Multi-source data-based city-level live-action three-dimensional data processing method and terminal

Abstract

The invention provides a city-level live-action three-dimensional data processing method based on multi-source data and a terminal. The method comprises the following steps: firstly, acquiring a building design drawing, indoor point cloud data, an airborne image and laser radar load data; building an indoor three-dimensional model of the building according to the building design drawing and the indoor point cloud data, and building an outdoor three-dimensional model of the building according to the airborne image and the laser radar load data; determining indoor and outdoor time difference vectors and spatial difference vectors according to airborne images, laser radar load data and indoor point cloud data, and fusing the building indoor three-dimensional model and the building outdoor three-dimensional model to obtain an indoor and outdoor integrated model; and finally, texture mapping is carried out to obtain a city-level live-action three-dimensional model. In a traditional indoor and outdoor building fusion process, city transition caused by a relatively long data acquisition period is considered, and a corresponding time difference vector and a corresponding space difference vector are calculated, so that more accurate indoor and outdoor integrated modeling is carried out.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional digitization, and in particular relates to a city-level real-scene three-dimensional data processing method and terminal based on multi-source data. Background Art

[0002] The scene 3D model is the data foundation of technologies such as 3D geographic information services, building information models, and virtual reality. The city-level indoor and outdoor 3D integration is a comprehensive concept of geographic information and spatial data presentation. It integrates the 3D spatial information of the city's outdoor macro-architecture, topography, and traffic roads with the 3D information of the detailed structure and facility layout of indoor buildings in a unified system framework. For example, in a large commercial center area, the outdoor 3D model shows the appearance, height, surrounding parking lots, roads, and greenery of the commercial center building; the indoor 3D model can show the store distribution, channel direction, elevator and staircase locations on each floor of the shopping mall in detail.

[0003] At present, indoor and outdoor integration is usually based on a single building or street-level buildings. Due to the long data collection cycle and large number of collection times at the city level, as well as the complex urban environment and dense buildings, the accuracy of ordinary indoor and outdoor integration methods is low in the process of city-level three-dimensional integration. Summary of the invention

[0004] In view of this, the present invention provides a city-level real-scene three-dimensional data processing method and terminal based on multi-source data, aiming to solve the problem of low accuracy of indoor and outdoor integration methods in the city-level three-dimensional integration process in the prior art.

[0005] A first aspect of an embodiment of the present invention provides a method for processing city-level real-scene three-dimensional data based on multi-source data, comprising:

[0006] Obtain architectural design drawings, indoor point cloud data, airborne images, and lidar payload data;

[0007] Build a 3D model of the building's interior based on the architectural design and indoor point cloud data, and build a 3D model of the building's exterior based on airborne images and LiDAR payload data;

[0008] Determine the time difference vector and space difference vector of indoor and outdoor areas according to the airborne image, laser radar payload data and indoor point cloud data;

[0009] According to the time difference vector and the space difference vector, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are merged to obtain an indoor and outdoor integrated model;

[0010] Texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene 3D model.

[0011] In a possible implementation, determining the time difference vector and the space difference vector between indoor and outdoor based on the airborne image, the laser radar payload data and the indoor point cloud data includes:

[0012] Determine urban change information based on airborne images and urban change prediction models;

[0013] According to the urban change information, the lidar payload data and indoor point cloud data are processed to determine the time difference vector and space difference vector between indoor and outdoor.

[0014] In a possible implementation, the laser radar load data and the indoor point cloud data are processed according to the urban change information to determine the time difference vector and the space difference vector between indoor and outdoor, including:

[0015] Perform data registration on the LiDAR payload data and indoor point cloud data to obtain indoor and outdoor data under unified coordinates;

[0016] According to the city change information, obtain the difference data from the indoor data and outdoor data in the unified coordinate system;

[0017] Based on the difference data, a time difference vector and a space difference vector are determined.

[0018] In a possible implementation, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are fused according to the time difference vector and the space difference vector to obtain an indoor and outdoor integrated model, including:

[0019] Determine the fusion weight according to the time difference vector and the space difference vector;

[0020] According to the fusion weight, the indoor 3D model of the building and the outdoor 3D model of the building are fused to obtain an indoor and outdoor integrated model.

