Three-dimensional real scene modeling method and system based on unmanned aerial vehicle

Abstract

The invention relates to the technical field of three-dimensional modeling, in particular to a three-dimensional live-action modeling method and system based on an unmanned aerial vehicle, and the method comprises the steps: obtaining a high-altitude overlook image collected by the unmanned aerial vehicle and ground multi-angle shooting data collected by ground photography equipment, and then carrying out the preprocessing based on the high-altitude overlook image and the multi-angle shooting data, the preprocessing comprises the steps of image distortion correction and point cloud data splicing. And further, performing multi-source data fusion based on the target high-altitude overlook image and the target multi-angle shooting data to obtain multi-source fusion data, and performing three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional live-action model. According to the method, multi-source data fusion is executed to integrate data from different sources, and the advantages of the two are fully utilized to realize data complementation, so that the accuracy and reliability of a three-dimensional live-action model created by utilizing the multi-source fusion data are improved.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional modeling, and in particular to a three-dimensional real-scene modeling method and system based on an unmanned aerial vehicle. Background Art

[0002] With the advancement of information technology and the development of drone technology, drones have been widely used in various industries. Especially in the fields of geographic information systems and remote sensing, drones have gradually become one of the main tools for obtaining high-resolution images due to their flexibility and cost-effectiveness.

[0003] In terms of 3D real scene modeling, commonly used methods mainly include traditional photogrammetry, that is, generating 3D real scene models through image data collected by drones, which is of great significance for urban planning, rapid disaster response, etc. However, the perspective of drones is from top to bottom, so when buildings or other target objects are high, their bottoms are easily blocked by other objects. At the same time, although high-altitude overhead images can capture the overall structure of the target area, they often cannot obtain the detailed texture information of the target object, making the 3D real scene models generated only by high-altitude overhead images collected by drones low in accuracy.

[0004] Therefore, how to provide a three-dimensional real scene modeling method to improve the accuracy of the model is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0005] The purpose of this application is to provide a drone-based three-dimensional real-scene modeling method and system to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions: In the first aspect, the present application provides a method for three-dimensional real scene modeling based on a drone, which adopts the following technical solution: A three-dimensional real scene modeling method based on unmanned aerial vehicle, comprising: Acquire high-altitude bird's-eye view images collected by drones and ground multi-angle shooting data collected by ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; the ground multi-angle shooting data are used to display the details and texture of the objects; Preprocessing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain a target high-altitude bird's-eye view image and target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching; Multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model.

[0007] By adopting the above technical solution, the high-altitude bird's-eye view images collected by drones and the ground multi-angle shooting data collected by ground photography equipment are obtained. Then, the high-altitude bird's-eye view images and multi-angle shooting data are preprocessed to obtain the target high-altitude bird's-eye view images and target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data splicing. Furthermore, multi-source data fusion is performed based on the target high-altitude bird's-eye view images and target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model. Performing multi-source data fusion integrates data from different sources, fully utilizing the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0008] In a preferred example, the present application can be further configured as follows: the high-altitude overhead image and the multi-angle shooting data are pre-processed to obtain the target high-altitude overhead image and the target multi-angle shooting data, wherein the pre-processing includes: image distortion correction and point cloud data stitching, including: Performing distortion detection based on the high-altitude bird's-eye view image to determine a distortion detection result, and when the distortion detection result indicates that distortion exists, performing image distortion correction on the high-altitude bird's-eye view image to obtain a target high-altitude bird's-eye view image; Data screening is performed based on the multi-angle shooting data to determine the laser radar point cloud data, point cloud data is stitched based on the laser radar point cloud data to obtain stitched point cloud data, and target multi-angle shooting data is determined based on the ground upward-looking image in the multi-angle shooting data and the stitched point cloud data.

[0009] In a preferred example, the present application may be further configured as follows: the multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain the multi-source fusion data, including: Extract feature points based on the high-altitude overhead image and the ground upward image to obtain overhead image feature points and upward image feature points; Perform feature point matching based on the feature points of the overhead image and the feature points of the upward image to determine an image feature mapping relationship; The laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and based on the image feature mapping relationship, multi-source data fusion is performed on the laser scanning point cloud data and the stitching point cloud data to obtain multi-source fused data.

[0010] In a preferred example, the present application may be further configured as follows: before acquiring the high-altitude bird's-eye view image collected by the drone, the method further includes: Obtain a map of the area to be modeled, perform a multi-UAV collaborative operation analysis based on the map of the area to be modeled, and determine an image acquisition flight plan corresponding to each UAV, wherein the multi-UAV collaborative operation analysis is used to control multiple UAVs to acquire images from different heights, different angles, and different flight routes to form a three-dimensional coverage network; Sending the image acquisition flight plan to the corresponding target UAV, and controlling the target UAV to perform image acquisition according to the image acquisition flight plan; The image acquisition data sent by each of the target UAVs is acquired, and each of the image acquisition data is fused to obtain a high-altitude bird's-eye view image.

