Unmanned aerial vehicle automatic inspection path planning method and system based on fusion of three-dimensional geographic information, and medium

Abstract

The invention provides an unmanned aerial vehicle automatic inspection path planning method and system based on fusion of three-dimensional geographic information, and a medium. The method comprises the following steps: constructing a three-dimensional model of a target area based on a three-dimensional visual environment, receiving polygon vertex data input by a user, constructing a polygon area, and obtaining an effective inspection task area; extracting a horizontal projection boundary of the effective inspection task area as a horizontal constraint, constructing a digital surface model, and obtaining a flight three-dimensional space of the unmanned aerial vehicle through space calculation based on the three-dimensional geographic information and a preset safe flight height; receiving inspection parameters set by a user, and obtaining a flight path of the unmanned aerial vehicle based on user setting; converting the flight path of the unmanned aerial vehicle into a standard task file format to obtain a planned path, and controlling the unmanned aerial vehicle to execute inspection to obtain an inspection result; through task area verification and flight space calculation based on a high three-dimensional model, the risk that the unmanned aerial vehicle collides with obstacles and breaks into a no-fly zone is fundamentally avoided.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) automatic control and mission planning technology, and more specifically, to a method, system and medium for UAV automatic inspection path planning based on fused three-dimensional geographic information. Background Technology

[0002] With the widespread application of drone technology in surveying, inspection, and security, the demand for automated and intelligent flight mission planning is becoming increasingly urgent. Traditional two-dimensional planar path planning methods have obvious limitations: they cannot accurately consider actual terrain undulations, building heights, and other three-dimensional spatial information, which can easily lead to collisions between planned flight paths and obstacles, or the inability to maintain a constant shooting distance and angle, thus affecting the quality of data acquisition.

[0003] Existing 3D path planning schemes, while considering elevation information, typically suffer from the following problems: The planning process is not closely integrated with the geographical environment: the planning process is not closely integrated with high-precision 3D models (such as digital surface models, DSM), and spatial constraints such as no-fly zones and complex building complexes are not fully considered, resulting in insufficient safety.

[0004] Insufficient validity verification: User-defined inspection areas lack automated validity verification (such as self-intersection of areas, excessively small area, overlap with no-fly zones, etc.), which may lead to invalid or dangerous flight missions.

[0005] Poor path usability: The generated path may only be a series of discrete waypoints, without taking into account the dynamic constraints of the drone, resulting in an unsmooth flight trajectory and unstable speed when turning, which affects flight efficiency and shooting results.

[0006] Low integration: The process from region setting and route planning to task assignment and execution is fragmented, failing to form a complete and automated solution.

[0007] Therefore, there is an urgent need in this field for an intelligent planning method and system that can deeply integrate three-dimensional geographic information, automatically verify the mission area, and generate smooth, safe flight trajectories that conform to dynamic constraints. Summary of the Invention

[0008] The purpose of this application is to provide a method, system and medium for automatic inspection path planning of unmanned aerial vehicles (UAVs) based on the fusion of three-dimensional geographic information. By verifying the task area and calculating the flyable space based on the high three-dimensional model, the risk of UAVs colliding with obstacles and entering no-fly zones is fundamentally avoided.

[0009] This application also provides a method for automatic inspection path planning of unmanned aerial vehicles (UAVs) based on the fusion of three-dimensional geographic information, including: A 3D model of the target area is constructed based on a 3D visualization environment. The polygon vertex data input by the user is received, and a polygon region is constructed in the 3D model in real time. The validity of the polygon region is verified to obtain the valid inspection task area. The horizontal projection boundary of the effective inspection task area is extracted as a horizontal constraint, a digital surface model is constructed, and three-dimensional geographic information of the area is obtained based on the digital surface model. Based on the three-dimensional geographic information and the preset safe flight altitude, the three-dimensional space in which the UAV can fly is obtained through spatial calculation. Receive inspection parameters set by the user, including the distance between the aircraft and the target, the distance between the flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points; Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. The drone is then controlled to perform inspections based on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained.

[0010] Optionally, in the UAV automatic inspection path planning method based on fused 3D geographic information described in the embodiments of this application, constructing a 3D model of the target area based on a 3D visualization environment specifically includes: A basic 3D interactive environment is built based on a 3D visualization rendering engine; Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, and no-fly zone boundary data; A basic 3D model of the target area is generated based on multi-source geographic information data using 3D modeling algorithms. The basic 3D model of the target area is rendered to enhance the spatial location, shape and correlation of multi-source geographic information data, resulting in a rendered 3D model of the target area.