[0021] In a possible implementation, texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene 3D model, including:

[0022] Acquire building texture data from airborne images;

[0023] Determine the correspondence between the model surface and the building texture data;

[0024] According to the texture relationship, the building texture data is mapped to the indoor and outdoor integrated model to obtain a city-level real-scene 3D model.

[0025] In a possible implementation, a building interior 3D model is constructed based on the building design drawing and the indoor point cloud data, including:

[0026] Create a basic interior model based on the architectural design drawings;

[0027] After preprocessing, the indoor point cloud data is added to the indoor basic model to obtain the building interior 3D model.

[0028] In one possible implementation, a three-dimensional outdoor model of a building is constructed based on airborne images and lidar payload data, including:

[0029] Create an outdoor base model based on LiDAR load data;

[0030] The basic model is corrected and optimized according to the airborne images to obtain the outdoor three-dimensional model of the building.

[0031] A second aspect of an embodiment of the present invention provides a city-level real-scene three-dimensional data processing device based on multi-source data, comprising:

[0032] The acquisition module is used to acquire architectural design drawings, indoor point cloud data, airborne images, and lidar payload data;

[0033] A construction module is used to construct a 3D model of the interior of the building based on the architectural design drawings and indoor point cloud data, and to construct a 3D model of the exterior of the building based on airborne images and LiDAR payload data;

[0034] A determination module, used for determining the time difference vector and the space difference vector of indoor and outdoor according to the airborne image, the laser radar load data and the indoor point cloud data;

[0035] A fusion module is used to fuse the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building according to the time difference vector and the space difference vector to obtain an indoor and outdoor integrated model;

[0036] The mapping module is used to perform texture mapping on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model.

[0037] A third aspect of an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the city-level real-scene three-dimensional data processing method based on multi-source data of the first aspect above are implemented.

[0038] A fourth aspect of an embodiment of the present invention provides a city-level real-scene three-dimensional data processing system, including a data acquisition device, a point cloud acquisition device camera, a laser radar and a terminal as described in the third aspect above.

[0039] The fifth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the city-level real-scene three-dimensional data processing method based on multi-source data as described in the first aspect above.

[0040] The city-level real-scene three-dimensional data processing method and terminal based on multi-source data provided by the embodiment of the present invention first obtain architectural design drawings, indoor point cloud data, airborne images and laser radar load data; then build the indoor three-dimensional model of the building according to the architectural design drawings and indoor point cloud data, and build the outdoor three-dimensional model of the building according to the airborne image and laser radar load data; then determine the time difference vector and space difference vector of indoor and outdoor according to the airborne image, laser radar load data and indoor point cloud data; then fuse the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building according to the time difference vector and the space difference vector to obtain an indoor and outdoor integrated model; finally, texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model. In the traditional indoor and outdoor building fusion process, the present invention takes into account the urban changes caused by the long data collection cycle, calculates the corresponding time difference vector and space difference vector, and thus performs more accurate indoor and outdoor integrated modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.

[0042] Figure 1 is a schematic diagram of the structure of a city-level real-scene three-dimensional data processing system provided by an embodiment of the present invention;

[0043] Figure 2 is a flowchart of an implementation method of a city-level real-scene three-dimensional data processing method based on multi-source data provided by an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of the structure of a city-level real-scene three-dimensional data processing device based on multi-source data provided by an embodiment of the present invention;

[0045] Figure 4 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0047] Figure 1The structure diagram of the city-level real-scene 3D data processing system provided by the embodiment of the present invention includes a data acquisition device 11, a point cloud acquisition device 12, a camera 13, a laser radar 14 and a terminal 15.

[0048] like Figure 1 As shown, the data acquisition device 11 usually has a high-resolution scanning or digital input function, which can accurately obtain the image information of the paper architectural design drawing. It may have functions such as automatic correction and image enhancement to ensure that the collected design drawings are clear and accurate. It supports multiple file formats for output, which is convenient for subsequent processing and storage. The point cloud acquisition device 12 generally adopts laser scanning technology, which can quickly and accurately obtain the three-dimensional point cloud data of the indoor space. It has high-precision measurement capabilities and can capture the details and shapes of indoor objects. It may have functions such as automatic splicing and noise filtering to improve the quality of point cloud data. The camera 13 is usually a high-resolution digital camera installed on an airborne platform such as an aircraft or a drone. It has good optical performance and stable shooting functions, and can take clear and stable images during flight. It may have functions such as automatic focus and exposure control to adapt to different lighting conditions. The laser radar 14 uses a laser beam to scan outdoor targets, measure the distance and reflection intensity of the target, and generate high-precision three-dimensional point cloud data. It has the characteristics of long-distance measurement capability, high resolution and fast scanning speed. It may have functions such as multi-angle scanning and automatic calibration to adapt to different terrains and environments. Terminal 15 receives data from various data acquisition devices, including architectural design drawings, indoor point cloud data, airborne images and outdoor LiDAR payload data. It has a large-capacity storage device that can safely store this data for subsequent processing and analysis.