[0011] In a preferred example, the present application may be further configured as follows: after performing three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model, the present application may further include: Performing a multi-dimensional model quality assessment based on the three-dimensional real scene model to determine a model quality assessment result, wherein the multi-dimensional model quality assessment includes: integrity quality assessment, accuracy quality assessment, consistency quality assessment and texture quality assessment; When the model quality assessment result is that the model does not meet the quality requirements, an abnormal warning of the real scene model is generated.

[0012] In a preferred example, the present application may be further configured as follows: after performing a multi-dimensional model quality assessment based on the three-dimensional real scene model and determining a model quality assessment result, the configuration further includes: When the model quality assessment result meets the quality requirements, the lighting simulation conditions are obtained, and based on the holographic projection technology and the lighting simulation conditions, a virtual three-dimensional image is obtained for the three-dimensional real scene model, wherein the virtual three-dimensional image is used to simulate scene conditions under different lighting conditions in a virtual space.

[0013] In the second aspect, the present application provides a three-dimensional real scene modeling system based on a drone, which adopts the following technical solution: A data acquisition module is used to acquire high-altitude bird's-eye view images collected by drones and ground multi-angle shooting data collected by ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; and the ground multi-angle shooting data are used to display the details and texture of the ground objects; A preprocessing module, used for performing preprocessing based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain a target high-altitude bird's-eye view image and target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching; The three-dimensional modeling module is used to perform multi-source data fusion based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and perform three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model.

[0014] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned drone-based three-dimensional real scene modeling method.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned three-dimensional real-scene modeling method based on a drone.

[0016] In summary, the present application includes at least one of the following beneficial technical effects: The high-altitude overhead image collected by the UAV and the ground multi-angle shooting data collected by the ground photography equipment are obtained, and then the high-altitude overhead image and the multi-angle shooting data are pre-processed to obtain the target high-altitude overhead image and the target multi-angle shooting data, wherein the pre-processing includes: image distortion correction and point cloud data stitching. Furthermore, multi-source data fusion is performed based on the target high-altitude overhead image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model. Performing multi-source data fusion integrates data from different sources, fully utilizing the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0017] Distortion detection is performed based on the high-altitude bird's-eye view image to determine the distortion detection result. When the distortion detection result shows that there is distortion, the high-altitude bird's-eye view image is subjected to image distortion correction to obtain the target high-altitude bird's-eye view image. Image distortion correction is performed to improve the clarity and accuracy of the high-altitude bird's-eye view image, providing a reliable foundation for subsequent three-dimensional modeling. At the same time, data is screened based on multi-angle shooting data to determine the LiDAR point cloud data. In order to improve the comprehensiveness of the point cloud data and the accuracy of the subsequent three-dimensional model, the point cloud data is spliced ​​based on the LiDAR point cloud data to obtain spliced ​​point cloud data, and the target multi-angle shooting data is determined based on the ground upward image and the spliced ​​point cloud data in the multi-angle shooting data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a method for three-dimensional real scene modeling based on a drone in one embodiment of the present application; Figure 2It is a structural schematic diagram of a three-dimensional real scene modeling system based on a drone according to one embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] The following combination Figures 1 to 3 This application is described in further detail.

[0020] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0021] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0022] In addition, 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. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0023] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0024] The embodiment of the present application provides a method for 3D real scene modeling based on drones, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes step S101, step S102 and step S103, wherein: Step S101: Acquire high-altitude bird's-eye view images collected by drones and ground multi-angle shooting data collected by ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; and the ground multi-angle shooting data are used to display the details and texture of the objects.

[0025] For the embodiments of the present application, in the process of three-dimensional real scene modeling, drones have become one of the main tools for collecting high-resolution images in building three-dimensional real scene models due to their flexibility and cost-effectiveness, that is, using high-resolution cameras, laser radars and various sensors carried by drones to take aerial photos of the target area at a suitable flight altitude and angle. The drones are connected to electronic devices wirelessly so that the electronic devices can obtain the high-altitude overhead images collected by the drones in real time. The high-altitude overhead images are used to clearly display the overall structure and layout of the surface, such as the road network of the city, the distribution of buildings, etc.

[0026] When drones are shooting at high altitudes, they may be blocked by obstacles such as buildings and trees, resulting in some areas being unable to be photographed, causing information to be missing in the aerial bird's-eye view images. At the same time, although aerial bird's-eye view images can show the overall structure and layout of the surface, due to the limitations of shooting angles and distances, their detail resolution is often relatively low, making it difficult to accurately capture and represent the detailed shape and texture of the objects. Therefore, ground photography equipment, such as ground lidar, panoramic cameras, etc., are deployed in the area to be modeled to control the ground photography equipment to take multi-angle photos of the target objects from different angles and positions on the ground. The ground photography equipment is connected to the electronic equipment wirelessly so that the electronic equipment can obtain the ground multi-angle shooting data collected by the ground camera equipment in real time. The ground multi-angle shooting data is used to display the details and texture of the objects, such as the walls, roofs, doors and windows of buildings, etc. Step S102: Preprocessing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching.

