A bridge alignment measurement method, device, equipment and medium based on virtual simulation and autonomous flight of unmanned aerial vehicles

Abstract

The present application discloses a method, device, equipment and medium for bridge alignment measurement based on virtual simulation and UAV autonomous flight, which relates to the technical field of bridge measurement and is applied to a bridge alignment measurement system. The method includes: obtaining a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a UAV based on an initial flight path autonomously planned by the UAV; generating an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the longitude, latitude and altitude information of each waypoint; obtaining a target bridge image captured by the UAV based on the aerial photography path file, and generating a target three-dimensional model of the bridge based on the target bridge image; using the plane fitting technology and quantifying the vertical undulation of the bridge according to the target three-dimensional model, and determining the vertical deviation between the quantified data and the bridge design data. It can reduce the risk and difficulty of bridge alignment measurement.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge measurement, and particularly relates to a bridge alignment measurement method, device, equipment and medium based on virtual simulation and autonomous flight of an unmanned aerial vehicle (UAV). Background Art

[0002] Currently, traditional bridge alignment measurement equipment, including total stations and levels, can complete the measurement of bridge alignment. However, the operation is relatively cumbersome, requiring operations such as station moving and station setting, the measurement process is troublesome, and the measurement time is long. In addition, the purchase and maintenance costs of levels and total stations are relatively high, requiring expensive instrument equipment and professional maintenance personnel. Moreover, in complex construction sites, operators may need to carry out measurement work in dangerous environments such as high altitudes and cliffs, increasing the safety risks of the operation.

[0003] In summary, how to reduce the risks and difficulties of bridge alignment measurement is a problem to be solved currently. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a bridge alignment measurement method, device, equipment and medium based on virtual simulation and autonomous flight of an unmanned aerial vehicle (UAV), which can reduce the risks and difficulties of bridge alignment measurement. The specific solutions are as follows:

[0005] In a first aspect, the present application discloses a bridge alignment measurement method based on virtual simulation and autonomous flight of an unmanned aerial vehicle (UAV), which is applied to a bridge alignment measurement system. The method includes:

[0006] Obtain a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by the UAV based on an initial flight path autonomously planned by the UAV;

[0007] Generate an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file includes the longitude, latitude and altitude information of each flight point;

[0008] Obtain a target bridge image captured by the UAV based on the aerial photography path file, and generate a target three-dimensional model of the bridge based on the target bridge image;

[0009] Use plane fitting technology and determine the vertical undulation of the bridge according to the target three-dimensional model, and determine the vertical deviation between the quantified data and the bridge design data.

[0010] Optionally, the generating an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file includes:

[0011] Construct a space model based on the bridge simulation environment;

[0012] Determine the flight area in the spatial model based on a predetermined shooting area, determine a number of waypoints in the flight area based on the UAV parameters, and generate an initial aerial photography path according to the waypoints;

[0013] Complete obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path;

[0014] Optimize the obstacle avoidance path to generate an optimal aerial photography path to obtain an aerial photography path file; the path length of the optimal aerial photography path is less than or equal to that of the obstacle avoidance path.

[0015] Optionally, the completing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path includes:

[0016] Use the A* algorithm and complete obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path.

[0017] Optionally, the optimizing the obstacle avoidance path to generate an optimal aerial photography path to obtain an aerial photography path file includes:

[0018] Use an energy consumption model and a shortest path calculation model to optimize the obstacle avoidance path to generate an optimal aerial photography path with energy consumption and path meeting preset requirements to obtain an aerial photography path file;

[0019] Correspondingly, the shortest path calculation model is the Dijkstra algorithm; the energy consumption model is: ; where represents energy consumption, represents flight distance, represents flight speed, represents flight time, represents a constant.

[0020] Optionally, the constructing a spatial model based on the bridge simulation environment includes:

[0021] Construct a geometric model based on the bridge simulation environment; the geometric model includes obstacles represented by geometric shapes.

[0022] Optionally, the obtaining a bridge simulation environment based on an initial bridge image includes:

[0023] Obtain a bridge simulation environment corresponding to an initial bridge image constructed after simulating a reference 3D model of a bridge based on a virtual game engine; the reference 3D model is a model constructed by 3D reconstruction software based on the initial bridge image.

[0024] Optionally, after determining the vertical deviation between the quantified data and the bridge design data, it further includes:

[0025] If the vertical deviation exceeds a preset deviation value, a target alarm is issued according to a preset alarm method; the target alarm includes the vertical deviation exceeding the preset deviation value and the position information corresponding to the vertical deviation.