[0049] Figure 2 1 is a flowchart of the implementation of the city-level real-scene 3D data processing method based on multi-source data provided by an embodiment of the present invention. Figure 2 As shown, in some embodiments, a method for processing city-level real-scene 3D data based on multi-source data includes:

[0050] S210, acquiring architectural design drawings, indoor point cloud data, airborne images, and laser radar payload data.

[0051] S220, constructing a three-dimensional indoor model of the building according to the architectural design drawing and the indoor point cloud data, and constructing a three-dimensional outdoor model of the building according to the airborne image and the laser radar payload data.

[0052] In some embodiments, a building interior three-dimensional model is constructed based on architectural design drawings and indoor point cloud data, including: creating an indoor basic model based on the architectural design drawings; pre-processing the indoor point cloud data and adding it to the indoor basic model to obtain the building interior three-dimensional model.

[0053] In the embodiment of the present invention, the architectural design drawings need to be sorted out first, specifically to ensure the accuracy and completeness of the design drawings, including plan views, section views, elevation views, etc., to identify key dimension information, wall locations, door and window locations, etc.

[0054] Then the indoor point cloud data needs to be processed. Specifically, the collected point cloud data needs to be denoised to remove abnormal points and noise points to improve data quality. Point cloud registration is performed to unify the point cloud data collected from different perspectives into one coordinate system.

[0055] Then, we create the basic model of the interior based on the architectural design. Using 3D modeling software, we create basic structures such as walls, floors, and roofs according to the dimensions and layout in the design. We also place elements such as doors, windows, and stairs accurately to ensure that they are consistent with the design. Figure 1 To.

[0056] Finally, the processed point cloud data is imported into the modeling software. The basic model is corrected and refined through the point cloud data to make the model more accurately reflect the actual indoor space. For example, the flatness of the wall, the size and position of the doors and windows, etc. are adjusted according to the point cloud data. At the same time, details are added to add interior decoration elements to the model, such as furniture, lamps, decorations, etc. Material mapping can be performed according to actual needs to enhance the realism of the model.

[0057] After modeling is completed, model optimization and verification are required. Specifically, the geometric accuracy of the model is checked to eliminate possible errors and discontinuities. The model is simplified and optimized to improve rendering efficiency and performance. The constructed 3D model is compared with the actual indoor scene to check if there are any differences. Relevant personnel can also be invited to evaluate and provide feedback to ensure the accuracy and practicality of the model.

[0058] In some embodiments, an outdoor three-dimensional model of a building is constructed based on airborne images and lidar payload data, including: creating an outdoor basic model based on the lidar payload data; and correcting and optimizing the basic model based on the airborne images to obtain an outdoor three-dimensional model of the building.

[0059] In the embodiment of the present invention, it is first necessary to sort out the airborne images. Specifically, the image quality is checked to ensure clarity and remove obviously blurred or distorted images. The images are geometrically corrected to make the geometric relationship between different images more accurate. Key feature points in the images, such as corners and edges of buildings, are extracted to prepare for subsequent data fusion.

[0060] Next, the lidar payload data needs to be processed. Specifically, the noise points in the lidar data are removed to improve the accuracy of the data. Point cloud registration is performed to unify the point cloud data of different scanning angles into one coordinate system. Ground points and building points are classified to better build the model.

[0061] Then, we create an outdoor basic model based on the LiDAR data. Specifically, we use the elevation information of the LiDAR point cloud data to construct the approximate shape and height of the building. We determine the edges and outlines of the building through the density and distribution of the point cloud. We segment different parts of the building, such as the roof and walls, for more detailed modeling.

[0062] Finally, the airborne image feature points are fused. Specifically, the feature points extracted from the airborne image are matched with the LiDAR point cloud data. The geometric shape and position of the building model are further optimized using the matched feature points. At the same time, details are added. Specifically, some details such as windows and balconies are added to the building model based on the LiDAR data and image feature points. The position and shape of these details can be determined by analyzing the local features of the point cloud data.