[0027] For the embodiments of the present application, when the drone is shooting at high altitude, due to various factors such as the camera lens, flight attitude, atmospheric refraction, etc., the high-altitude overhead image taken will be distorted. The distorted image will affect the subsequent three-dimensional modeling precision and accuracy. Therefore, image distortion correction is performed to eliminate the distortion of the high-altitude overhead image, so that the target high-altitude overhead image conforms to the characteristics of the object, and the quality and clarity of the image shooting are improved. At the same time, the laser radar point cloud data in the multi-angle shooting data is point cloud data under different viewing angles. In order to enable the subsequent three-dimensional real-scene model to more comprehensively display the geometric shape and spatial distribution of each target object in the area to be modeled, point cloud data splicing is performed based on the laser radar point cloud data in the multi-angle shooting data to obtain the target multi-angle shooting data. Performing point cloud data splicing helps to reduce the subsequent three-dimensional real-scene model distortion or deformation due to errors in a single point cloud scan or a single angle point cloud data or due to data loss.

[0028] There are many specific implementation processes for preprocessing, which are no longer limited in the embodiments of the present application. In one feasible method, distortion detection is performed based on the high-altitude bird's-eye view image to determine the distortion detection result. When the distortion detection result shows that there is distortion, the high-altitude bird's-eye view image is corrected for image distortion using a distortion correction algorithm to obtain a target high-altitude bird's-eye view image; data screening is performed based on the multi-angle shooting data to determine the lidar point cloud data; point cloud data is spliced ​​based on the lidar point cloud data to obtain spliced ​​point cloud data; and based on the ground upward view image and the spliced ​​point cloud data in the multi-angle shooting data, the target multi-angle shooting data is determined.

[0029] Step S103: performing multi-source data fusion based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and performing three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model.

[0030] For the embodiments of the present application, the high-altitude overhead image of the target collected by the drone can provide a macroscopic and comprehensive perspective, covering a large area, but may lack details and accuracy. The multi-angle shooting data of the target collected by the ground photography equipment can be finely photographed from multiple angles to capture detailed information. Then, multi-source data fusion is performed to integrate data from different sources, making full use of the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data. There are many specific implementation methods for multi-source data fusion, and the embodiments of the present application are no longer limited. In one achievable method, feature points are extracted based on the high-altitude overhead image and the ground upward image to obtain the feature points of the overhead image and the feature points of the upward image; feature points are matched based on the feature points of the overhead image and the feature points of the upward image to determine the image feature mapping relationship; the laser scanning point cloud data corresponding to the high-altitude overhead image is obtained, and based on the image feature mapping relationship, the laser scanning point cloud data and the spliced ​​point cloud data are multi-source data fused to obtain multi-source fusion data.

[0031] Then, three-dimensional modeling is performed based on multi-source fusion data to generate a three-dimensional real scene model with higher realism and accuracy. The three-dimensional real scene model can truly reflect the spatial structure and detail characteristics of the actual scene in the area to be modeled, provide strong support for research and application in related fields, and also provide a common data basis for research and application in different fields. The specific implementation process of three-dimensional modeling is as follows: an irregular triangulated network is constructed based on the point cloud data in the multi-source fusion data. The irregular triangulated network can accurately represent the surface morphology of terrain and buildings, and is an important part of three-dimensional modeling. Then, the texture images in the high-altitude overhead image and the ground upward image are mapped to the three-dimensional model to increase the realism and details of the model. The texture adding step needs to ensure the accuracy and consistency of the texture to avoid problems such as texture dislocation or stretching. Then, the initially constructed three-dimensional model is optimized, including but not limited to: removing redundant data, smoothing the surface, repairing loopholes, etc., to improve the accuracy and visualization effect of the three-dimensional model. Finally, multiple three-dimensional models are integrated into a unified scene to form a complete three-dimensional real scene model. In this integration step, it is necessary to ensure the seamless connection and consistency between different three-dimensional models.

[0032] It can be seen that in the embodiment of the present application, the high-altitude bird's-eye view image collected by the drone and the ground multi-angle shooting data collected by the ground photography equipment are obtained, and then pre-processing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the pre-processing includes: image distortion correction and point cloud data stitching. Furthermore, multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model. Performing multi-source data fusion integrates data from different sources, fully utilizing the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0033] Furthermore, in order to improve the clarity and accuracy of the high-altitude bird's-eye view image, and to enhance the comprehensiveness of the point cloud data and the accuracy of the subsequent three-dimensional model, in the embodiment of the present application, preprocessing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data splicing, including: Distortion detection is performed based on the high-altitude overhead image to determine the distortion detection result. When the distortion detection result shows that there is distortion, image distortion correction is performed on the high-altitude overhead image to obtain the target high-altitude overhead image; Data screening is performed based on the multi-angle shooting data to determine the lidar point cloud data, point cloud data is stitched based on the lidar point cloud data to obtain stitched point cloud data, and target multi-angle shooting data is determined based on the ground upward-looking image and stitched point cloud data in the multi-angle shooting data.

