corresponding feature matching degree is calculated, and the single tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and output.

[0059] For example, for buildings, we can only calculate the geometric feature matching degree, perform geometric feature matching degree calculation on each selected single tilt model of the building, output the single tilt model of the building with the maximum geometric feature matching degree and save it.

[0060] If it is also necessary to filter according to the building color blocks, the color feature matching degree of each selected single tilted building model can be calculated, and the average of the corresponding geometric feature matching degree can be calculated. Finally, the single tilted building model with the largest average value can be selected and saved.

[0061] Therefore, the required single tilt model can be derived according to the user definition.

[0062] Preferably, the method further comprises: A distributed file system is used to store the characteristic parameters of each single tilt model and the selected corresponding single tilt model, including: Saving the required characteristic parameters of the single tilt model to the master node of the distributed file system; The master node prepares a corresponding data node for the single tilt model to be separated according to the saved information. After the separated single tilt model is exported, the master node identifies the characteristic parameters of the separated single tilt model and stores them in the corresponding data node.

[0063] Distributed file system: HDFS, with master nodes (management nodes) and data nodes (storage nodes). Therefore, this part can be combined with the distributed file system HDFS to store the exported individual tilt models and their characteristics separately, so as to facilitate the subsequent management and classification application of each individual tilt model. Specifically: This technical solution uses a distributed file system to store and manage the characteristic parameters of each single tilt model (such as a building model diagram) and the corresponding model file. The system is mainly composed of a distributed file system, a master node, a data node, and a model management and export module.

[0064] Distributed file system construction Select a suitable distributed file system (such as Hadoop HDFS, Ceph, etc.), and build and configure it according to system requirements.

[0065] Ensure that the distributed file system has high availability, high throughput, and data fault tolerance.

[0066] Feature parameters are saved to the master node‌ When a single tilt model needs to be stored, the characteristic parameters of the model are first extracted.

[0067] Feature parameters may include the model's geometric information, texture information, material information, etc.

[0068] The extracted feature parameters are saved in a specific format (such as JSON, XML or binary format) to the master node of the distributed file system.

[0069] The master node is responsible for receiving and storing these characteristic parameters and recording their storage location and related information.

[0070] Preparing Data Nodes‌ The master node prepares corresponding data nodes for the single tilt model to be separated according to the saved characteristic parameter information.

[0071] Data nodes are nodes in the distributed file system that are used to store actual data. They are responsible for storing the original files or processed files of the model.

[0072] The master node selects a suitable data node to store the model file to be exported based on the system's load balancing strategy, data node capacity and other factors.

[0073] Export and save separate models‌ The Model Management and Export module is responsible for exporting individual tilted models to specific file formats (such as OBJ, FBX, COLLADA, etc.).

[0074] The exported model file is transferred to the previously prepared data node for storage.

[0075] During the storage process, data nodes ensure the integrity and consistency of file data.

[0076] Feature parameters are stored in corresponding data nodes‌ After the model file is successfully stored, the master node identifies and extracts the previously saved feature parameters.

[0077] The master node associates these feature parameters with the model file and stores them on the previously prepared data node, or in a location that is the same as or associated with the model file.

[0078] When storing, the feature parameters can be associated with the model file in the form of metadata to facilitate subsequent retrieval and use.

[0079] Specifically, it can be understood and implemented in conjunction with the HDFS system architecture.

[0080] This technical solution uses a distributed file system to store and manage the characteristic parameters of a single tilt model and the corresponding model files, thereby achieving efficient storage, retrieval and use of model data.

[0081] Fig. 9 The present invention is a block diagram of a system for automatically separating scene elements of an oblique photography model according to an exemplary embodiment. The system is used for an automatic separation method of scene elements of an oblique photography model based on digital twins. Fig. 9 , the system comprises: A collection module, used to collect and prepare tilt model scenes; A scanning module, used for scanning the entire tilt model scene to obtain overall scene data; A model feature selection module, used for selecting the single tilt model that meets the feature parameters pre-set for the single tilt model from the overall scene data, wherein the feature parameters include geometric features and color features of the single tilt model; The model element separation module is used to separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

[0082] Please understand the functions and interactions of the above modules in conjunction with the corresponding steps of the above methods, and will not be repeated here.

[0083] Fig.10 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig.10 As shown, the electronic device may include the above Fig. 9 The system for automatically separating scene elements of the oblique photography model is shown. Optionally, the electronic device 410 may include a first processor 2001.