[0063] After modeling is completed, model optimization and verification are required. Specifically, the geometric accuracy of the model is checked to eliminate possible errors and discontinuities. The model is simplified and optimized to remove unnecessary details and improve the performance of the model. The scale and size of the model are adjusted to make it more consistent with the actual building. The constructed 3D model is compared with the actual scene to check if there are any obvious differences. Other measurement data or reference materials can also be used for verification.

[0064] S230, determining the time difference vector and space difference vector between indoor and outdoor according to the airborne image, the laser radar payload data and the indoor point cloud data.

[0065] In some embodiments, the time difference vector and space difference vector of indoor and outdoor are determined based on airborne images, lidar payload data and indoor point cloud data, including: determining city change information based on airborne images and a city change prediction model; based on the city change information, processing the lidar payload data and indoor point cloud data to determine the time difference vector and space difference vector of indoor and outdoor.

[0066] In the embodiment of the present invention, the city change prediction model can be a neural network model, a deep learning model, etc., which is not limited here. The airborne image provides visual information about the city, and the city change prediction model may infer the changes that have occurred in the city within a specific time period by analyzing the features, patterns, and historical data in the image, such as the emergence of new buildings, the demolition of old buildings, and the change of land use. By classifying and arranging these change information according to preset labels, the city change information can be obtained.

[0067] In some embodiments, according to the city change information, the lidar load data and the indoor point cloud data are processed to determine the time difference vector and the space difference vector between indoor and outdoor, including: performing data registration on the lidar load data and the indoor point cloud data to obtain indoor data and outdoor data under a unified coordinate system; according to the city change information, obtaining difference data from the indoor data and outdoor data under a unified coordinate system; and determining the time difference vector and the space difference vector based on the difference data.

[0068] In the embodiment of the present invention, since the indoor and outdoor point cloud data are usually collected under different coordinate systems, it is necessary to first perform a coordinate system. This can be done by setting common control points indoors and outdoors, or by using technologies such as the global positioning system to obtain absolute coordinates, and then converting the indoor and outdoor point cloud data to a unified coordinate system. For example, several common control points can be set at the entrance of a building, and these control points can be scanned by a ground 3D laser scanner and a handheld 3D laser scanner, respectively, and then the conversion relationship between the two coordinate systems can be determined by calculation. After the coordinate system is established, the indoor and outdoor point cloud data need to be registered, that is, they are aligned to the same coordinate system. The data registration methods mainly include feature-based registration and iterative nearest point-based registration. Feature-based registration is to extract feature points, such as corner points, edge points, etc., from indoor and outdoor point cloud data, and then use these feature points for matching and registration. This method is suitable for scenes with obvious features, but may not work well for areas with unclear features. Iterative nearest point-based registration is an iterative algorithm that minimizes the distance between two point clouds by continuously adjusting the transformation parameters between point clouds. This method is suitable for most scenarios, but it requires a lot of calculations and a long time.

[0069] In an embodiment of the present invention, if the urban change information shows that a certain area has new building construction or road reconstruction, then this area can be determined as a change area. From the indoor data and outdoor data in the unified coordinate system, the data related to the change area is filtered out. Spatial query or data filtering technology can be used to extract the required data based on geographic location, attribute information or other conditions. For example, indoor point cloud data and outdoor lidar data located in the change area can be selected.

[0070] Preprocess the extracted data to improve data quality and usability. This may include operations such as noise removal, missing value filling, and data compression. For indoor data, data cleaning and organization may also be required to remove unnecessary information and erroneous data.

[0071] Data alignment: Align indoor data with outdoor data for difference calculation. Spatial alignment algorithms, such as nearest neighbor search, iterative nearest point algorithm, etc., can be used to match corresponding points of indoor and outdoor data. Ensure that the data is spatially consistent so that differences can be accurately calculated. For each corresponding point, calculate its difference in position, attributes, etc. Position differences can be determined by calculating coordinate differences, such as calculating the difference between indoor and outdoor points in X, Y, and Z coordinates. Attribute differences can be determined based on specific data types and application requirements, such as calculating color differences, texture differences, intensity differences, etc. Mathematical operations, statistical analysis, or other methods can be used to calculate differences.