[0026] In a second aspect, the present application discloses a bridge alignment measurement device based on virtual simulation and autonomous UAV flight, which is applied to a bridge alignment measurement system. The device includes:

[0027] A first acquisition module, configured to acquire a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a UAV based on an initial flight path autonomously planned by the UAV.

[0028] A file generation module, configured to generate an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file includes the longitude, latitude and altitude information of each waypoint.

[0029] A second acquisition module, configured to acquire a target bridge image captured by the UAV based on the aerial photography path file, and generate a target three-dimensional model of the bridge based on the target bridge image.

[0030] A measurement module, configured to quantify the vertical undulation of the bridge by using a plane fitting technique and according to the target three-dimensional model, and determine the vertical deviation between the quantified data and the bridge design data.

[0031] In a third aspect, the present application discloses an electronic device, including:

[0032] A memory, configured to store a computer program;

[0033] A processor, configured to execute the computer program to implement the aforementioned bridge alignment measurement method based on virtual simulation and autonomous UAV flight.

[0034] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the aforementioned bridge alignment measurement method based on virtual simulation and autonomous UAV flight is implemented.

[0035] It can be seen that this application obtains a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image taken by a drone based on the initial flight path; the initial flight path is an initial flight path constructed by a drone route planning system based on drone performance parameters and a three-dimensional model of the original bridge structure; an optimal aerial photography path is generated based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the latitude, longitude, and altitude information of each waypoint; a target bridge image taken by the drone based on the aerial photography path file is obtained, and a target three-dimensional model of the bridge is generated based on the target bridge image; the vertical undulation of the bridge is quantified using a plane fitting technique and based on the target three-dimensional model, and the vertical deviation between the quantified data and the bridge design data is determined. This application fully utilizes the drone for bridge observation and image acquisition, without the need for manual participation or traditional bridge alignment measurement equipment, reducing the measurement risk and difficulty; in addition, two drone image acquisitions are performed, the first for path planning and the second for bridge measurement, and the two acquisitions improve the image acquisition accuracy and further improve the bridge measurement accuracy. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0037] Figure 1 Flowchart of a bridge alignment measurement method based on virtual simulation and autonomous drone flight disclosed in this application;

[0038] Figure 2 Schematic plan view of a rough three-dimensional model of a bridge disclosed in this application;

[0039] Figure 3 Schematic diagram showing the measurement data display at the clicked position of a bridge disclosed in this application;

[0040] Figure 4 Bridge deck coverage path in a virtual environment disclosed in this application;

[0041] Figure 5 Schematic structural diagram of a bridge alignment measurement device based on virtual simulation and autonomous drone flight disclosed in this application;

[0042] Figure 6 Structural diagram of an electronic device disclosed in this application. Detailed Embodiments

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0044] Currently, traditional bridge alignment measurement devices, including total stations and levels, although can complete the measurement of bridge alignment, the operation is relatively cumbersome, requiring operations such as moving stations and setting up stations. The measurement process is troublesome and the measurement time is long; in addition, the purchase and maintenance costs of levels and total stations are relatively high, requiring expensive instrument equipment and professional maintenance personnel; moreover, in complex construction sites, operators may need to carry out measurement work in dangerous environments such as high altitudes and cliffs, increasing the safety risks of the operation.

[0045] Therefore, the embodiments of this application propose a bridge alignment measurement solution, which can reduce the risks and difficulties of bridge alignment measurement.

[0046] The embodiments of this application disclose a bridge alignment measurement method based on virtual simulation and UAV autonomous flight. As shown in Figure 1 the following, this method includes:

[0047] Step S11: Obtain a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image taken by a UAV based on an initial flight path autonomously planned by the UAV.

[0048] In this embodiment, the obtaining of the bridge simulation environment constructed based on the initial bridge image includes: obtaining a bridge simulation environment corresponding to the initial bridge image constructed after simulating a reference three-dimensional model of the bridge based on a virtual game engine; the reference three-dimensional model is a model constructed by a three-dimensional reconstruction software based on the initial bridge image.