[0011] Optionally, in the UAV automatic inspection path planning method based on fused 3D geographic information described in the embodiments of this application, the validity verification of the polygonal region specifically includes: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

[0012] Optionally, in the UAV automatic inspection path planning method based on fused three-dimensional geographic information described in the embodiments of this application, the method for constructing the UAV's flyable three-dimensional space includes: Horizontal constraints are established based on the horizontal projection boundary of the effective inspection task area to obtain the planar range boundary of the UAV flight. Based on the planar range boundary of the UAV flight, obtain the raw three-dimensional geographic information of the effective inspection task area; The raw 3D geographic information data is denoised, stitched together and registered to obtain preprocessed data; The preprocessed data is modeled using a 3D modeling algorithm to obtain a digital surface model. 3D geographic information is then extracted from the digital surface model, including terrain undulation data, building vertex elevations, and the distribution and height of obstacles. A safe flight altitude is set, and horizontal and vertical constraint ranges are set based on the safe flight altitude and three-dimensional geographic information to obtain the three-dimensional space in which the UAV can fly.

[0013] Optionally, in the UAV automatic inspection path planning method based on fused 3D geographic information described in this application embodiment, a 3D path covering the effective inspection task area is planned based on user-defined inspection parameters, horizontal constraints, and 3D geographic information to obtain the UAV flight trajectory, specifically including: Receive the inspection parameters set by the user, parse the validity of the inspection parameters, obtain the parsed parameters, and convert the parsed parameters into rule data for path planning and invocation; Obtain horizontal constraints within the effective inspection area, and generate a complete constraint system based on the horizontal constraints and rule data; The structured path planning algorithm is used to perform initial 3D path planning for the UAV based on a complete constraint system. The initial 3D path is smoothed and optimized by using B-spline curve or polynomial trajectory fitting algorithms to eliminate sharp corners in the path and obtain the UAV flight trajectory.

[0014] Optionally, in the UAV automatic inspection path planning method based on fused 3D geographic information described in this application embodiment, the planned path is obtained by converting the UAV flight trajectory into a standard task file format, and the UAV is controlled to perform inspection based on the planned path. Upon reaching each data collection point, the camera is automatically triggered to take pictures to obtain the inspection results. Specifically, this includes: Acquire the drone's flight trajectory and analyze its current format information; Determine whether the current format information meets the set standard format information; If the current format information is not satisfied, the current format information is converted to the standard task file format, and the standard task file format is verified. Based on the verified standard task file format, an executable planning path for the UAV is generated. The inspection is carried out by using a planned path control drone to verify the planned path. Multiple data collection points are set on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures and obtain the inspection results. If the set standard format information is met, the planned path that the drone can execute can be obtained directly.

[0015] Secondly, embodiments of this application provide an automatic inspection path planning system for unmanned aerial vehicles (UAVs) based on fused 3D geographic information. The system includes a memory and a processor. The memory includes a program for an automatic inspection path planning method for UAVs based on fused 3D geographic information. When the program for the automatic inspection path planning method for UAVs based on fused 3D geographic information is executed by the processor, it implements the following steps: A 3D model of the target area is constructed based on a 3D visualization environment. The polygon vertex data input by the user is received, and a polygon region is constructed in the 3D model in real time. The validity of the polygon region is verified to obtain the valid inspection task area. The horizontal projection boundary of the effective inspection task area is extracted as a horizontal constraint, a digital surface model is constructed, and three-dimensional geographic information of the area is obtained based on the digital surface model. Based on the three-dimensional geographic information and the preset safe flight altitude, the three-dimensional space in which the UAV can fly is obtained through spatial calculation. Receive inspection parameters set by the user, including the distance between the aircraft and the target, the distance between the flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points; Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. The drone is then controlled to perform inspections based on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained.

[0016] Optionally, in the UAV automatic inspection path planning system based on fused 3D geographic information described in this application embodiment, constructing a 3D model of the target area based on a 3D visualization environment specifically includes: A basic 3D interactive environment is built based on a 3D visualization rendering engine; Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, and no-fly zone boundary data; A basic 3D model of the target area is generated based on multi-source geographic information data using 3D modeling algorithms. The basic 3D model of the target area is rendered to enhance the spatial location, shape and correlation of multi-source geographic information data, resulting in a rendered 3D model of the target area.

[0017] Optionally, in the UAV automatic inspection path planning system based on fused 3D geographic information described in this application embodiment, the validity verification of the polygonal region specifically includes: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

[0018] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes a program for an automatic inspection path planning method for unmanned aerial vehicles (UAVs) based on fused three-dimensional geographic information. When the program is executed by a processor, it implements the steps of the automatic inspection path planning method for UAVs based on fused three-dimensional geographic information as described in any of the above claims.

