Intelligent construction site management method and management system based on unmanned aerial vehicle

Abstract

The invention relates to engineering management, in particular to an intelligent construction site management method and management system based on an unmanned aerial vehicle, and the method comprises the steps: planning an inspection path according to a construction site area, and determining the positions of all shooting points in the inspection path; acquiring a video shot by the unmanned aerial vehicle, and performing attribute marking on a target object in the video; comparing the building in the video with the building in the BIM model to determine the position of each key point in the video, and calculating the actual position of the target object according to the position of each key point in the video; acquiring aerial survey data acquired by the unmanned aerial vehicle, and constructing a three-dimensional live-action model of the construction site area in combination with the on-site video of the construction site area; performing target object marking on the three-dimensional live-action model according to the actual position and the attribute mark of the target object, and constructing a live-action management platform based on the marked three-dimensional live-action model; the technical scheme provided by the invention can effectively overcome the defect that the unmanned aerial vehicle is difficult to effectively and safely manage the construction site in the prior art.

Description

Technical Field

[0001] The present invention relates to engineering management, and in particular to a smart construction site management method and management system based on unmanned aerial vehicles. Background Art

[0002] With the rapid development of modern engineering construction, the number and scale of projects under construction are becoming increasingly large. Scientific construction management is an important part of ensuring the quality, safety and progress of the project. At present, in the construction process of various buildings, the safety management of construction sites still mainly relies on regular or irregular inspections by safety personnel. As the scale of construction projects becomes larger and larger and the structure of buildings becomes more and more complex, it is difficult for personnel to inspect everything, which is prone to omissions and leads to the existence of risks. At the same time, some areas of the construction site are difficult to approach manually, which brings certain difficulties to safety management.

[0003] In recent years, drone technology has developed rapidly and has been widely used in various fields. Drones have the characteristics of flexible flight and high-definition image capture, and can achieve all-round and multi-angle monitoring of construction sites. However, the application of drone technology to construction site management still faces some challenges, such as how to accurately identify and locate various target objects in the construction site area in real time, how to build a precisely matched three-dimensional real-life model based on the actual situation of the construction site area, and how to build a real-life management platform that facilitates safety personnel to manage the construction site. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a smart construction site management method and management system based on drones, which can effectively overcome the defect of the prior art that it is difficult to use drones to effectively and safely manage construction sites.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A smart construction site management method based on drones, comprising the following steps:

[0009] S1. Plan the inspection route according to the construction site area and determine the locations of all shooting points in the inspection route;

[0010] S2, obtain the video taken by the drone and mark the attributes of the target object in the video;

[0011] S3, by comparing the building in the video with the building in the BIM model, determining the position of each key point in the video, and calculating the actual position of the target object according to the position of each key point in the video;

[0012] S4, obtaining the aerial survey data collected by the drone, and combining it with the on-site video of the construction site to build a three-dimensional real scene model of the construction site;

[0013] S5, marking the target object on the three-dimensional real scene model according to the actual position and attribute mark of the target object, and building a real scene management platform based on the marked three-dimensional real scene model;

[0014] S6. Collect multi-dimensional data of the construction site area and analyze and process the multi-dimensional data;

[0015] S7. Associate the multi-dimensional data analysis and processing results with the on-site video of the construction site area and store them in the corresponding target object in the real-view management platform. By selecting the target object in the real-view management platform, the data and video of the target object are obtained.

[0016] Preferably, obtaining a video shot by a drone in S2 and marking the attributes of a target object in the video includes:

[0017] Obtain the videos shot by the drone at each shooting point, perform target detection on the target objects in the video, and mark the attributes of the target objects according to the target detection results;

[0018] Among them, the target objects include the building itself, personnel, vehicles, construction equipment, building materials and safety facilities.

[0019] Preferably, S3 determines the position of each key point in the video by comparing the building in the video with the building in the BIM model, and calculates the actual position of the target object according to the position of each key point in the video, including:

[0020] S31, determining a building body according to the target detection result, and generating a first building outline;

[0021] S32, retrieving the BIM model according to the position of the shooting point of the drone video, and generating a second building outline;

[0022] S33, comparing the first building outline and the second building outline, and determining the position coordinates of each key point in the first building outline according to the comparison result;

[0023] S34. Calculate the actual position coordinates of the target object according to the position coordinates of each key point in the first building outline.