[0049] It should be noted that through the route planning and image acquisition of consumer drones, first of all, through the route planning of the consumer drones themselves, a flight path covering all aspects of the bridge can be independently designed. During the route planning process, the key is to consider the overall structure of the bridge, the flight environment, and the requirements of the shooting angle to ensure that clear images of all parts of the bridge can be collected from different angles. The drones used in this part can be consumer-grade drones on the market. These drones usually have high cost performance and are equipped with functions such as high-resolution cameras and GPS positioning systems (Global Positioning System). Through autonomous flight, the drone can take pictures according to the predetermined path, avoiding the complexity and errors of manual intervention. After that, during image acquisition, the drone will automatically take multiple images of the bridge according to the set flight altitude, shooting angle, and frequency. These images will cover different aspects and details of the bridge to ensure that no important structural information is missed. For example, for the suspension part, piers, and bridge deck of the bridge, the accuracy and comprehensiveness of image acquisition will directly affect the accuracy of subsequent reconstruction and analysis.

[0050] It should be noted that the commercial 3D reconstruction software generates a rough 3D model. For details, please refer to Figure 2 As shown, it is a schematic plan view of a rough 3D model of a bridge. Clicking on any position of the bridge model can obtain the 3D coordinates of that position, as well as the distance, area, and volume. When clicking on Figure 2 the click position in, the measurement data shown in Figure 3 can be obtained. Figure 3 As shown, it is a schematic diagram showing the measurement data of the click position of a bridge. In the figure, the measurement box includes the content of coordinates, distance, area, and volume. Among them, the coordinate position is also the 3D coordinate. The 3D coordinates of the click position shown in the figure are 28.1371988N, 112.9459181E, and 36.616M (the three numbers specifically represent the latitude (unit: degree), longitude (unit: degree), and altitude (unit: meter) of this point in the WGS84 (World Geodetic System 1984) coordinate system). It should be noted that after the image acquisition is completed, the system will use commercial 3D reconstruction software to process the collected images to generate a rough 3D model. Since these images contain GPS information, the reconstructed 3D model not only has a geometric structure but can also be associated with the actual geographical coordinates. This rough 3D model can help initially identify the appearance and general shape of the bridge, but its accuracy and details have not yet reached the standard for precise analysis, so subsequent optimization is required.

[0051] It should be noted that in the virtual game engine, a bridge simulation environment is created: a rough 3D model is imported into the virtual game engine to generate an interactive bridge simulation environment. In this virtual environment, users can observe the bridge from the first-person perspective or the third-person perspective. The core purpose of this stage is to utilize the efficient graphics processing ability and real-time computing ability of the game engine to provide a visual operation platform for subsequent path planning and refined modeling.

[0052] It should be noted that virtual simulation: uses computer technology to create a virtual environment and simulate the physical behavior of the real world. In bridge monitoring, virtual simulation can be used to create a realistic bridge model so that the flight data of the simulated drone in this model can be directly imported into the real drone.

[0053] Step S12: Generate an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the latitude, longitude, and altitude information of each waypoint.

[0054] In this embodiment, generating an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file includes: constructing a spatial model based on the bridge simulation environment; determining the flight area in the spatial model based on a predetermined shooting area, and determining several waypoints in the flight area based on the drone parameters, and generating an initial aerial photography path according to the waypoints; completing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path; optimizing the obstacle avoidance path to generate an optimal aerial photography path to obtain an aerial photography path file; the path length of the optimal aerial photography path is less than or equal to the obstacle avoidance path.

[0055] It should be noted that through the precise analysis of the bridge structure in the virtual environment in this application, the system can use the bridge deck coverage path planning algorithm to automatically generate the optimal aerial photography path. The core goal of path planning is to ensure that the drone can cover each important part of the bridge as comprehensively as possible during the shooting process and minimize the redundancy or repetition on the flight path, thereby improving the efficiency and accuracy of data collection. See Figure 4 As shown, it is a schematic diagram of the bridge deck coverage path in a virtual environment. The black line is the path, and the four circular images in the upper right corner of the picture represent the drones. Other contents will not be elaborated here specifically.

[0056] In one embodiment, the data required for bridge deck coverage path planning mainly includes the three-dimensional model of the bridge structure, that is, the spatial model (including obstacle information), the performance parameters of the drone (flight speed, battery capacity, maximum range, etc.), shooting requirements (waypoint spacing, shooting angle, shooting resolution), and environmental parameters (such as wind speed, etc.); specifically, input: Bridge Model: includes the geometric model of the bridge, including the bridge deck, brackets, bridge piers, etc. Drone Model: includes the maximum flight height, maximum flight speed, flight time, battery consumption rate, etc. Flight Area: the monitoring area of the bridge, including the specific shooting area (such as the bridge deck, bridge piers). Obstacles: the positions of obstacles (bridge piers, brackets, steel cables, etc.) and their sizes. EnergyModel: the energy consumption of the drone at different speeds. KML File: a standard format file for outputting the path.