[0019] As can be seen from the above, the UAV automatic inspection path planning method, system, and medium provided in this application embodiment, based on the fusion of three-dimensional geographic information, constructs a three-dimensional model of the target area based on a three-dimensional visualization environment, receives polygon vertex data input by the user, constructs polygonal regions in real time on the three-dimensional model, verifies the validity of the polygonal regions, and obtains the valid inspection task area; extracts the horizontal projection boundary of the valid inspection task area as a horizontal constraint, constructs a digital surface model, obtains three-dimensional geographic information within the area based on the digital surface model, and obtains the UAV's flyable three-dimensional space through spatial calculation based on the three-dimensional geographic information and the preset safe flight altitude; and receives the inspection parameters set by the user. The inspection parameters include the distance between the aircraft and the target, the flight path spacing, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points. Based on the user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The UAV flight trajectory is converted into a standard task file format to obtain the planned path. The UAV is controlled to perform the inspection based on the planned path, and the camera is automatically triggered to take pictures when it arrives at each data collection point to obtain the inspection results. Through task area verification and calculation of the flyable space based on the high 3D model, the risk of UAV collisions with obstacles and intrusion into no-fly zones is fundamentally avoided. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart of an automatic inspection path planning method for unmanned aerial vehicles based on fused 3D geographic information provided in this application embodiment; Figure 2 A flowchart of a 3D model construction method for an unmanned aerial vehicle (UAV) automatic inspection path planning method based on fused 3D geographic information, provided in an embodiment of this application; Figure 3 A block diagram of an automatic inspection path planning system for unmanned aerial vehicles (UAVs) based on fused 3D geographic information, provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an automatic UAV inspection path planning method based on fused 3D geographic information, as described in some embodiments of this application. This automatic UAV inspection path planning method based on fused 3D geographic information is used in a terminal device and includes the following steps: S101 constructs a 3D model of the target area based on a 3D visualization environment, receives polygon vertex data input by the user, constructs a polygon area in the 3D model in real time, verifies the validity of the polygon area, and obtains the valid inspection task area. S102, extract the horizontal projection boundary of the effective inspection task area as a horizontal constraint, construct a digital surface model, obtain three-dimensional geographic information within the area based on the digital surface model, and obtain the UAV's flyable three-dimensional space through spatial calculation based on the three-dimensional geographic information and the preset safe flight altitude. S103 receives the inspection parameters set by the user. The inspection parameters include the distance between the aircraft and the target, the distance between the flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points. S104: Based on the user-defined inspection parameters, horizontal constraints, and three-dimensional geographic information, a three-dimensional path covering the effective inspection task area is planned to obtain the UAV flight trajectory. S105 converts the drone's flight trajectory into a standard mission file format to obtain a planned path. Based on the planned path, it controls the drone to perform inspections. When the drone arrives at each data collection point, it automatically triggers the camera to take pictures and obtains the inspection results.

[0025] It should be noted that in the 3D visualization environment, a 3D model of the target area is rendered and displayed. This 3D model includes terrain, buildings, and geographic information elements related to no-fly zones. The system receives polygon vertex data input by the user through a graphical interface, constructs and displays a closed polygonal region in the 3D scene in real time, and extracts the horizontal projection boundary of the validated polygonal region as a spatial horizontal constraint for path planning. 3D geographic information data within this region is acquired to construct a digital elevation model or digital surface model to accurately represent the elevation information of terrain and obstacles. Based on the 3D model and a preset safe flight altitude, spatial calculations are performed to determine the flyable 3D space for the UAV within this region.

[0026] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a 3D model construction method for an unmanned aerial vehicle (UAV) automatic inspection path planning method based on fused 3D geographic information, as described in some embodiments of this application. According to embodiments of the present invention, constructing a 3D model of a target area based on a 3D visualization environment specifically includes: S201 is a basic 3D interactive environment built on a 3D visualization rendering engine. S202, Collect multi-source geographic information data of the target area. The multi-source geographic information data includes topographic elevation data, building outline and height data and no-fly zone boundary data. S203, Based on multi-source geographic information data, a basic three-dimensional model of the target area is generated using a three-dimensional modeling algorithm; S204 renders the basic 3D model of the target area, enhancing the spatial location, shape, and correlation of multi-source geographic information data to obtain the rendered 3D model of the target area.

[0027] It should be noted that in the 3D visualization environment setup phase: the system first starts the 3D visualization rendering engine to build a basic 3D interactive environment, supporting graphical interface operation and real-time rendering display, providing support for subsequent 3D model loading and interaction; Geographic information data acquisition and import process: Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, no-fly zone boundary data, etc.; import this data into the system according to the preset format to form the data source for 3D model construction; 3D model construction and integration: Based on the imported geographic information data, a basic 3D model of the target area is generated through 3D modeling algorithms. This model integrates core geographic information elements such as terrain, buildings, and no-fly zones to ensure that the model can accurately represent the 3D spatial characteristics of the target area. 3D model rendering and display: In the established 3D visualization environment, the completed 3D model is rendered in real time, clearly presenting the spatial location, shape and relationship of each geographic information element, making it convenient for users to intuitively view the target area environment, and providing a visualization foundation for subsequent task area construction.