[0084] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0085] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0086] Combine the following Fig.10 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0087] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0088] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Fig.10 CPU0 and CPU1 are shown in FIG.

[0089] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Fig.10 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0090] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0091] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Fig.10 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0092] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0093] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Fig.10The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0094] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Fig.10 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0095] It should be noted that Fig.10 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0096] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the automatic separation method of scene elements of the oblique photography model based on digital twins described in the above method embodiment, and will not be repeated here.

[0097] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0098] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0099] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of 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, the process or function described in the embodiment of the present invention is generated in whole or in part. 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 computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0100] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0101] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0102] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean 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.

[0103] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] In the several embodiments provided by the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the system or unit, which can be electrical, mechanical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0108] If the functions are implemented in the form of 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 the present invention, 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. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0109] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for automatically separating scene elements of an oblique photography model based on digital twins, characterized in that: The method comprises: S1, prepare the tilt model scene; S2, scanning the entire tilt model scene to obtain overall scene data; S3, according to the characteristic parameters pre-set for the single tilt model, selecting the single tilt model that meets the characteristic parameters from the overall scene data, wherein the characteristic parameters include geometric features and color features of the single tilt model; S4. Separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

2. The method for automatically separating scene elements of an oblique photography model based on digital twins according to claim 1 is characterized in that: In step S4, after deriving the separated single tilt model, the method further includes: The base model and the material map of the single tilted model are separated, an association relationship between the base model and the material map is established, and the model is output and saved.

3. The method for automatically separating scene elements of an oblique photography model based on digital twins 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 tilted photography space coordinate system, and the color features include the color range values ​​of a plurality of color blocks on the single tilted model.

4. The method for automatically separating scene elements of an oblique photography model based on digital twins according to claim 3 is characterized in that: In step S3, after selecting the single tilt model that meets the characteristic parameters pre-set for the single tilt model from the overall scene data, the method further includes: Pre-constructing a feature template and configuring target parameters of corresponding features, wherein the feature template is configured with a corresponding feature matching algorithm; Inputting the selected characteristic parameters of each of the single tilt models into the characteristic template; The feature matching degree of each selected single tilt model is calculated based on the feature matching algorithm, and the single tilt model corresponding to the maximum feature matching degree is selected as the target tilt model and outputted.

5. The method for automatically separating scene elements of an oblique photography model based on digital twins according to claim 4 is characterized in that: The feature matching algorithm includes a geometric feature matching algorithm: ， in: G is the geometric feature matching degree; They are the geometric characteristic parameters of the model: volume, surface area, and tilt angle; are the preset target geometric parameters respectively; They are the sub-weights of geometric features, α1+α2+α3=1; is the attenuation coefficient of the tilt angle difference; min() and max() represent the minimum and maximum values ​​respectively.

6. The method for automatically separating scene elements of an oblique photography model based on digital twins according to claim 4 is characterized in that: The feature matching algorithm includes a color feature matching algorithm: ， in: C is the color feature matching degree; Is the color feature parameter of the model: RGB color mean vector; is the preset target color mean vector; Represents Euclidean distance, normalized to [0,1]; For block color consistency; is the sub-weight of the color feature (β1+β2=1).

7. The method for automatically separating scene elements of an oblique photography model based on digital twins according to claim 1, characterized in that: The method further comprises: A distributed file system is used to store the characteristic parameters of each single tilt model and the selected corresponding single tilt model, including: Saving the required characteristic parameters of the single tilt model to the master node of the distributed file system; The master node prepares a corresponding data node for the single tilt model to be separated according to the saved information. After the separated single tilt model is exported, the master node identifies the characteristic parameters of the separated single tilt model and stores them in the corresponding data node.

8. A system for automatically separating oblique photography model scene elements, the system for automatically separating oblique photography model scene elements is used to implement the method for automatically separating oblique photography model scene elements based on digital twins as claimed in any one of claims 1 to 7, characterized in that: The system comprises: A collection module, used to collect and prepare tilt model scenes; A scanning module, used for scanning the entire tilt model scene to obtain overall scene data; A model feature selection module, used for selecting the single tilt model that meets the feature parameters pre-set for the single tilt model from the overall scene data, wherein the feature parameters include geometric features and color features of the single tilt model; The model element separation module is used to separate the selected single tilted model from the tilted model scene, export the separated single tilted model and save it separately.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images