[0057] In this embodiment, constructing the spatial model based on the bridge simulation environment includes: constructing a geometric model based on the bridge simulation environment; the geometric model includes obstacles represented by geometric shapes.

[0058] It should be noted that the three-dimensional model here is different from the three-dimensional model in step 1. It is to construct a spatial obstacle model based on the given bridge structure and obstacle data. Each obstacle can be represented by a rectangle, a circle or a polygon. Specifically, its boundary should include brackets, bridge piers, steel cables, etc. It should be noted that the geometric model does not directly affect the subsequent bridge deck recognition, but instead plays a supporting role. For example, the bridge deck is a simple rectangle, and the street lamp is simplified into a thin cylinder. Subsequently, the bridge deck is identified from the geometric shapes through object segmentation, the waypoints and each flight area in the bridge deck are determined, and it is checked whether the flight area is valid. If it is invalid, it means that it exceeds the allowed flight area and reaches outside the bridge deck, then the flight area is adjusted on the bridge deck. If all are valid, a preliminary path is generated. Specifically, by scanning the bridge deck and taking each shooting point as a waypoint, a preliminary path is generated. The goal of the preliminary path planning is to cover the entire bridge area and ensure that each important area is covered by shooting. When generating the scanning path, the "zigzag" scanning path strategy is adopted to generate paths on both sides of the bridge to ensure that the images can cover the entire bridge deck from different angles. It should be noted that when setting the waypoint spacing, based on the shooting resolution of the camera and the geometric complexity of the bridge, the interval between waypoints is determined. In the straight part of the bridge, the waypoint spacing can be set larger; while in the arched or complex part, the waypoint spacing needs to be reduced.

[0059] In this embodiment, after the preliminary path planning, obstacle avoidance processing is added to ensure that the drone does not collide with obstacles. The obstacle avoidance path obtained by performing obstacle avoidance processing based on the flight area and the initial aerial photography path includes: using the A* algorithm and performing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain the obstacle avoidance path. In specific applications, at each step of path planning, it is necessary to calculate the distance between the current waypoint and the target waypoint to obstacles, and adjust the flight route according to the size and shape of the obstacles. During local obstacle avoidance, if the drone approaches an obstacle (such as a suspension cable) during flight, a local obstacle avoidance strategy based on inverse kinematics can be used to adjust the flight path to avoid collisions.

[0060] Specifically, a new algorithm can also be set based on the A* algorithm, which can be called the SOA algorithm. Specifically, the improvement advantages of the SOA algorithm compared to the A* algorithm are as follows: (1) Static obstacle optimization: The positions and shapes of all obstacles are known before the start of the planning, and the path planning process directly calculates based on this static information. Characteristics: There is no need to dynamically update the obstacle avoidance area, and the computational complexity is lower; (2) Focus on a single goal (obstacle avoidance): It does not involve complex multi-goal optimization, and only focuses on generating an effective and legal obstacle avoidance path. Characteristics: Simple and efficient, suitable for scenarios with clear constraints (such as drone bridge inspection).

[0061] The specific pseudocode of the SOA algorithm is as follows:

[0062] SOA_algorithm(initial_path,obstacles,flight_area):

[0063] Initialize open_list and cost_map # Store points to be processed and cost values;

[0064] Add the starting point of initial_path to open_list;

[0065] while open_list is not empty:

[0066] current = Take out the point with the lowest cost in open_list;

[0067] If current is the end point of the path:

[0068] Return the reconstructed path;

[0069] for neighbor in neighbors of current:

[0070] If the neighbor is outside the flight area or conflicts with an obstacle:

[0071] continue # Skip invalid points;

[0072] Calculate the new cost to the neighbor;

[0073] If the new cost is better or the neighbor has not been visited:

[0074] Update the cost_map, record the path, and add it to the open_list;

[0075] Return "no valid path" # when no path can be found.

[0076] In this embodiment, optimizing the obstacle avoidance path to generate an optimal aerial path to obtain an aerial path file includes: using an energy consumption model and a shortest path calculation model to optimize the obstacle avoidance path to generate an optimal aerial path with energy consumption and path meeting preset requirements to obtain an aerial path file; correspondingly, the shortest path calculation model is the Dijkstra algorithm; the energy consumption model is: ; where represents the energy consumption, represents the flight distance, represents the flight speed, represents the flight time, represents a constant.