[0028] According to an embodiment of the present invention, validating the polygonal region specifically includes: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

[0029] It should be noted that, based on the completed 3D model of the target area, the following process is executed: Data receiving stage: The system receives polygon vertex data input by the user through a graphical interface. This data is the basis for constructing the inspection task area and directly determines the coverage and shape of the area. Real-time region construction: Based on the received vertex data, a closed polygon region is generated in real time in the rendered and displayed 3D model of the target region, realizing a "what you see is what you get" interactive effect, making it convenient for users to intuitively confirm whether the region meets the inspection requirements. Validity verification process: To avoid invalid or dangerous flight missions, multi-dimensional verification is performed on the constructed polygonal region, including vertex count verification (to ensure the validity of the region shape), region area verification (to ensure the feasibility of the inspection operation), self-intersection detection (to ensure the compliance of the region logic), and no-fly zone overlap detection (to ensure flight safety). Valid region confirmation step: Only when the polygonal region passes all the above checks can it be determined as a valid inspection task region, serving as the basic constraint for subsequent flight space calculation and path planning; if it fails the checks, the user needs to be notified to adjust the vertex data and reconstruct the region.

[0030] According to an embodiment of the present invention, a method for constructing a flyable three-dimensional space for a drone includes: Horizontal constraints are established based on the horizontal projection boundary of the effective inspection task area to obtain the planar range boundary of the UAV flight. Based on the planar range boundary of the UAV flight, obtain the raw three-dimensional geographic information of the effective inspection task area; The raw 3D geographic information data is denoised, stitched together and registered to obtain preprocessed data; The preprocessed data is modeled using a 3D modeling algorithm to obtain a digital surface model. 3D geographic information is then extracted from the digital surface model, including terrain undulation data, building vertex elevations, and the distribution and height of obstacles. A safe flight altitude is set, and horizontal and vertical constraint ranges are set based on the safe flight altitude and three-dimensional geographic information to obtain the three-dimensional space in which the UAV can fly.

[0031] It should be noted that the steps for calculating flyable space are analyzed as follows: Horizontal constraint determination step: Extract the horizontal projection boundary of the valid inspection task area that has passed the verification, and use it as the horizontal spatial constraint for path planning to clarify the plane range boundary of the UAV flight and avoid exceeding the preset inspection area; Digital Surface Model (DSM) Construction: Based on the target area range corresponding to the effective inspection task area, the geographic information processing module is called to obtain the raw three-dimensional geographic information data (such as terrain elevation, building height, and feature outline) within the area. After data preprocessing (denoising, stitching, and registration), a three-dimensional modeling algorithm is used to construct the digital surface model of the area, accurately representing the surface elevation characteristics of all features within the area. The three-dimensional geographic information extraction stage: using the constructed digital surface model as a carrier, the three-dimensional geographic information of the area is accurately extracted from it, including key information such as terrain relief data, building vertex elevation, and the distribution and height of obstacles, to provide accurate data support for subsequent spatial calculations; Flightable 3D Space Calculation: Combining the extracted 3D geographic information with the user-preset safe flight altitude (i.e., the minimum safe distance that the drone must maintain from various ground features / obstacles), spatial algorithms such as spatial overlay analysis and buffer zone calculation are used to delineate a 3D space that meets both horizontal constraints and vertical safe distance requirements. This space is the 3D area where the drone can fly safely, ensuring that the subsequently planned path avoids all obstacles.

[0032] By integrating precise spatial constraints with three-dimensional information, the safety of UAV flight is fundamentally guaranteed, providing a reliable spatial boundary basis for subsequent path planning. The horizontal projection boundary of the effective area is extracted as a horizontal constraint, and three-dimensional geographic information data within the area is obtained to construct a digital elevation or surface model. Combined with the preset safe flight altitude, the three-dimensional space in which the UAV can fly is calculated.

[0033] According to an embodiment of the present invention, a three-dimensional path covering the effective inspection task area is planned based on user-defined inspection parameters, horizontal constraints, and three-dimensional geographic information to obtain the UAV flight trajectory, specifically including: Receive the inspection parameters set by the user, parse the validity of the inspection parameters, obtain the parsed parameters, and convert the parsed parameters into rule data for path planning and invocation; Obtain horizontal constraints within the effective inspection area, and generate a complete constraint system based on the horizontal constraints and rule data; The structured path planning algorithm is used to perform initial 3D path planning for the UAV based on a complete constraint system. The initial 3D path is smoothed and optimized by using B-spline curve or polynomial trajectory fitting algorithms to eliminate sharp corners in the path and obtain the UAV flight trajectory.