[0024] Preferably, in S4, the aerial survey data collected by the drone is obtained, and a three-dimensional real scene model of the construction site area is constructed in combination with the on-site video of the construction site area, including:

[0025] S41, obtaining the aerial survey data collected by the drone at each shooting point, and generating point cloud data of the construction site area;

[0026] S42, gridding the point cloud data of the construction site area, connecting the discrete points into a continuous grid structure, and constructing a spatial three-dimensional model;

[0027] S43, performing optimization processing including smoothing, removing redundancy and filling holes on the spatial three-dimensional model;

[0028] S44. Use live video of the construction site area to add texture to the spatial 3D model to enhance the realism and readability of the model;

[0029] S45, rendering the spatial three-dimensional model after adding texture by adjusting parameters including lighting, shadow and color, to obtain a three-dimensional real scene model of the construction site area.

[0030] Preferably, in S41, the aerial survey data collected by the drone at each shooting point is obtained, and point cloud data of the construction site area is generated, including:

[0031] S411, constructing a fitting surface to fit the construction site area according to the position coordinates of the shooting points;

[0032] S412, calculating the shooting posture of the UAV at the shooting point according to the vector angle of the fitting surface and the set shooting parameters;

[0033] S413, controlling the UAV to collect aerial survey data at each shooting point with a corresponding shooting posture;

[0034] S414, registering the aerial survey data collected by the drone at different shooting points, and generating point cloud data of the construction site area based on the registered aerial survey data.

[0035] Preferably, the on-site video of the construction site area is collected in 360° panoramic view by an area array video acquisition unit composed of multiple CCD cameras. The on-site video of the construction site area contains multi-angle texture information of each target object, and simultaneously records the posture information and position information of the camera at each moment.

[0036] Preferably, collecting multi-dimensional data of the construction site area in S6 includes:

[0037] S611, compressing and sampling the original signal using a sampling matrix to obtain an intermediate signal, and embedding a sequence number in a data packet of the intermediate signal;

[0038] S612, performing logical operation processing on the data in adjacent data packets, and adding identifiers to generate redundant data packets;

[0039] S613, putting the data packet and the redundant data packet into the signal, and performing data transmission in a disrupted order;

[0040] The identification is composed of the serial numbers of adjacent data packets, and the multi-dimensional data includes monitoring data, monitoring data and electrical data.

[0041] Preferably, the step of analyzing and processing the multidimensional data in S6 includes:

[0042] S621, after receiving the data packet and the redundant data packet, re-order them according to the sequence number and the identifier;

[0043] S622, judging whether packet loss occurs according to the sorting result, if packet loss occurs, recovering data using redundant data packets to obtain an intermediate signal, otherwise directly obtaining the intermediate signal through the data packets;

[0044] S623: Reconstruct the intermediate signal to obtain the original signal.

[0045] A smart construction site management system based on drones, comprising an inspection path planning module, a target object detection module, a target object actual position calculation module, a three-dimensional real scene model construction module, a real scene management platform construction module, a multi-dimensional data analysis and processing module and an associated storage module;

[0046] Inspection route planning module plans the inspection route according to the construction site area and determines the locations of all shooting points in the inspection route;

[0047] The target object detection module obtains the video shot by the drone, detects the target object in the video, and marks the attribute of the target object according to the target detection result;

[0048] The actual position calculation module of the target object determines the position of each key point in the video by comparing the building in the video with the building in the BIM model, and calculates the actual position of the target object based on the position of each key point in the video;

[0049] The 3D real scene model construction module obtains the aerial survey data collected by the drone and combines it with the on-site video of the construction site to build a 3D real scene model of the construction site area;

[0050] A real scene management platform construction module marks the target object on the three-dimensional real scene model according to the actual position and attribute mark of the target object, and builds the real scene management platform based on the marked three-dimensional real scene model;

[0051] The multi-dimensional data analysis and processing module collects multi-dimensional data of the construction site area and analyzes and processes the multi-dimensional data;

[0052] The associated storage module associates and stores the multi-dimensional data analysis and processing results and the on-site video of the construction site area to the corresponding target object in the real-scene management platform, so as to obtain the data and video of the target object by selecting the target object in the real-scene management platform.