[0034] For the embodiment of the present application, when the drone is shooting at high altitude, due to various factors such as camera lens, flight attitude, atmospheric refraction, etc., the high-altitude overhead image taken will be distorted. The distortion will cause the geometric relationship in the image to be distorted, affecting the subsequent three-dimensional modeling precision and accuracy. Therefore, image distortion correction is performed on the distorted high-altitude overhead image to eliminate the distortion in the high-altitude overhead image and restore the true geometric relationship of the image, so as to improve the clarity and accuracy of the high-altitude overhead image and provide a reliable basis for subsequent three-dimensional modeling. Specifically, a suitable distortion detection algorithm is selected to perform distortion detection on the high-altitude overhead image to determine the distortion detection result, wherein the distortion detection result includes: the presence of distortion and the absence of distortion. When distortion exists, the distortion detection algorithm can accurately identify the distortion type (for example, radial distortion, tangential distortion and atmospheric refraction, etc.) and degree in the high-altitude overhead image. The distortion detection algorithm includes but is not limited to: an algorithm based on feature point matching and an algorithm based on edge detection. Furthermore, when the distortion detection result shows that there is distortion, the internal parameters of the camera and the flight attitude data corresponding to the UAV are obtained, and an image distortion correction model is established based on the internal parameters of the camera and the flight attitude data. The image distortion correction model can describe the relationship between image distortion and flight attitude, and is used to predict and correct distortion. Then, the image distortion correction model is used to perform image distortion correction on the high-altitude overhead image with distortion to obtain the target high-altitude overhead image. The image distortion correction is used to convert the distorted pixel coordinates into correct coordinates.

[0035] At the same time, the multi-angle shooting data includes the laser radar point cloud data collected by the ground laser radar and the ground upward image collected by the panoramic camera. Therefore, data screening is performed based on the multi-angle shooting data to determine the laser radar point cloud data. However, the laser radar point cloud data is a single point cloud scan or a single angle point cloud data. There are errors or data missing in the laser radar point cloud data. If the laser radar point cloud data is directly used for three-dimensional construction, it will cause the subsequent three-dimensional real scene model to be distorted or deformed. In order to improve the comprehensiveness of the point cloud data and the accuracy of the subsequent three-dimensional model, the point cloud data is spliced ​​based on the laser radar point cloud data to obtain spliced ​​point cloud data. Through the point cloud data splicing, each local point cloud data can be integrated into a unified three-dimensional coordinate system. The local point cloud data complement and verify each other, reduce errors and omissions, and thus improve the precision and accuracy of the subsequent constructed three-dimensional model. Common methods for point cloud data splicing include but are not limited to: target splicing method, overlapping area splicing method and control point splicing method. Users can select a suitable point cloud data splicing method according to the specific situation of the point cloud data. This embodiment of the present application is no longer limited. Furthermore, based on the ground upward-looking image and the stitched point cloud data in the multi-angle shooting data, the target multi-angle shooting data is determined.

[0036] It can be seen that in the embodiment of the present application, distortion detection is performed based on the high-altitude bird's-eye view image to determine the distortion detection result. When the distortion detection result shows that there is distortion, image distortion correction is performed on the high-altitude bird's-eye view image to obtain the target high-altitude bird's-eye view image. Image distortion correction is performed to improve the clarity and accuracy of the high-altitude bird's-eye view image, providing a reliable foundation for subsequent three-dimensional modeling. At the same time, data screening is performed based on multi-angle shooting data to determine the lidar point cloud data. In order to improve the comprehensiveness of the point cloud data and the accuracy of the subsequent three-dimensional model, point cloud data splicing is performed based on the lidar point cloud data to obtain spliced ​​point cloud data, and based on the ground upward image and the spliced ​​point cloud data in the multi-angle shooting data, the target multi-angle shooting data is determined.

[0037] Furthermore, in order to improve the accuracy and reliability of the three-dimensional real scene model, in the embodiment of the present application, multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, including: Feature points are extracted based on the high-altitude overhead image and the ground upward image to obtain the feature points of the overhead image and the upward image; Matching feature points based on the feature points of the overhead image and the feature points of the upward image to determine the image feature mapping relationship; The laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and based on the image feature mapping relationship, multi-source data fusion is performed on the laser scanning point cloud data and the stitching point cloud data to obtain multi-source fused data.

[0038] For the embodiments of the present application, the high-altitude bird's-eye view images of the target collected by the drone can provide a macro and comprehensive perspective and cover a large area, but may lack details and accuracy. The multi-angle shooting data of the target collected by the ground photography equipment can be finely photographed from multiple angles to capture detailed information. Then, multi-source data fusion is performed to integrate data from different sources, fully utilizing the advantages of both and achieving data complementarity, so as to improve the accuracy and reliability of the three-dimensional real-scene model created using multi-source fusion data.