[0072] Ensure that both indoor and outdoor data have accurate timestamp information. Timestamps record the time when data was collected for time series analysis. For data collected at different time points, ensure the accuracy and consistency of timestamps. Analyze indoor and outdoor data collected at different time points to detect changes. Change detection algorithms such as difference method, ratio method, principal component analysis, etc. can be used to determine the areas and degree of change in the data. Change detection can help identify urban changes that occur over time, such as the construction, demolition, and renovation of buildings.

[0073] For the detected change areas, calculate their differences in time. Time series analysis methods, such as difference method, regression analysis, time series modeling, etc., can be used to quantify time differences. Time differences can be expressed as time intervals, change speeds, change trends, etc. These time difference information are integrated into a time difference vector, and each component of the vector can represent different time characteristics. The time difference vector can be used to analyze the time dynamics of urban changes, predict future change trends, and evaluate the effectiveness of urban planning and management. For example, the hot spots of urban changes, the speed and direction of changes can be determined by analyzing the time difference vector, providing a basis for urban planning and decision-making.

[0074] Extract spatial features such as location, shape, size, direction, etc. from indoor and outdoor data. Spatial analysis methods such as geometric analysis, topological analysis, spatial statistical analysis, etc. can be used to extract spatial features. Spatial features can help describe the layout and structure of indoor and outdoor spaces, as well as the relationship between them.

[0075] For the extracted spatial features, calculate the spatial differences between the corresponding positions indoors and outdoors. Spatial distance metrics, such as Euclidean distance, Manhattan distance, Hausdorff distance, etc., can be used to determine spatial differences. Spatial differences can be expressed as position differences, shape differences, size differences, etc. These spatial difference information are integrated into a spatial difference vector, and each component of the vector can represent a different spatial feature. The spatial difference vector can be used to analyze the degree of integration of indoor and outdoor spaces, optimize architectural design and urban planning, and improve the accuracy of indoor and outdoor navigation and positioning. For example, the discontinuous areas and conflicting areas of indoor and outdoor spaces can be determined by analyzing the spatial difference vector, providing improvement suggestions for architectural design and urban planning.

[0076] S240: According to the time difference vector and the space difference vector, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are merged to obtain an indoor-outdoor integrated model.

[0077] In some embodiments, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are fused according to the time difference vector and the space difference vector to obtain an indoor and outdoor integrated model, including: determining a fusion weight according to the time difference vector and the space difference vector; and fusing the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building according to the fusion weight to obtain an indoor and outdoor integrated model.

[0078] In the embodiment of the present invention, statistical analysis is performed on the time difference vector and the space difference vector to understand their distribution characteristics, mean, variance, correlation, etc. Statistical analysis can help determine the importance and influence of the difference vector and provide a basis for determining the fusion weight.

[0079] Comprehensively consider the statistical analysis and visualization analysis results of the time difference vector and the space difference vector, and conduct a comprehensive evaluation of the difference vector. The evaluation can include considerations such as the importance, reliability, and stability of the difference vector. According to the comprehensive evaluation results, determine the weight distribution strategy of the difference vector in the fusion process.

[0080] According to the determined weight strategy, select the appropriate weight calculation method. You can use mathematical formulas, algorithm models, machine learning methods, etc. to calculate weights. For example, you can use mathematical methods such as linear weighting method, hierarchical analysis method, fuzzy comprehensive evaluation method to calculate fusion weights; you can also use machine learning methods such as neural networks, support vector machines, random forests, etc. to automatically learn weight distribution strategies.

[0081] In an embodiment of the present invention, the point cloud data in the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are weighted according to the fusion weight to obtain fused point cloud data, that is, to obtain an indoor and outdoor integrated model.

[0082] S250, texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model.

[0083] In some embodiments, texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model, including: acquiring building texture data from airborne images; determining the correspondence between the model surface and the building texture data; and mapping the building texture data to the indoor and outdoor integrated model based on the texture relationship to obtain a city-level real-scene three-dimensional model.

[0084] In the embodiment of the present invention, the collected airborne images are subjected to denoising to remove interference caused by vibrations during flight, sensor noise, etc. Color correction is performed to keep the colors of different images consistent so that subsequent texture mapping is more natural. Image deformation caused by factors such as camera lens distortion and aircraft attitude changes is eliminated. The camera's intrinsic and extrinsic parameters can be used for correction.