[0053] Preferably, the three-dimensional real scene model construction module obtains the aerial survey data collected by the drone, and constructs the three-dimensional real scene model of the construction site area in combination with the on-site video of the construction site area, including:

[0054] Obtain the aerial survey data collected by the drone at each shooting point and generate point cloud data of the construction site area;

[0055] Grid the point cloud data of the construction site area, connect the discrete points into a continuous grid structure, and construct a spatial three-dimensional model;

[0056] Optimize the spatial 3D model including smoothing, removing redundancy and filling holes;

[0057] Use live video of the construction area to add texture to the spatial 3D model to enhance the model's realism and readability;

[0058] The three-dimensional model of the space with added texture is rendered by adjusting parameters including lighting, shadow and color to obtain a three-dimensional real-scene model of the construction site area.

[0059] (III) Beneficial effects

[0060] Compared with the prior art, the intelligent construction site management method and management system based on drones provided by the present invention has the following beneficial effects:

[0061] 1) Plan the inspection route according to the construction site area, determine the positions of all shooting points in the inspection route, obtain the video taken by the drone, and mark the attributes of the target objects in the video. By comparing the buildings in the video with the buildings in the BIM model, determine the positions of the key points in the video, and calculate the actual positions of the target objects based on the positions of the key points in the video, so as to accurately identify and locate various target objects in the construction site area in real time, and provide data support for the subsequent establishment of the corresponding relationship between the target objects and the three-dimensional real scene model;

[0062] 2) Acquire the aerial survey data collected by the drone, and build a 3D real scene model of the construction site area in combination with the on-site video of the construction site area, so as to build a precisely matched 3D real scene model according to the actual situation of the construction site area;

[0063] 3) Mark the target object on the three-dimensional real-scene model according to the actual position and attribute mark of the target object, and build a real-scene management platform based on the marked three-dimensional real-scene model, collect multi-dimensional data of the construction site area, analyze and process the multi-dimensional data, associate the multi-dimensional data analysis and processing results with the on-site video of the construction site area and store them in the corresponding target object in the real-scene management platform. By selecting the target object in the real-scene management platform, the data and video of the target object can be obtained, thereby building a visual real-scene management platform, which is convenient for safety personnel to manage the construction site and effectively improves the quality and efficiency of construction site management. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0065] Figure 1 It is a schematic diagram of the process of the present invention;

[0066] Figure 2 A schematic diagram of a flow chart for calculating the actual position of a target object in the present invention;

[0067] Figure 3 It is a schematic diagram of the process of constructing a three-dimensional real scene model of a construction site area in the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] A smart construction site management method based on drones, such as Figure 1 and Figure 2 As shown, S1, plan an inspection route according to the construction site area, and determine the positions of all shooting points in the inspection route.

[0070] S2. Obtain the video taken by the drone and mark the attributes of the target objects in the video, including:

[0071] Obtain the videos shot by the drone at each shooting point, perform target detection on the target objects in the video, and mark the attributes of the target objects according to the target detection results;

[0072] Among them, the target objects include the building itself, personnel, vehicles, construction equipment, building materials and safety facilities.

[0073] S3. By comparing the building in the video with the building in the BIM model, the position of each key point in the video is determined, and the actual position of the target object is calculated according to the position of each key point in the video, specifically including:

[0074] S31, determining a building body according to the target detection result, and generating a first building outline;

[0075] S32, retrieving the BIM model according to the position of the shooting point of the drone video, and generating a second building outline;

[0076] S33, comparing the first building outline and the second building outline, and determining the position coordinates of each key point in the first building outline according to the comparison result;

[0077] S34. Calculate the actual position coordinates of the target object according to the position coordinates of each key point in the first building outline.

[0078] The above technical solution plans the inspection route according to the construction site area, determines the positions of all shooting points in the inspection route, obtains the video taken by the drone, and marks the attributes of the target objects in the video. By comparing the buildings in the video with the buildings in the BIM model, the positions of the key points in the video are determined, and the actual positions of the target objects are calculated based on the positions of the key points in the video. This enables accurate real-time identification and positioning of various target objects in the construction site area, providing data support for the subsequent establishment of the correspondence between the target objects and the three-dimensional real-scene model.