[0077] It should be noted that unnecessary flights are reduced by calculating the shortest distance of the flight path. The Dijkstra algorithm is used to calculate the shortest path. When calculating the path, the influence of flight speed on energy consumption is considered, and the flight speed is reasonably set to avoid too high or too low flight speed. According to the battery capacity of the UAV, the maximum flight time or distance is limited. When the flight distance exceeds the maximum range that the battery can bear, the system will suggest replacing the battery or refueling midway. In addition, on the basis of obstacle avoidance and shortest path planning, the path is further streamlined, and the redundancy between waypoints is reduced by path merging (ensuring there are no obstacles). For example, if there are no obstacles between two adjacent waypoints and they can fly directly, these two waypoints can be merged into a new waypoint.

[0078] Specifically, a new algorithm can also be set based on the Dijkstra algorithm, which can be called the OD algorithm. The improvement advantages of the specific OD algorithm compared with the traditional Dijkstra algorithm are as follows: (1) Support key point compression to reduce redundant storage; Improvement point: Only record the key nodes in the path (such as the starting point, turning points, and ending point), and ignore the redundant intermediate nodes on the straight line. Advantage: Reduces the space overhead of storing the path; Improves the readability of the path representation, which is suitable for path display and subsequent optimization. (2) Batch process neighbor nodes to improve efficiency; Improvement point: Adopt a batch calculation and filtering mechanism for processing neighbor nodes (such as checking legality first and then calculating the cost). Advantage: Reduces the calculation overhead of invalid nodes; Improves the running efficiency of the algorithm on large-scale graphs.

[0079] The pseudocode of the OD algorithm is as follows:

[0080] OD_algorithm(graph, start, goal, light_area):

[0081] Initialize open_list = PriorityQueue() # Priority queue for storing nodes to be processed;

[0082] Initialize cost_map = empty dictionary # Record the minimum cost from the start point to each node;

[0083] Initialize came_from = empty dictionary # Record the predecessor node of each node;

[0084] Add (0, start) to open_list;

[0085] cost_map[start] = 0;

[0086] while open_list is not empty:

[0087] current = Remove the node with the lowest cost from open_list;

[0088] if current == goal:

[0089] Return reconstruct_path(came_from, start, goal);

[0090] for neighbor in all neighbors of current:

[0091] if neighbor is not in flight_area:

[0092] continue # Skip illegal nodes;

[0093] new_cost = cost_map[current] + graph[current][neighbor];

[0094] if neighbor has not been visited or the new cost is smaller:

[0095] cost_map[neighbor] = new_cost;

[0096] Add (new_cost, neighbor) to open_list;

[0097] came_from[neighbor]=current;

[0098] Return "Path not found".

[0099] It should be noted that the path planning algorithm not only needs to consider the shortest or most economical flight path, but also makes dynamic adjustments based on factors such as the complexity of the bridge structure and the requirements of the shooting angle. For example, for the arched or suspended parts of the bridge, the algorithm may plan special flight paths to ensure that these parts are photographed from multiple angles and avoid blind spots; once the path planning is completed, the system will automatically export the GPS information of all waypoints as a.kml file, which is a standard geographic information file format and can be compatible with most drone navigation systems. This file contains the exact positions (latitude, longitude, and altitude information) of each waypoint and guides the drone to fly precisely along the predetermined path.

[0100] In a specific embodiment, the pseudocode for path planning using the A* algorithm and the algorithm is as follows: def generate_path(bridge_model, drone_model, obstacles, energy_model, flight_area):

[0101] # Step 1: Modeling:

[0102] bridge_points = extract_bridge_points(bridge_model);

[0103] obstacles = extract_obstacles(bridge_model);

[0104] # Step 2: Check if the flight area is valid:

[0105] if not is_valid_flight_area(flight_area, bridge_points):

[0106] raise ValueError("The bridge model exceeds the allowed flight area");

[0107] # Step 3: Initial path generation:

[0108] initial_path = scan_bridge(bridge_points, drone_model, flight_area);

[0109] # Step 4: Obstacle avoidance path generation:

[0110] obstacle_free_path = SOA_algorithm(initial_path, obstacles, flight_area);

[0111] # Step 5: Energy optimization:

[0112] optimized_path = optimize_energy(obstacle_free_path, drone_model, energy_model, flight_area);

[0113] # Step 6: Output path:

[0114] kml_file = generate_kml(optimized_path);

[0115] return kml_file;

[0116] def is_valid_flight_area(flight_area, bridge_points):

[0117] # Determine whether the monitoring area of the bridge is within the flight area;

[0118] for point in bridge_points:

[0119] if not is_within_area(flight_area, point):

[0120] return False;

[0121] return True;

[0122] def is_within_area(flight_area, point):