[0034] According to an embodiment of the present invention, a planned path is obtained by converting the UAV flight trajectory into a standard task file format. The UAV is then controlled to perform inspections based on the planned path, and the camera is automatically triggered to take pictures when it arrives at each data collection point to obtain the inspection results. Specifically, this includes: Acquire the drone's flight trajectory and analyze its current format information; Determine whether the current format information meets the set standard format information; If the current format information is not satisfied, the current format information is converted to the standard task file format, and the standard task file format is verified. Based on the verified standard task file format, an executable planning path for the UAV is generated. The inspection is carried out by using a planned path control drone to verify the planned path. Multiple data collection points are set on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures and obtain the inspection results. If the set standard format information is met, the planned path that the drone can execute can be obtained directly.

[0035] It should be noted that the standard mission file conversion process involves calling the mission management and communication module to convert the UAV flight trajectory obtained after optimization into a standard mission file format (such as KMZ or Mission format) that can be recognized by the flight control system or simulator. During the conversion process, key information in the inspection parameters (such as inspection speed, shooting point location, and number of shots) needs to be integrated simultaneously to ensure that the mission file contains complete flight control instructions and operation instructions. The planning path confirmation and task issuance process involves: verifying the completeness of the converted standard task file (confirming that the flight trajectory data and operation instructions are not missing or incorrect). Once the verification is successful, the final executable planning path can be obtained. The task file is then issued to the designated UAV through the ground station system, establishing a communication connection between the UAV and the ground system to ensure stable instruction transmission. The drone inspection execution control process: After receiving the mission file, the drone parses the planned path information and operation instructions and starts the fully automatic flight mode; the flight control system strictly follows the planned path to execute the inspection mission and provides real-time feedback on the flight status (such as current position, flight speed, and remaining battery power) to the ground system to ensure that the flight process is monitorable and traceable; Automatic photo triggering and inspection result acquisition: During the flight of the UAV, the positioning module matches the current position with the preset data collection points in the task file in real time; when it arrives at any collection point, the flight control system automatically triggers the onboard camera to take pictures according to the set number of pictures; after all the inspection tasks are completed, the UAV automatically returns to base and uploads the collected image data (i.e., inspection results) to the ground system through the communication module to complete the entire inspection process; Compatibility is ensured by using standard file formats, and operational accuracy is ensured by precise positioning and automatic triggering, ultimately obtaining complete inspection results efficiently. The optimized flight trajectory is converted into a standard task file format, sent to the drone, and controlled to perform inspections according to the planned path, automatically triggering photo taking when it arrives at the collection point.

[0036] In a preferred embodiment of this application, it is assumed that the property management or engineering department needs to conduct a comprehensive automated image acquisition of the facade and roof of a specific residential building in a community for the purpose of detecting exterior wall damage, investigating illegal buildings, or 3D modeling.

[0037] Implementation process: 3D scene interaction, task area construction and verification: The operator starts the system, and the 3D visualization and interaction module loads a real-world 3D model or a high-precision oblique photogrammetry model of the community. The model clearly shows the target building, surrounding buildings, trees, roads, and no-fly zones set up to ensure privacy and security (such as the airspace above schools and kindergartens).

[0038] The operator uses the mouse to draw a closed polygonal area around the outer contour of the target residential building in the 3D scene. This polygon not only covers the building's projection but also reserves sufficient safety distance and camera field of view space.

[0039] Once the drawing is complete, the region verification module immediately initiates the automated verification process: Vertex and closure check: Ensure that the polygon consists of at least 3 vertices and is closed at both ends.

[0040] Area verification: Calculate the area of ​​the polygon to ensure that it is not less than the minimum inspection area set by the system (e.g., 100 square meters) to avoid delineating an invalid area that is too small due to misoperation.

[0041] Self-intersection detection: Ensures that the boundary lines of a polygon do not intersect each other, forming a logically valid region.

[0042] No-fly zone overlap detection: The system performs spatial overlay analysis between the polygon and the no-fly zones in the database. For example, if the area drawn by the operator inadvertently covers the airspace above an adjacent kindergarten, the system will immediately issue an alarm and highlight the overlapping part, requiring the user to readjust the area until all no-fly zones are completely avoided.

[0043] Flightable space calculation: After the region verification is passed, the system extracts the horizontal projection boundary of the polygon as the horizontal constraint for path planning.

[0044] The geographic information processing module calls the digital surface model (DSM) for the area. This DSM accurately contains elevation information of the ground, the target building, surrounding trees, and other structures.

[0045] The system performs spatial analysis on the DSM based on the user-preset safe flight altitude (e.g., specifying that the drone must maintain a distance of at least 10 meters from any building surface). Through calculation, it generates a three-dimensional flyable space that surrounds the target building, remains roughly parallel to the building's surface shape, and meets the minimum safe distance. This space is open above the roof and forms a "shell"-like passageway on the side of the building.

[0046] Inspection parameter configuration: Operators can set specific parameters for this inspection task through the parameter configuration module: Distance between the drone and the shooting area: For exterior wall inspection, it is set to 15 meters (that is, the drone maintains a distance of 15 meters from the building facade).