[0039] Specifically, feature points are extracted based on the high-altitude overhead image and the ground upward image to obtain the feature points of the overhead image and the upward image, that is, feature points are detected in the high-altitude overhead image and the ground upward image respectively using a feature point detection algorithm (for example, SIFT, SURF, ORB, etc.). The feature point detection algorithm can identify points with significant local characteristics in the image, such as corner points, edge points, etc. Then, for each detected feature point, its descriptor is calculated, which can also be called a feature vector. The descriptor usually contains local information around the feature point for subsequent feature point matching. Furthermore, through the feature point matching algorithm, the feature points of the overhead image and the feature points of the upward image are matched to establish a matching relationship between the two feature points. That is, when performing feature point matching, the feature point matching algorithm finds possible matching pairs by comparing the descriptors of the feature points. Using the screened matching point pairs, the homography matrix between the high-altitude overhead image and the ground upward image is calculated. The homography matrix describes the mapping relationship between the two planes and can be used to map points in the overhead image to the upward image, or vice versa.

[0040] Then, the laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and the laser scanning point cloud data and the spliced ​​point cloud data are fused with multi-source data based on the image feature mapping relationship to obtain multi-source fused data. For multi-source data fusion, the laser scanning point cloud data and the spliced ​​point cloud data are registered using the image feature mapping relationship to achieve accurate alignment between the point cloud data; then, based on the registration, the laser scanning point cloud data and the spliced ​​point cloud data are fused to generate high-quality multi-source fused data. In this fusion process, processing steps such as merging, deduplication, and smoothing of point cloud data are involved.

[0041] It can be seen that in the embodiment of the present application, feature points are extracted based on the high-altitude bird's-eye view image and the ground-based upward view image to obtain the feature points of the bird's-eye view image and the upward view image, and feature points are matched based on the feature points of the bird's-eye view image and the upward view image to determine the image feature mapping relationship. Then, the laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and based on the image feature mapping relationship, multi-source data fusion is performed on the laser scanning point cloud data and the spliced ​​point cloud data to obtain multi-source fused data. Multi-source data fusion is performed to integrate data from different sources, fully utilize the advantages of both, and achieve data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0042] Furthermore, in order to improve the working efficiency of drone image acquisition and obtain a more complete and accurate high-altitude bird's-eye view image, in the embodiment of the present application, before obtaining the high-altitude bird's-eye view image collected by the drone, it also includes: Obtain a map of the area to be modeled, perform multi-UAV collaborative operation analysis based on the map of the area to be modeled, and determine the image acquisition flight plan corresponding to each UAV. The multi-UAV collaborative operation analysis is used to control multiple UAVs to collect images from different heights, angles, and flight routes to form a three-dimensional coverage network. Send the image acquisition flight plan to the corresponding target UAV, and control the target UAV to perform image acquisition according to the image acquisition flight plan; The image acquisition data sent by each target UAV is obtained, and each image acquisition data is fused to obtain a high-altitude bird's-eye view image.

[0043] For the embodiments of the present application, before collecting high-altitude bird's-eye view images, the drone needs to formulate a detailed image collection flight plan to ensure that each drone flies and shoots according to the predetermined route and parameters. In order to improve the work efficiency of drone image collection, multiple drones are coordinated to greatly shorten the image collection time. At the same time, by controlling multiple drones to collect images from different heights, different angles and different flight routes, more complete and accurate high-altitude bird's-eye view images can be obtained.

[0044] Specifically, a map of the area to be modeled is obtained, which may include satellite remote sensing images, topographic maps, digital elevation models (DEMs), etc., and the map of the area to be modeled is preprocessed to improve the accuracy and availability of the map of the area to be modeled. Then, according to the size, shape and complexity of the area to be modeled, the map of the area to be modeled is divided into several small operation areas. Each operation area is imaged by multiple drones from different angles and heights, and it is ensured that the image acquisition area covers the entire area to be modeled. Then, based on the specific map data of each operation area, a detailed flight plan is formulated for each drone, including take-off point, flight route, altitude, speed, shooting parameters, etc. The flight plan should take into account factors such as terrain, obstacles, and weather to ensure the safe flight of the drone and the quality of image acquisition. Furthermore, a collaborative strategy between drones is designed, including communication protocols, information sharing mechanisms, task allocation and scheduling, etc., to ensure that multiple drones can share information and coordinate actions in real time to achieve efficient collaborative operations. After that, the image acquisition flight plan is sent to the corresponding target drone, and the target drone is controlled to perform image acquisition according to the image acquisition flight plan.

[0045] Wireless communication is used between drones and electronic devices so that the image data collected by drones can be transmitted to the electronic devices in real time. Therefore, after receiving the image data sent by each target drone, the electronic devices fuse the image data based on each image data to obtain a high-altitude bird's-eye view image. In the fusion operation of the above image data, factors such as image overlap and matching accuracy should be considered to ensure the data quality of the fused high-altitude bird's-eye view image.