[0123] # Check whether a point is within the flight area;

[0124] # Flight Area is a polygon or rectangle, and here a simple method of judging whether a point is within a polygon is demonstrated;

[0125] return is_point_in_polygon(flight_area, point);

[0126] def a_star_algorithm(path, obstacles, flight_area):

[0127] # Use the A* algorithm to generate an obstacle - avoidance path and ensure the path is within the flight area;

[0128] # The A* algorithm here will consider the boundaries of the flight area;

[0129] Pass;

[0130] def optimize_energy(path, drone_model, energy_model, flight_area):

[0131] # Optimize the path based on the energy model and ensure the path is completely within the flight area;

[0132] total_energy = 0;

[0133] optimized_path = [];

[0134] for i in range(1, len(path)):

[0135] if not is_within_area(flight_area, path[i]):

[0136] continue # If the waypoint is outside the flight area, skip this waypoint;

[0137] segment_distance = calculate_distance(path[i - 1], path[i]);

[0138] energy_consumed = energy_model(segment_distance, drone_model);

[0139] total_energy += energy_consumed;

[0140] optimized_path.append(path[i]);

[0141] if total_energy > drone_model.battery_capacity:

[0142] return optimized_path#Add recharge points or suggest energy-saving routes.

[0143] return optimized_path。

[0144] Step S13: Obtain the target bridge image captured by the drone based on the aerial photography path file, and generate a target three-dimensional model of the bridge based on the target bridge image.

[0145] In this embodiment, the drone captures the bridge deck image along the optimal path: the user imports the.kml file into the drone control system, and the robot automatically navigates through GPS and autonomously flies according to the planned path. The drone will capture pictures of the bridge deck according to the designed route to ensure that every key part of the bridge is covered; then, refined three-dimensional modeling and vertical undulation analysis: through the high-precision images collected by the drone, combined with image reconstruction technology and three-dimensional point cloud data, a refined three-dimensional model of the bridge can be generated. Compared with the preliminary rough three-dimensional model, the refined model has higher resolution and more detailed bridge structure details.

[0146] Step S14: Quantify the vertical undulation of the bridge using plane fitting technology and according to the target three-dimensional model, and determine the vertical deviation between the quantified data and the bridge design data.

[0147] In this embodiment, plane fitting technology can be used to quantitatively analyze the vertical undulation of the bridge deck. Through the fitting algorithm, the point cloud data of the bridge deck is compared with the ideal plane on the design drawing to obtain the vertical deviation (i.e., the undulation of the bridge deck). When these deviations exceed the design standard range, the system will issue a warning to indicate possible structural problems and remind the engineer to conduct inspections, repairs or adjustments in a timely manner.

[0148] In this embodiment, after determining the vertical deviation between the quantified data and the bridge design data, it further includes: if the vertical deviation exceeds the preset deviation value, a target alarm is issued according to the preset alarm method; the target alarm includes the vertical deviation exceeding the preset deviation value and the position information corresponding to the vertical deviation.

[0149] It should be noted that if there is a large deviation between the alignment of the bridge and the designed alignment, the system can automatically identify and display the specific deviation position and value. This is crucial for the maintenance and safety monitoring of the bridge. Through real-time monitoring and analysis, the bridge management party can timely discover potential safety hazards such as bridge deck settlement, deformation, cracks and other problems, and thus take necessary repair or reinforcement measures to avoid structural failures.

[0150] It should be noted that the UAV bridge alignment measurement technology based on virtual simulation and intelligent path planning can significantly improve the measurement accuracy and efficiency, reduce the errors and redundancies of traditional manual measurements, and optimize the data acquisition process through precise modeling and path planning in the virtual environment. The UAV automatically plans the optimal flight path, avoids obstacles and maximizes the coverage of the bridge structure, thus enhancing the comprehensiveness and accuracy of the measurement. Compared with traditional manual measurements, the measurement time can usually be reduced by about 50%-70%, and the cost can be saved by about 60%-80%. This technology not only reduces the labor cost and equipment investment, but also improves the flight safety and avoids manual contact with high-risk areas. At the same time, through 3D modeling and real-time monitoring, structural deviations of the bridge can be detected in a timely manner, supporting intelligent bridge maintenance and repair decisions, and enhancing the sustainability and long-term management ability of the data. In addition, the automation and adaptability of the system ensure its wide application in the measurement tasks of various bridges, with strong adaptability and intelligence levels, promoting the modernization development of the bridge inspection field.