[0079] like Figure 1 and Figure 3 As shown, S4, obtaining the aerial survey data collected by the drone, and combining it with the on-site video of the construction site to build a three-dimensional real scene model of the construction site area, specifically including:

[0080] S41, obtaining the aerial survey data collected by the drone at each shooting point, and generating point cloud data of the construction site area;

[0081] S42, gridding the point cloud data of the construction site area, connecting the discrete points into a continuous grid structure, and constructing a spatial three-dimensional model;

[0082] S43, performing optimization processing including smoothing, removing redundancy and filling holes on the spatial three-dimensional model;

[0083] S44. Use live video of the construction site area to add texture to the spatial 3D model to enhance the realism and readability of the model;

[0084] S45, rendering the spatial three-dimensional model after adding texture by adjusting parameters including lighting, shadow and color, to obtain a three-dimensional real scene model of the construction site area.

[0085] Specifically, in S41, the aerial survey data collected by the drone at each shooting point is obtained, and point cloud data of the construction site area is generated, including:

[0086] S411, constructing a fitting surface to fit the construction site area according to the position coordinates of the shooting points;

[0087] S412, calculating the shooting posture of the UAV at the shooting point according to the vector angle of the fitting surface and the set shooting parameters;

[0088] S413, controlling the UAV to collect aerial survey data at each shooting point with a corresponding shooting posture;

[0089] S414, registering the aerial survey data collected by the drone at different shooting points, and generating point cloud data of the construction site area based on the registered aerial survey data.

[0090] In the technical solution of the present application, the on-site video of the construction site area is collected in 360° surround view by an area array video acquisition unit composed of multiple CCD cameras. The on-site video of the construction site area contains multi-angle texture information of each target object, and also records the posture information and position information of the camera at each moment.

[0091] The above technical solution obtains the aerial survey data collected by the drone, and builds a three-dimensional real-scene model of the construction site area in combination with the on-site video of the construction site area, so as to build a precisely matched three-dimensional real-scene model according to the actual situation of the construction site area.

[0092] like Figure 1 As shown, S5, according to the actual position and attribute mark of the target object, the three-dimensional real scene model is marked with the target object, and a real scene management platform is constructed based on the marked three-dimensional real scene model.

[0093] S6. Collect multi-dimensional data of the construction site area and analyze and process the multi-dimensional data.

[0094] 1) S6 collects multi-dimensional data of the construction site area, including:

[0095] S611, compressing and sampling the original signal using a sampling matrix to obtain an intermediate signal, and embedding a sequence number in a data packet of the intermediate signal;

[0096] S612, performing logical operation processing on the data in adjacent data packets, and adding identifiers to generate redundant data packets;

[0097] S613, putting the data packet and the redundant data packet into the signal, and performing data transmission in a disrupted order;

[0098] The identification is composed of the serial numbers of adjacent data packets, and the multi-dimensional data includes monitoring data, monitoring data and electrical data.

[0099] 2) S6 performs analysis and processing on multidimensional data, including:

[0100] S621, after receiving the data packet and the redundant data packet, re-order them according to the sequence number and the identifier;

[0101] S622, judging whether packet loss occurs according to the sorting result, if packet loss occurs, recovering data using redundant data packets to obtain an intermediate signal, otherwise directly obtaining the intermediate signal through the data packets;

[0102] S623: Reconstruct the intermediate signal to obtain the original signal.

[0103] S7. Associate the multi-dimensional data analysis and processing results with the on-site video of the construction site area and store them in the corresponding target object in the real-view management platform. By selecting the target object in the real-view management platform, the data and video of the target object are obtained.

[0104] The above technical scheme marks the target object on the three-dimensional real-scene model according to the actual position and attribute mark of the target object, and builds a real-scene management platform based on the marked three-dimensional real-scene model, collects multi-dimensional data of the construction site area, and analyzes and processes the multi-dimensional data, and associates the multi-dimensional data analysis and processing results with the on-site video of the construction site area and stores them in the corresponding target object in the real-scene management platform. By selecting the target object in the real-scene management platform and obtaining the data and video of the target object, a visual real-scene management platform can be built, which is convenient for safety personnel to manage the construction site and effectively improves the quality and efficiency of construction site management.