[0047] Line spacing: Set to 8 meters to ensure sufficient image overlap.

[0048] Inspection speed: Set to 3 meters per second to ensure image clarity.

[0049] Shooting point spacing: A shooting point is set every 5 meters along the flight path.

[0050] Number of shots per shooting point: To perform 3D reconstruction, one photo is taken at each shooting point.

[0051] 3D Path Intelligent Planning and Trajectory Optimization: The path planning and optimization engine begins to work, using the three-dimensional flyable space calculated in the previous step as the boundary and the user-defined parameters as the rules to perform intelligent planning.

[0052] Path generation: The system automatically generates zigzag or spiral 3D flight paths covering the entire flyable space. For example, for a building facade, it generates multiple parallel flight paths perpendicular to the ground; for a roof, it generates flight paths parallel to the ground. All these waypoints are precisely placed within the previously calculated "safety shell" passageway.

[0053] Trajectory optimization: The generated initial path may contain sharp corners. Optimization algorithms (such as B-spline curves and polynomial trajectory fitting) smooth this path, generating a continuous, smooth flight trajectory that conforms to UAV dynamic constraints (such as maximum turning radius and maximum pitch angle). This allows the UAV to turn smoothly and steadily around building corners, avoiding sudden stops and turns, thus ensuring the stability of the captured footage and flight safety.

[0054] Task file generation and automatic execution: Once the planning is complete, the mission management and communication module will package and convert the final optimized 3D flight trajectory, all waypoint coordinates, flight speed, and camera trigger commands into a standard KMZ mission file.

[0055] The operator uploaded the KMZ file to the inspection drone using ground station software.

[0056] After takeoff, the drone enters fully automatic operation mode. The flight control system strictly follows the planned three-dimensional trajectory: The drone autonomously flies from the takeoff point to the starting point of the mission area.

[0057] It flies smoothly along the three-dimensional trajectory of the building's side and top, always maintaining a set safe distance from the building surface.

[0058] Whenever the system reaches a preset data collection point, the flight control system automatically triggers the onboard camera to take pictures, capturing complete image data of the building's facade and roof.

[0059] After the mission is completed, the drone automatically returns to base. The collected image data can be directly used for subsequent manual analysis or automated detection using AI algorithms (such as crack identification and tile detachment detection).

[0060] In summary, compared with the prior art, the present invention has the following significant advantages: Intelligentization and Automation: By deeply integrating 3D geographic information into every aspect of route planning, the entire process from area setting and parameter configuration to route generation and task issuance is fully automated, greatly improving operational efficiency.

[0061] High path quality: The generated path is not only three-dimensional, but also smooth and continuous, conforming to the dynamic characteristics of the UAV, ensuring flight stability and data acquisition quality (such as image clarity and overlap rate).

[0062] Highly practical: By outputting standard mission files, it can seamlessly interface with mainstream flight control systems and simulators on the market, exhibiting excellent versatility and ease of use.

[0063] Secondly, embodiments of this application provide an automatic inspection path planning system for unmanned aerial vehicles (UAVs) based on fused 3D geographic information. The system includes a memory and a processor. The memory contains a program for an automatic inspection path planning method for UAVs based on fused 3D geographic information. When the program for the automatic inspection path planning method for UAVs based on fused 3D geographic information is executed by the processor, it performs the following steps: A 3D model of the target area is constructed based on a 3D visualization environment. The polygon vertex data input by the user is received, and a polygon region is constructed in the 3D model in real time. The validity of the polygon region is verified to obtain the valid inspection task area. The horizontal projection boundary of the effective inspection task area is extracted as a horizontal constraint, a digital surface model is constructed, and three-dimensional geographic information of the area is obtained based on the digital surface model. Based on the three-dimensional geographic information and the preset safe flight altitude, the three-dimensional space in which the UAV can fly is obtained through spatial calculation. The system receives inspection parameters set by the user, including the distance between the aircraft and the target, the spacing between flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points. Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. The drone is then controlled to perform inspections based on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained.

[0064] It should be noted that the system includes the following components: 3D Visualization and Interaction Module: Used to render 3D scenes and receive user interactions to define polygonal task areas.

[0065] Region verification module: Connected to the 3D visualization and interaction module, it is used to verify the validity of user-defined polygonal regions.

[0066] Geographic Information Processing Module: Used to acquire and process 3D geographic information data, construct digital surface models, and calculate flyable space.

[0067] Parameter configuration module: Used to receive inspection parameters set by the user.

[0068] Path planning and optimization engine: Connected to the area verification module, geographic information processing module and parameter configuration module respectively, it is used to generate and optimize three-dimensional flight paths and trajectories.