[0151] It should be noted that it is also easy to complete bridge measurements through other technologies. Specifically: Terrestrial laser scanning technology: Laser scanners can be installed on the ground or on the bridge, and data can be obtained from multiple perspectives for 3D modeling. Although this technology can provide high-precision data, there are some disadvantages. First, although the laser scanning technology can obtain high-precision data, its coverage is relatively limited, and it usually needs to be scanned repeatedly at different positions to ensure the complete data acquisition of the bridge, which makes the scanning process time-consuming and requires a large amount of manual intervention. Second, the effectiveness of the terrestrial laser scanner depends on the limitations of the scanning angle and field of view. In the high-altitude part or complex structure area of the bridge, the perspective of the scanner may be limited, resulting in incomplete data acquisition of some parts, thus affecting the accuracy of the final model. Third, laser scanners usually need to be transported to the bridge site and operated by staff, which may involve safety risks, especially in viaducts or complex environments.

[0152] It can be seen that the present application obtains a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a drone based on the initial flight path; the initial flight path is an initial flight path constructed by a drone route planning system based on drone performance parameters and a three-dimensional model of the original bridge structure; an optimal aerial photography path is generated based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the latitude, longitude, and altitude information of each waypoint; a target bridge image captured by the drone based on the aerial photography path file is obtained, and a target three-dimensional model of the bridge is generated based on the target bridge image; the vertical undulation of the bridge is quantified using a plane fitting technique and based on the target three-dimensional model, and the vertical deviation between the quantified data and the bridge design data is determined. The present application fully utilizes the drone for bridge observation and image acquisition, without the need for manual participation or traditional bridge alignment measurement equipment, reducing the measurement risk and difficulty; in addition, two drone image acquisitions are performed, the first for path planning and the second for bridge measurement, and the two acquisitions improve the image acquisition accuracy and further improve the bridge measurement accuracy.

[0153] Correspondingly, an embodiment of the present application also discloses a bridge alignment measurement device based on virtual simulation and autonomous drone flight, as shown in Figure 5 The device includes:

[0154] A first acquisition module 11, configured to obtain a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a drone based on an initial flight path autonomously planned by the drone;

[0155] A file generation module 12, configured to generate an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the latitude, longitude, and altitude information of each waypoint;

[0156] A second acquisition module 13, configured to obtain a target bridge image captured by the drone based on the aerial photography path file, and generate a target three-dimensional model of the bridge based on the target bridge image;

[0157] A measurement module 14, configured to quantify the vertical undulation of the bridge using a plane fitting technique and based on the target three-dimensional model, and determine the vertical deviation between the quantified data and the bridge design data.

[0158] Among them, for the more specific working processes of the above-mentioned various modules, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated herein.

[0159] It can be seen that this application obtains a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a drone based on the initial flight path; the initial flight path is an initial flight path constructed by a drone route planning system based on the performance parameters of the drone and the three-dimensional model of the original bridge structure; an optimal aerial photography path is generated based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the longitude, latitude, and altitude information of each waypoint; a target bridge image captured by the drone based on the aerial photography path file is obtained, and a target three-dimensional model of the bridge is generated based on the target bridge image; the vertical undulation of the bridge is quantified using a plane fitting technique and according to the target three-dimensional model, and the vertical deviation between the quantified data and the bridge design data is determined. This application fully utilizes drones for bridge observation and image acquisition, without the need for manual participation or traditional bridge alignment measurement equipment, reducing the measurement risk and difficulty; in addition, two drone image acquisitions are performed, the first for path planning and the second for bridge measurement, and the two acquisitions improve the image acquisition accuracy and further improve the bridge measurement accuracy.

[0160] Furthermore, an embodiment of this application also provides an electronic device. Figure 6 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be considered as any limitation on the scope of use of this application.

[0161] Figure 6 It is a structural schematic diagram of an electronic device 20 provided by an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the bridge alignment measurement method based on virtual simulation and autonomous drone flight disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0162] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of this application, and no specific limitation is imposed on it here; the input / output interface 24 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0163] In addition, as a carrier for storing resources, the memory 22 can be a read-only memory, a random access memory, a magnetic disk, an optical disk, etc. The resources stored thereon can include a computer program 221, and the storage method can be temporary storage or permanent storage. Among them, in addition to the computer program that can be used to complete the bridge alignment measurement method based on virtual simulation and UAV autonomous flight executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 221 can further include computer programs that can be used to complete other specific tasks.

[0164] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the bridge alignment measurement method based on virtual simulation and UAV autonomous flight disclosed above is implemented.