[0105] On the basis of the above-mentioned smart construction site management method based on drones, the technical solution of the present application also discloses a smart construction site management system based on drones, including an inspection path planning module, a target object detection module, a target object actual position calculation module, a three-dimensional real scene model construction module, a real scene management platform construction module, a multi-dimensional data analysis and processing module and an associated storage module;

[0106] Inspection route planning module plans the inspection route according to the construction site area and determines the locations of all shooting points in the inspection route;

[0107] The target object detection module obtains the video shot by the drone, detects the target object in the video, and marks the attribute of the target object according to the target detection result;

[0108] The actual position calculation module of the target object determines the position of each key point in the video by comparing the building in the video with the building in the BIM model, and calculates the actual position of the target object based on the position of each key point in the video;

[0109] The 3D real scene model construction module obtains the aerial survey data collected by the drone and combines it with the on-site video of the construction site to build a 3D real scene model of the construction site area;

[0110] A real scene management platform construction module marks the target object on the three-dimensional real scene model according to the actual position and attribute mark of the target object, and builds the real scene management platform based on the marked three-dimensional real scene model;

[0111] The multi-dimensional data analysis and processing module collects multi-dimensional data of the construction site area and analyzes and processes the multi-dimensional data;

[0112] The associated storage module associates and stores the multi-dimensional data analysis and processing results and the on-site video of the construction site area to the corresponding target object in the real-scene management platform, so as to obtain the data and video of the target object by selecting the target object in the real-scene management platform.

[0113] Specifically, the 3D real scene model construction module obtains the aerial survey data collected by the drone and combines the on-site video of the construction site area to construct a 3D real scene model of the construction site area, including:

[0114] Obtain the aerial survey data collected by the drone at each shooting point and generate point cloud data of the construction site area;

[0115] Grid the point cloud data of the construction site area, connect the discrete points into a continuous grid structure, and construct a spatial three-dimensional model;

[0116] Optimize the spatial 3D model including smoothing, removing redundancy and filling holes;

[0117] Use live video of the construction area to add texture to the spatial 3D model to enhance the model's realism and readability;

[0118] The three-dimensional model of the space with added texture is rendered by adjusting parameters including lighting, shadow and color to obtain a three-dimensional real-scene model of the construction site area.

[0119] 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 will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart construction site management method based on drones, characterized by: The following steps are involved: S1. Plan the inspection route according to the construction site area and determine the locations of all shooting points in the inspection route; S2, obtain the video taken by the drone and mark the attributes of the target object in the video; S3, by comparing the building in the video with the building in the BIM model, determining the position of each key point in the video, and calculating the actual position of the target object according to the position of each key point in the video; S4, obtaining the aerial survey data collected by the drone, and combining it with the on-site video of the construction site to build a three-dimensional real scene model of the construction site; S5, marking the target object on the three-dimensional real scene model according to the actual position and attribute mark of the target object, and building a real scene management platform based on the marked three-dimensional real scene model; S6. Collect multi-dimensional data of the construction site area and analyze and process the multi-dimensional data; S7. Associate the multi-dimensional data analysis and processing results with the on-site video of the construction site area and store them in the corresponding target object in the real-view management platform. By selecting the target object in the real-view management platform, the data and video of the target object are obtained.

2. The intelligent construction site management method based on drone according to claim 1 is characterized in that: S2 obtains the video shot by the drone and marks the attributes of the target objects in the video, including: Obtain the videos shot by the drone at each shooting point, perform target detection on the target objects in the video, and mark the attributes of the target objects according to the target detection results; Among them, the target objects include the building itself, personnel, vehicles, construction equipment, building materials and safety facilities.

3. The intelligent construction site management method based on drone according to claim 2 is characterized in that: S3 compares the building in the video with the building in the BIM model to determine the position of each key point in the video, and calculates the actual position of the target object based on the position of each key point in the video, including: S31, determining a building body according to the target detection result, and generating a first building outline; S32, retrieving the BIM model according to the position of the shooting point of the drone video, and generating a second building outline; S33, comparing the first building outline and the second building outline, and determining the position coordinates of each key point in the first building outline according to the comparison result; S34. Calculate the actual position coordinates of the target object according to the position coordinates of each key point in the first building outline.

4. The intelligent construction site management method based on drone according to claim 3 is characterized in that: S4 obtains the aerial survey data collected by the drone and combines it with the on-site video of the construction site to build a 3D real scene model of the construction site, including: S41, obtaining the aerial survey data collected by the drone at each shooting point, and generating point cloud data of the construction site area; S42, gridding the point cloud data of the construction site area, connecting the discrete points into a continuous grid structure, and constructing a spatial three-dimensional model; S43, performing optimization processing including smoothing, removing redundancy and filling holes on the spatial three-dimensional model; S44. Use live video of the construction site area to add texture to the spatial 3D model to enhance the realism and readability of the model; S45, rendering the spatial three-dimensional model after adding texture by adjusting parameters including lighting, shadow and color, to obtain a three-dimensional real scene model of the construction site area.