[0046] It can be seen that in the embodiment of the present application, in order to improve the work efficiency of drone image acquisition, a map of the area to be modeled is obtained, and a multi-drone collaborative operation analysis is performed based on the map of the area to be modeled, and the image acquisition flight plan corresponding to each drone is determined. The image acquisition flight plan is sent to the corresponding target drone to control the target drone to perform image acquisition according to the image acquisition flight plan, and multiple drones are controlled to perform image acquisition from different heights, different angles and different flight routes, so as to obtain a more complete and accurate high-altitude bird's-eye view image. Then, the image acquisition data sent by each target drone is obtained, and each image acquisition data is fused to obtain a high-altitude bird's-eye view image.

[0047] Furthermore, in order to timely discover defects in the 3D real scene model and improve the reliability and stability of the 3D real scene model, in the embodiment of the present application, after performing 3D modeling based on multi-source fusion data and obtaining the 3D real scene model, the following steps are further included: Perform multi-dimensional model quality assessment based on the three-dimensional real scene model to determine the model quality assessment results, wherein the multi-dimensional model quality assessment includes: integrity quality assessment, accuracy quality assessment, consistency quality assessment and texture quality assessment; When the model quality assessment result does not meet the quality requirements, a real-life model abnormality warning is generated.

[0048] For the embodiments of the present application, the three-dimensional real scene model serves as an important data basis, and its quality directly affects the effect and accuracy of subsequent applications. Therefore, by performing a multi-dimensional model quality assessment operation on the three-dimensional real scene model, it is helpful to promptly discover problems in the three-dimensional real scene model in terms of integrity, accuracy, consistency, and texture, so that timely measures can be taken to correct and optimize it, which helps to improve the reliability and stability of the three-dimensional real scene model.

[0049] Specifically, a multi-dimensional model quality assessment is performed based on the three-dimensional real scene model to determine the model quality assessment result, wherein the multi-dimensional model quality assessment includes: integrity quality assessment, accuracy quality assessment, consistency quality assessment and texture quality assessment. For integrity quality assessment, it is verified whether the three-dimensional real scene model covers all target objects in the area to be modeled, that is, the integrity quality assessment is achieved by comparing the original data source (high-altitude overhead image and multi-angle shooting data) with the information in the three-dimensional real scene model to ensure that no important geographical or structural features are omitted in the three-dimensional real scene model. For accuracy quality assessment, the accuracy of the three-dimensional real scene model is verified using known feature points of objects (for example, control points, landmark buildings, etc.), that is, the accuracy of the three-dimensional real scene model is evaluated by comparing the consistency of the position, size and shape in the three-dimensional real scene model with the actual objects. For consistency quality assessment, it is checked whether different parts (for example, buildings, roads, vegetation, etc.) in the three-dimensional real scene model are logically consistent and there are no contradictions, which helps to ensure the reality and credibility of the three-dimensional real scene model. For texture quality assessment, for 3D real-life models containing texture information, it is necessary to check the clarity, coherence and authenticity of the texture, that is, the texture should match the appearance of the actual object without obvious distortion or splicing errors.

[0050] Furthermore, when the model quality assessment result is not in compliance with the quality requirements, a real-scene model abnormality warning is generated, which is used to prompt relevant personnel to respond in a timely manner and take relevant measures to solve the problem, so as to prevent adverse consequences caused by inaccurate three-dimensional real-scene models.

[0051] It can be seen that in the embodiment of the present application, a multi-dimensional model quality assessment is performed based on the three-dimensional real scene model to determine the model quality assessment result. When the model quality assessment result does not meet the quality requirements, a real scene model abnormality warning is generated. By performing a multi-dimensional model quality assessment operation on the three-dimensional real scene model, it is helpful to timely discover problems in the integrity, accuracy, consistency and texture of the three-dimensional real scene model, so as to take timely measures to correct and optimize it, which helps to improve the reliability and stability of the three-dimensional real scene model.

[0052] Furthermore, in order to enhance the user's immersion and experience effect and make the scene in the virtual space more vivid and realistic, in the embodiment of the present application, after performing a multi-dimensional model quality assessment based on the three-dimensional real scene model and determining the model quality assessment result, it also includes: When the model quality assessment result meets the quality requirements, the lighting simulation conditions are obtained, and based on the holographic projection technology and the lighting simulation conditions, a virtual three-dimensional image is obtained for the three-dimensional real scene model, wherein the virtual three-dimensional image is used to simulate the scene conditions under different lighting conditions in the virtual space.

[0053] For the embodiments of the present application, by combining holographic projection technology and lighting simulation conditions, scene conditions under different lighting conditions are simulated, making the virtual three-dimensional image closer to the real scene, which helps to enhance the user's immersion and experience effect, and makes the scene in the virtual space more vivid and realistic.

[0054] Specifically, when the model quality assessment result meets the quality requirements, the lighting simulation conditions are obtained, which are the lighting data under different time periods and different weather conditions. Then, the lighting simulation conditions and the three-dimensional real-scene model are loaded into the holographic projection system, and the three-dimensional real-scene model is visualized and rendered using holographic projection technology to obtain a virtual three-dimensional image that simulates the scene conditions under different lighting conditions.