[0165] For the specific steps of this method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0166] The various embodiments in this application are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and reference can be made to the description in the method part for related parts.

[0167] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of the examples have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0168] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0169] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0170] The above has introduced in detail a bridge alignment measurement method, device, equipment, and storage medium based on virtual simulation and UAV autonomous flight provided by the present application. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for measuring the bridge alignment based on virtual simulation and autonomous flight of unmanned aerial vehicles, characterized in that, Applied to a bridge alignment measurement system, the method includes: Obtaining a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a drone based on an initial flight path autonomously planned by the drone; Generating an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file contains the longitude, latitude, and altitude information of each waypoint; Obtaining a target bridge image captured by the drone based on the aerial photography path file, and generating a target three-dimensional model of the bridge based on the target bridge image; Quantifying the vertical undulation of the bridge using plane fitting technology and based on the target three-dimensional model, and determining the vertical deviation between the quantified data and the bridge design data.

2. The method for measuring the bridge alignment based on virtual simulation and autonomous flight of unmanned aerial vehicle according to claim 1, wherein The generating an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file includes: Constructing a spatial model based on the bridge simulation environment; Determining a flight area in the spatial model based on a predetermined photographing area, and determining a number of waypoints in the flight area based on drone parameters, and generating an initial aerial photography path according to the waypoints; Completing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path; Optimizing the obstacle avoidance path to generate an optimal aerial photography path to obtain an aerial photography path file; the path length of the optimal aerial photography path is less than or equal to the obstacle avoidance path.

3. The method for measuring the bridge alignment based on virtual simulation and autonomous flight of an unmanned aerial vehicle according to claim 2, wherein The completing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path includes: Using the A* algorithm, and completing obstacle avoidance processing based on the flight area and the initial aerial photography path to obtain an obstacle avoidance path.

4. The method for measuring the bridge alignment based on virtual simulation and UAV autonomous flight according to claim 2, wherein The optimizing the obstacle avoidance path to generate an optimal aerial photography path to obtain an aerial photography path file includes: Using an energy consumption model and a shortest path calculation model to optimize the obstacle avoidance path to generate an optimal aerial photography path with energy consumption and path meeting preset requirements to obtain an aerial photography path file; Correspondingly, the shortest path calculation model is the Dijkstra algorithm.

5. The method for measuring the bridge alignment based on virtual simulation and autonomous flight of an unmanned aerial vehicle according to claim 2, wherein The constructing a spatial model based on the bridge simulation environment includes: Constructing a geometric model based on the bridge simulation environment; the geometric model includes obstacles represented by geometric shapes.

6. The method for measuring the bridge alignment based on virtual simulation and autonomous flight of an unmanned aerial vehicle according to claim 1, wherein The obtaining a bridge simulation environment constructed based on an initial bridge image includes: Obtaining a bridge simulation environment corresponding to the initial bridge image constructed after simulating a reference three-dimensional model of the bridge using a virtual game engine; the reference three-dimensional model is a model constructed by three-dimensional reconstruction software based on the initial bridge image.

7. The bridge alignment measurement method based on virtual simulation and UAV autonomous flight according to any one of claims 1 to 6, characterized in that, After determining the vertical deviation between the quantified data and the bridge design data, it further includes: If the vertical deviation exceeds a preset deviation value, a target alarm is issued according to a preset alarm method; the target alarm includes the vertical deviation exceeding the preset deviation value and the position information corresponding to the vertical deviation.

8. A bridge alignment measuring device based on virtual simulation and autonomous flight of unmanned aerial vehicles, characterized in that, Applied to a bridge alignment measurement system, the device includes: A first acquisition module, configured to acquire a bridge simulation environment constructed based on an initial bridge image; the initial bridge image is a bridge image captured by a drone based on an initial flight path autonomously planned by the drone; A file generation module, configured to generate an optimal aerial photography path based on the bridge simulation environment to obtain an aerial photography path file; the aerial photography path file includes the latitude, longitude, and altitude information of each waypoint; A second acquisition module, configured to acquire a target bridge image captured by the drone based on the aerial photography path file, and generate a target three-dimensional model of the bridge based on the target bridge image; A measurement module, configured to utilize the plane fitting technique and quantify the vertical undulation of the bridge according to the target three-dimensional model, and determine the vertical deviation between the quantified data and the bridge design data.

9. An electronic device, characterized in that, Comprising: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the bridge alignment measurement method based on virtual simulation and drone autonomous flight according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by the processor, it implements the bridge alignment measurement method based on virtual simulation and drone autonomous flight according to any one of claims 1 to 7.

Images