[0069] Task Management and Communication Module: Connected to the path planning and optimization engine, it generates standard task files and communicates with the UAV flight control system to issue task commands.

[0070] According to an embodiment of the present invention, constructing a three-dimensional model of a target area based on a three-dimensional visualization environment specifically includes: A basic 3D interactive environment is built based on a 3D visualization rendering engine; Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, and no-fly zone boundary data; A basic 3D model of the target area is generated based on multi-source geographic information data using 3D modeling algorithms. The basic 3D model of the target area is rendered to enhance the spatial location, shape and correlation of multi-source geographic information data, resulting in a rendered 3D model of the target area.

[0071] According to an embodiment of the present invention, validating the polygonal region specifically includes: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

[0072] like Figure 3 As shown, the core components of the system include: React frontend: Map component: Displays drone location and inspection route; Task management: Create, issue, and monitor inspection tasks; Real-time monitoring: Receive real-time data and video from drones via WebSocket; Backend API server Spring Boot: User authentication: login verification and access control; Task management: Handles task planning, assignment, and status tracking; Real-time service: Communicates with the front end and drones via WebSocket; Drone side: It communicates with the backend via 4G / 5G networks, receives control commands, and uploads status data and media files.

[0073] A third aspect of the present invention provides a computer-readable storage medium including a program for an automatic inspection path planning method for unmanned aerial vehicles (UAVs) based on fused three-dimensional geographic information. When the program is executed by a processor, it implements the steps of the automatic inspection path planning method for UAVs based on fused three-dimensional geographic information as described above.

[0074] This invention discloses a method, system, and medium for automatic inspection path planning of unmanned aerial vehicles (UAVs) based on fused 3D geographic information. It constructs a 3D model of the target area based on a 3D visualization environment, receives user-input polygon vertex data, constructs polygonal regions in real time on the 3D model, verifies the validity of these regions to obtain the valid inspection task area, extracts the horizontal projection boundary of the valid inspection task area as a horizontal constraint, constructs a digital surface model, acquires 3D geographic information within the area based on the digital surface model, and obtains the UAV's flyable 3D space through spatial calculation based on the 3D geographic information and a preset safe flight altitude. It also receives inspection parameters set by the user. The inspection parameters include the distance between the aircraft and the target, the flight path spacing, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points. Based on the user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The UAV flight trajectory is converted into a standard task file format to obtain the planned path. The UAV is controlled to perform the inspection based on the planned path, and the camera is automatically triggered to take pictures when it arrives at each data collection point to obtain the inspection results. Through task area verification and calculation of the flyable space based on the high 3D model, the risk of UAV collisions with obstacles and intrusion into no-fly zones is fundamentally avoided.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0076] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0077] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0078] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] Alternatively, if the integrated units of the present invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. An unmanned aerial vehicle automatic inspection path planning method based on fused three-dimensional geographic information, characterized in that, include: A 3D model of the target area is constructed based on a 3D visualization environment. The polygon vertex data input by the user is received, and a polygon region is constructed in the 3D model in real time. The validity of the polygon region is verified to obtain the valid inspection task area. The horizontal projection boundary of the effective inspection task area is extracted as a horizontal constraint, a digital surface model is constructed, and three-dimensional geographic information of the area is obtained based on the digital surface model. Based on the three-dimensional geographic information and the preset safe flight altitude, the three-dimensional space in which the UAV can fly is obtained through spatial calculation. Receive inspection parameters set by the user, including the distance between the aircraft and the target, the distance between the flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points; Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. The drone is then controlled to perform inspections based on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained.

2. The method for automatic inspection path planning of unmanned aerial vehicles based on fused three-dimensional geographic information according to claim 1, characterized in that, Constructing a 3D model of the target area based on a 3D visualization environment, specifically including: A basic 3D interactive environment is built based on a 3D visualization rendering engine; Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, and no-fly zone boundary data; A basic 3D model of the target area is generated based on multi-source geographic information data using 3D modeling algorithms. The basic 3D model of the target area is rendered to enhance the spatial location, shape and correlation of multi-source geographic information data, resulting in a rendered 3D model of the target area.

3. The method for automatic inspection path planning of unmanned aerial vehicles based on fused three-dimensional geographic information according to claim 2, characterized in that, The validity of the polygonal region is validated, specifically including: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

4. The UAV automatic inspection path planning method based on fused three-dimensional geographic information according to claim 3, characterized in that, Methods for constructing a flyable 3D space for drones include: Horizontal constraints are established based on the horizontal projection boundary of the effective inspection task area to obtain the planar range boundary of the UAV flight. Based on the planar range boundary of the UAV flight, obtain the raw three-dimensional geographic information of the effective inspection task area; The raw 3D geographic information data is denoised, stitched together and registered to obtain preprocessed data; The preprocessed data is modeled using a 3D modeling algorithm to obtain a digital surface model. 3D geographic information is then extracted from the digital surface model, including terrain undulation data, building vertex elevations, and the distribution and height of obstacles. A safe flight altitude is set, and horizontal and vertical constraint ranges are set based on the safe flight altitude and three-dimensional geographic information to obtain the three-dimensional space in which the UAV can fly.