[0055] It can be seen that in the embodiment of the present application, when the model quality assessment result meets the quality requirements, the lighting simulation conditions are obtained, and based on the holographic projection technology and the lighting simulation conditions, the three-dimensional real scene model is subjected to a virtual three-dimensional image. By combining the holographic projection technology and the lighting simulation conditions, the scene conditions under different lighting conditions are simulated, so that the virtual three-dimensional image is closer to the real scene, which helps to enhance the user's immersion and experience effect, and makes the scene in the virtual space more vivid and realistic.

[0056] The above embodiment introduces a 3D real scene modeling method based on a drone from the perspective of method flow, and the following embodiment introduces a 3D real scene modeling system based on a drone from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0057] The present application embodiment provides a three-dimensional real scene modeling system based on a drone, such as Figure 2 As shown, the drone-based 3D real scene modeling system may specifically include: The data acquisition module 210 is used to acquire the high-altitude bird's-eye view images collected by the drone and the ground multi-angle shooting data collected by the ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; the ground multi-angle shooting data are used to display the details and texture of the ground objects; The preprocessing module 220 is used to perform preprocessing based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data splicing; The three-dimensional modeling module 230 is used to perform multi-source data fusion based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and perform three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model.

[0058] For the embodiment of the present application, the high-altitude bird's-eye view image collected by the drone and the ground multi-angle shooting data collected by the ground photography equipment are obtained, and then pre-processing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the pre-processing includes: image distortion correction and point cloud data stitching. Furthermore, multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model. Multi-source data fusion is performed to integrate data from different sources, fully utilizing the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0059] In a possible implementation of the embodiment of the present application, the preprocessing module 220 performs preprocessing based on the high-altitude overhead image and the multi-angle shooting data to obtain the target high-altitude overhead image and the target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data splicing, and is used to: Distortion detection is performed based on the high-altitude overhead image to determine the distortion detection result. When the distortion detection result shows that there is distortion, image distortion correction is performed on the high-altitude overhead image to obtain the target high-altitude overhead image; Data screening is performed based on the multi-angle shooting data to determine the lidar point cloud data, point cloud data is stitched based on the lidar point cloud data to obtain stitched point cloud data, and target multi-angle shooting data is determined based on the ground upward-looking image and stitched point cloud data in the multi-angle shooting data.

[0060] In a possible implementation of the embodiment of the present application, the 3D modeling module 230 performs multi-source data fusion based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain the multi-source fusion data, which is used to: Feature points are extracted based on the high-altitude overhead image and the ground upward image to obtain the feature points of the overhead image and the upward image; Matching feature points based on the feature points of the overhead image and the feature points of the upward image to determine the image feature mapping relationship; The laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and based on the image feature mapping relationship, multi-source data fusion is performed on the laser scanning point cloud data and the stitching point cloud data to obtain multi-source fused data.

[0061] A possible implementation of the embodiment of the present application is a 3D real scene modeling system based on a drone, further comprising: The collaborative operation analysis module is used to obtain a map of the area to be modeled, perform collaborative operation analysis of multiple drones based on the map of the area to be modeled, and determine the image acquisition flight plan corresponding to each drone. The collaborative operation analysis of multiple drones is used to control multiple drones to collect images from different heights, angles, and flight routes to form a three-dimensional coverage network. Send the image acquisition flight plan to the corresponding target UAV, and control the target UAV to perform image acquisition according to the image acquisition flight plan; The image acquisition data sent by each target UAV is obtained, and each image acquisition data is fused to obtain a high-altitude bird's-eye view image.

[0062] A possible implementation of the embodiment of the present application is a 3D real scene modeling system based on a drone, further comprising: A multi-dimensional model quality assessment module is used to perform multi-dimensional model quality assessment based on a three-dimensional real scene model and determine the model quality assessment result, wherein the multi-dimensional model quality assessment includes: integrity quality assessment, accuracy quality assessment, consistency quality assessment and texture quality assessment; When the model quality assessment result does not meet the quality requirements, a real-life model abnormality warning is generated.

[0063] A possible implementation of the embodiment of the present application is a 3D real scene modeling system based on a drone, further comprising: The holographic projection module is used to obtain lighting simulation conditions when the model quality assessment result meets the quality requirements. Based on the holographic projection technology and lighting simulation conditions, a virtual three-dimensional image is obtained for the three-dimensional real scene model, wherein the virtual three-dimensional image is used to simulate the scene conditions under different lighting conditions in the virtual space.

[0064] Technicians in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the drone-based three-dimensional real-scene modeling system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0065] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0066] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0067] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0068] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, 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.