5. The intelligent construction site management method based on drone according to claim 4 is characterized in that: S41 obtains the aerial survey data collected by the drone at each shooting point and generates point cloud data of the construction site area, including: S411, constructing a fitting surface to fit the construction site area according to the position coordinates of the shooting points; S412, calculating the shooting posture of the UAV at the shooting point according to the vector angle of the fitting surface and the set shooting parameters; S413, controlling the UAV to collect aerial survey data at each shooting point with a corresponding shooting posture; S414, registering the aerial survey data collected by the drone at different shooting points, and generating point cloud data of the construction site area based on the registered aerial survey data.

6. The intelligent construction site management method based on drone according to claim 4 is characterized in that: The on-site video of the construction site area is collected in 360° panoramic view by an area array video acquisition unit composed of multiple CCD cameras. The on-site video of the construction site area contains multi-angle texture information of each target object, and simultaneously records the posture information and position information of the camera at each moment.

7. The intelligent construction site management method based on drone according to claim 4 is characterized in that: S6 collects multi-dimensional data of the construction site area, including: S611, compressing and sampling the original signal using a sampling matrix to obtain an intermediate signal, and embedding a sequence number in a data packet of the intermediate signal; S612, performing logical operation processing on the data in adjacent data packets, and adding identifiers to generate redundant data packets; S613, putting the data packet and the redundant data packet into the signal, and performing data transmission in a disrupted order; The identification is composed of the serial numbers of adjacent data packets, and the multi-dimensional data includes monitoring data, monitoring data and electrical data.

8. The intelligent construction site management method based on drones according to claim 7 is characterized in that: S6 analyzes and processes multidimensional data, including: S621, after receiving the data packet and the redundant data packet, re-order them according to the sequence number and the identifier; S622, judging whether packet loss occurs according to the sorting result, if packet loss occurs, recovering data using redundant data packets to obtain an intermediate signal, otherwise directly obtaining the intermediate signal through the data packets; S623: Reconstruct the intermediate signal to obtain the original signal.

9. A drone-based smart construction site management system, used to implement the drone-based smart construction site management method according to claim 1, characterized in that: It includes inspection path planning module, target object detection module, target object actual position calculation module, three-dimensional real scene model construction module, real scene management platform construction module, multi-dimensional data analysis and processing module and associated storage module; Inspection route planning module plans the inspection route according to the construction site area and determines the locations of all shooting points in the inspection route; The target object detection module obtains the video shot by the drone, detects the target object in the video, and marks the attribute of the target object according to the target detection result; The actual position calculation module of the target object determines the position of each key point in the video by comparing the building in the video with the building in the BIM model, and calculates the actual position of the target object based on the position of each key point in the video; The 3D real scene model construction module obtains the aerial survey data collected by the drone and combines it with the on-site video of the construction site to build a 3D real scene model of the construction site area; A real scene management platform construction module marks the target object on the three-dimensional real scene model according to the actual position and attribute mark of the target object, and builds the real scene management platform based on the marked three-dimensional real scene model; The multi-dimensional data analysis and processing module collects multi-dimensional data of the construction site area and analyzes and processes the multi-dimensional data; The associated storage module associates and stores the multi-dimensional data analysis and processing results and the on-site video of the construction site area to the corresponding target object in the real-scene management platform, so as to obtain the data and video of the target object by selecting the target object in the real-scene management platform.

10. The intelligent construction site management system based on drones according to claim 9 is characterized in that: The three-dimensional real scene model construction module obtains the aerial survey data collected by the drone and constructs a three-dimensional real scene model of the construction site area in combination with the on-site video of the construction site area, including: Obtain the aerial survey data collected by the drone at each shooting point and generate point cloud data of the construction site area; Grid the point cloud data of the construction site area, connect the discrete points into a continuous grid structure, and construct a spatial three-dimensional model; Optimize the spatial 3D model by smoothing, removing redundancy and filling holes; Use live video of the construction area to add texture to the spatial 3D model to enhance the model's realism and readability; The three-dimensional model of the space with added texture is rendered by adjusting parameters including lighting, shadow and color to obtain a three-dimensional real-scene model of the construction site area.

Images