5. The UAV automatic inspection path planning method based on fused three-dimensional geographic information according to claim 4, characterized in that, Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned, resulting in the UAV flight trajectory, which specifically includes: Receive the inspection parameters set by the user, parse the validity of the inspection parameters, obtain the parsed parameters, and convert the parsed parameters into rule data for path planning and invocation; Obtain horizontal constraints within the effective inspection area, and generate a complete constraint system based on the horizontal constraints and rule data; The structured path planning algorithm is used to perform initial 3D path planning for the UAV based on a complete constraint system. The initial 3D path is smoothed and optimized by using B-spline curve or polynomial trajectory fitting algorithms to eliminate sharp corners in the path and obtain the UAV flight trajectory.

6. The method for automatic inspection path planning of unmanned aerial vehicles based on fused three-dimensional geographic information according to claim 5, characterized in that, The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. Based on this path, the drone is controlled to perform inspections. Upon reaching each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained, including: Acquire the drone's flight trajectory and analyze its current format information; Determine whether the current format information meets the set standard format information; If the current format information is not satisfied, the current format information is converted to the standard task file format, and the standard task file format is verified. Based on the verified standard task file format, an executable planning path for the UAV is generated. The inspection is carried out by using a planned path control drone to verify the planned path. Multiple data collection points are set on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures and obtain the inspection results. If the set standard format information is met, the planned path that the drone can execute can be obtained directly.

7. A UAV automatic inspection path planning system based on fused three-dimensional geographic information, characterized in that, The system includes a memory and a processor. The memory contains a program for an automatic UAV inspection path planning method based on fused 3D geographic information. When the processor executes the program for the automatic UAV inspection path planning method based on fused 3D geographic information, it performs the following steps: A 3D model of the target area is constructed based on a 3D visualization environment. The polygon vertex data input by the user is received, and a polygon region is constructed in the 3D model in real time. The validity of the polygon region is verified to obtain the valid inspection task area. The horizontal projection boundary of the effective inspection task area is extracted as a horizontal constraint, a digital surface model is constructed, and three-dimensional geographic information of the area is obtained based on the digital surface model. Based on the three-dimensional geographic information and the preset safe flight altitude, the three-dimensional space in which the UAV can fly is obtained through spatial calculation. Receive inspection parameters set by the user, including the distance between the aircraft and the target, the distance between the flight paths, the inspection speed, the number of shots taken at each shooting point, and the interval between the aircraft shooting points; Based on user-defined inspection parameters, horizontal constraints, and 3D geographic information, a 3D path covering the effective inspection task area is planned to obtain the UAV flight trajectory. The drone's flight trajectory is converted into a standard mission file format to obtain a planned path. The drone is then controlled to perform inspections based on the planned path. When the drone arrives at each data collection point, the camera is automatically triggered to take pictures, and the inspection results are obtained.

8. The UAV automatic inspection path planning system based on fused three-dimensional geographic information according to claim 7, characterized in that, Constructing a 3D model of the target area based on a 3D visualization environment, specifically including: A basic 3D interactive environment is built based on a 3D visualization rendering engine; Collect multi-source geographic information data of the target area, including topographic elevation data, building outline and height data, and no-fly zone boundary data; A basic 3D model of the target area is generated based on multi-source geographic information data using 3D modeling algorithms. The basic 3D model of the target area is rendered to enhance the spatial location, shape and correlation of multi-source geographic information data, resulting in a rendered 3D model of the target area.

9. The UAV automatic inspection path planning system based on fused three-dimensional geographic information according to claim 8, characterized in that, The validity of the polygonal region is validated, specifically including: Receive polygon vertex data input by the user, analyze the number of polygon vertices, and compare the number of polygon vertices with a set threshold. The projected area of ​​the polygon is calculated based on the polygon region, and then compared with a preset area threshold. The polygon boundary is detected based on the polygon region to obtain boundary information, and the existence of boundary self-intersection is analyzed based on the boundary information. Determine whether the polygonal region spatially overlaps with a known no-fly zone; If the number of polygon vertices is greater than or equal to the set threshold, the polygon projection area is greater than or equal to the preset area threshold, and the boundary information does not have self-intersection and no spatial overlap, then the polygon region is determined to be valid, and a valid inspection task area is obtained.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a UAV automatic inspection path planning method program based on fused three-dimensional geographic information. When the UAV automatic inspection path planning method program based on fused three-dimensional geographic information is executed by a processor, it implements the steps of the UAV automatic inspection path planning method based on fused three-dimensional geographic information as described in any one of claims 1 to 6.

Images