[0085] Use geographic information system software or professional 3D modeling software to import the indoor and outdoor integrated model and determine its geographic coordinate system. Import the airborne image into the same software and perform preliminary positioning based on its geographic location information when it was taken. Manual or automatic registration is performed by selecting feature points on the model and corresponding points on the image. Feature extraction algorithms such as scale-invariant feature transformation and accelerated robust features can be used to find similar feature points in the model and image, and then registration is performed using algorithms such as the least squares method.

[0086] For each surface of the indoor-outdoor integrated model, determine its corresponding position in the texture image. This can be achieved by projecting the model surface onto the image plane and then calculating the texture coordinates. Texture coordinates are usually a two-dimensional vector that represents the position of a point on the model surface in the texture image. The calculation can be performed using projection matrices, texture mapping algorithms, etc. Based on the texture relationship, the building texture data is mapped to the indoor-outdoor integrated model to obtain a city-level real-life 3D model.

[0087] In the 3D modeling software, set the texture mapping parameters, such as texture repetition mode, filtering mode, etc. According to the established texture coordinates, map the architectural texture data piece by piece onto the surface of the indoor and outdoor integrated model. Check and adjust the model after texture mapping to ensure that the texture fit, resolution, and color meet the requirements. If problems such as texture stretching, blurring, or misalignment are found, they can be corrected by adjusting the texture coordinates, re-registering the model and image, etc.

[0088] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.

[0089] Figure 3 Schematic diagram of the structure of a city-level real-scene 3D data processing device based on multi-source data provided by an embodiment of the present invention. Figure 3 As shown, in some embodiments, the city-level real-scene three-dimensional data processing device 3 based on multi-source data includes:

[0090] The acquisition module 310 is used to acquire architectural design drawings, indoor point cloud data, airborne images, and laser radar payload data;

[0091] A construction module 320 is used to construct a three-dimensional indoor model of the building according to the architectural design drawing and the indoor point cloud data, and to construct a three-dimensional outdoor model of the building according to the airborne image and the laser radar payload data;

[0092] A determination module 330, for determining a time difference vector and a space difference vector between indoor and outdoor based on the airborne image, the laser radar payload data and the indoor point cloud data;

[0093] A fusion module 340 is used to fuse the building indoor three-dimensional model and the building outdoor three-dimensional model according to the time difference vector and the space difference vector to obtain an indoor and outdoor integrated model;

[0094] The mapping module 350 is used to perform texture mapping on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model.

[0095] Optionally, the determination module 330 is used to determine the city change information based on the airborne image and the city change prediction model; based on the city change information, the lidar payload data and the indoor point cloud data are processed to determine the time difference vector and the space difference vector between indoor and outdoor.

[0096] Optionally, determine module 330, which is used to perform data alignment on the lidar payload data and indoor point cloud data to obtain indoor data and outdoor data under a unified coordinate system; obtain difference data from the indoor data and outdoor data under a unified coordinate system based on urban change information; and determine a time difference vector and a space difference vector based on the difference data.

[0097] Optionally, the fusion module 340 is used to determine a fusion weight according to the time difference vector and the space difference vector; and fuse the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building according to the fusion weight to obtain an indoor-outdoor integrated model.

[0098] Optionally, a mapping module 350 is used to obtain building texture data from airborne images; determine the correspondence between the model surface and the building texture data; and map the building texture data to an indoor and outdoor integrated model based on the texture relationship to obtain a city-level real-scene three-dimensional model.

[0099] Optionally, a construction module 320 is used to create an indoor basic model based on the architectural design drawing; pre-process the indoor point cloud data and add it to the indoor basic model to obtain a three-dimensional model of the building interior.

[0100] Optionally, a construction module 320 is used to create an outdoor basic model based on the laser radar load data; the basic model is corrected and optimized according to the airborne image to obtain an outdoor three-dimensional model of the building.

[0101] The city-level real-scene three-dimensional data processing device based on multi-source data provided in this embodiment can be used to execute the above method embodiments. Its implementation principles and technical effects are similar, and this embodiment will not be repeated here.

[0102] Figure 4 Schematic diagram of the structure of the terminal provided by the embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides a terminal 4, and the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the city-level real-scene 3D data processing method based on multi-source data are implemented, for example Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned system embodiments are realized, for example Figure 3 The functions of each module are shown.

[0103] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41, and are executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4.