[0069] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0070] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0071] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0072] The embodiment of the present application provides a computer program product, which includes a computer program, which implements the method in any of the above embodiments when executed by a processor. Compared with the related art, the embodiment of the present application obtains the high-altitude bird's-eye view image collected by the drone and the ground multi-angle shooting data collected by the ground photography equipment, and then pre-processes the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the pre-processing includes: image distortion correction and point cloud data splicing. Furthermore, multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model. Performing multi-source data fusion integrates data from different sources, fully utilizing the advantages of both, and realizing data complementarity, so as to improve the accuracy and reliability of the three-dimensional real scene model created using multi-source fusion data.

[0073] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0074] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A three-dimensional real scene modeling method based on drone, characterized in that: include: Acquire high-altitude bird's-eye view images collected by drones and ground multi-angle shooting data collected by ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; the ground multi-angle shooting data are used to display the details and texture of the objects; Preprocessing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain a target high-altitude bird's-eye view image and target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching; Multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and three-dimensional modeling is performed based on the multi-source fusion data to obtain a three-dimensional real scene model.

2. The method for three-dimensional real scene modeling based on drone according to claim 1, characterized in that: The preprocessing is performed based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain the target high-altitude bird's-eye view image and the target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching, including: Performing distortion detection based on the high-altitude bird's-eye view image to determine a distortion detection result, and when the distortion detection result indicates that distortion exists, performing image distortion correction on the high-altitude bird's-eye view image to obtain a target high-altitude bird's-eye view image; Data screening is performed based on the multi-angle shooting data to determine the laser radar point cloud data, point cloud data is stitched based on the laser radar point cloud data to obtain stitched point cloud data, and target multi-angle shooting data is determined based on the ground upward-looking image in the multi-angle shooting data and the stitched point cloud data.

3. The method for three-dimensional real scene modeling based on drone according to claim 2, characterized in that: The multi-source data fusion is performed based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain the multi-source fusion data, including: Extract feature points based on the high-altitude overhead image and the ground upward image to obtain overhead image feature points and upward image feature points; Perform feature point matching based on the feature points of the overhead image and the feature points of the upward image to determine an image feature mapping relationship; The laser scanning point cloud data corresponding to the high-altitude bird's-eye view image is obtained, and based on the image feature mapping relationship, multi-source data fusion is performed on the laser scanning point cloud data and the stitching point cloud data to obtain multi-source fused data.

4. The method for three-dimensional real scene modeling based on drone according to claim 1, characterized in that: Before obtaining the high-altitude bird's-eye view image collected by the drone, the method further includes: Obtain a map of the area to be modeled, perform a multi-UAV collaborative operation analysis based on the map of the area to be modeled, and determine an image acquisition flight plan corresponding to each UAV, wherein the multi-UAV collaborative operation analysis is used to control multiple UAVs to acquire images from different heights, different angles, and different flight routes to form a three-dimensional coverage network; Sending the image acquisition flight plan to the corresponding target UAV, and controlling the target UAV to perform image acquisition according to the image acquisition flight plan; The image acquisition data sent by each of the target UAVs is acquired, and each of the image acquisition data is fused to obtain a high-altitude bird's-eye view image.

5. The method for three-dimensional real scene modeling based on drone according to claim 1, characterized in that: After performing three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model, the method further includes: Performing a multi-dimensional model quality assessment based on the three-dimensional real scene model to determine a model quality assessment result, wherein the multi-dimensional model quality assessment includes: integrity quality assessment, accuracy quality assessment, consistency quality assessment and texture quality assessment; When the model quality assessment result is that the model does not meet the quality requirements, an abnormal warning of the real scene model is generated.

6. The method for three-dimensional real scene modeling based on unmanned aerial vehicle according to claim 5, characterized in that: After performing multi-dimensional model quality assessment based on the three-dimensional real scene model and determining the model quality assessment result, the method further includes: When the model quality assessment result meets the quality requirements, the lighting simulation conditions are obtained, and based on the holographic projection technology and the lighting simulation conditions, a virtual three-dimensional image is obtained for the three-dimensional real scene model, wherein the virtual three-dimensional image is used to simulate scene conditions under different lighting conditions in a virtual space.

7. A three-dimensional real scene modeling system based on drone, characterized in that: include: A data acquisition module is used to acquire high-altitude bird's-eye view images collected by drones and ground multi-angle shooting data collected by ground photography equipment, wherein the high-altitude bird's-eye view images are used to display the overall structure and layout of the surface; and the ground multi-angle shooting data are used to display the details and texture of the ground objects; A preprocessing module, used for performing preprocessing based on the high-altitude bird's-eye view image and the multi-angle shooting data to obtain a target high-altitude bird's-eye view image and target multi-angle shooting data, wherein the preprocessing includes: image distortion correction and point cloud data stitching; The three-dimensional modeling module is used to perform multi-source data fusion based on the target high-altitude bird's-eye view image and the target multi-angle shooting data to obtain multi-source fusion data, and perform three-dimensional modeling based on the multi-source fusion data to obtain a three-dimensional real scene model.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the drone-based three-dimensional real scene modeling method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the three-dimensional real scene modeling method based on a drone as described in any one of claims 1 to 6.

Images