[0104] The terminal 4 may be a terminal or a server. The terminal may be a mobile phone, MCU, ECU, industrial computer, etc., which are not limited here. The server may be a physical server, a cloud server, etc., which are not limited here. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0105] The processor 40 may be a central processing unit (CPU), or 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 any conventional processor, etc.

[0106] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0107] An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned embodiment of the city-level real-scene three-dimensional data processing method based on multi-source data are implemented.

[0108] The computer readable storage medium stores a computer program 42, which includes program instructions. When the program instructions are executed by the processor 40, all or part of the processes in the above-mentioned embodiment method are implemented. The computer program 42 can also be used to instruct related hardware to complete. The computer program 42 can be stored in a computer readable storage medium. When the computer program 42 is executed by the processor 40, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program 42 includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0109] The computer-readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0110] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.

[0111] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] 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.

[0114] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, 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 devices or units, which can be electrical, mechanical or other forms.

[0115] 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.

[0116] 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0117] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0118] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for processing city-level real-scene three-dimensional data based on multi-source data, characterized in that: include: Obtain architectural design drawings, indoor point cloud data, airborne images, and lidar payload data; Constructing an indoor three-dimensional model of the building according to the building design drawing and the indoor point cloud data, and constructing an outdoor three-dimensional model of the building according to the airborne image and the laser radar payload data; Determine a time difference vector and a space difference vector for indoor and outdoor according to the airborne image, the laser radar payload data and the indoor point cloud data; According to the time difference vector and the space difference vector, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are merged to obtain an indoor-outdoor integrated model; Texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model.

2. The city-level real-scene three-dimensional data processing method based on multi-source data according to claim 1 is characterized in that: Determining the time difference vector and the space difference vector of indoor and outdoor according to the airborne image, the laser radar payload data and the indoor point cloud data, including: Determining urban change information based on the airborne image and the urban change prediction model; The laser radar load data and the indoor point cloud data are processed according to the city change information to determine the time difference vector and space difference vector between indoor and outdoor.

3. The city-level real-scene three-dimensional data processing method based on multi-source data according to claim 2 is characterized in that: According to the city change information, the laser radar load data and the indoor point cloud data are processed to determine the time difference vector and the space difference vector between indoor and outdoor, including: Performing data registration on the laser radar payload data and the indoor point cloud data to obtain indoor data and outdoor data under unified coordinates; According to the city change information, obtaining difference data from indoor data and outdoor data in a unified coordinate system; The time difference vector and the space difference vector are determined according to the difference data.

4. The city-level real-scene three-dimensional data processing method based on multi-source data according to claim 3 is characterized in that: According to the time difference vector and the space difference vector, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are merged to obtain an indoor-outdoor integrated model, including: Determining a fusion weight according to the time difference vector and the space difference vector; According to the fusion weight, the indoor three-dimensional model of the building and the outdoor three-dimensional model of the building are fused to obtain an indoor-outdoor integrated model.

5. The method for processing city-level real-scene 3D data based on multi-source data according to claim 1, characterized in that: Texture mapping is performed on the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model, including: Acquiring building texture data from the airborne image; Determine the correspondence between the model surface and the building texture data; According to the texture relationship, the building texture data is mapped to the indoor and outdoor integrated model to obtain a city-level real-scene three-dimensional model.

6. The city-level real-scene 3D data processing method based on multi-source data according to claim 1 is characterized in that: Constructing a three-dimensional indoor model of a building according to the building design drawing and the indoor point cloud data, including: Create a basic interior model based on the architectural design drawings; The indoor point cloud data is preprocessed and added to the indoor basic model to obtain the building indoor three-dimensional model.

7. The method for processing city-level real-scene 3D data based on multi-source data according to claim 2, characterized in that: Constructing an outdoor three-dimensional model of a building according to the airborne image and the laser radar payload data, including: Create an outdoor base model based on LiDAR load data; The basic model is corrected and optimized according to the airborne image to obtain an outdoor three-dimensional model of the building.

8. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for processing city-level real-scene three-dimensional data based on multi-source data as described in any one of claims 1 to 7 are implemented.

9. A city-level real-scene three-dimensional data processing system, comprising a data acquisition device, a point cloud acquisition device camera, a laser radar and the terminal as described in claim 8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for processing city-level real-scene three-dimensional data based on multi-source data as described in any one of claims 1 to 7 above are implemented.

Images