Bridge crack automatic detection system based on unmanned aerial vehicle

Abstract

The invention relates to the technical field of crack measurement, and discloses an unmanned aerial vehicle-based bridge crack automatic detection system, which comprises an unmanned aerial vehicle and a collector arranged at the unmanned aerial vehicle, and further comprises a trajectory planning module for planning a surrounding flight trajectory of the unmanned aerial vehicle around a bridge ground pile, the track planning module sets tracks including spiral tracks and extension tracks, a starting target platform is arranged at the starting point of the bottom end of each spiral track, and the unmanned aerial vehicle is enabled to complement each other along the collection track surfaces formed by the spiral tracks to form a complete crack collection area or a crack collection area with an overlapping area; in order to reduce the safety risk, improve the detection frequency, utilize the extension characteristic of the crack, improve the detection frequency and reduce the time length of a single detection process by adopting the form of coarse pitch, multi-track route and single-track detection, the high-frequency detection has the advantages that the detection blank period can be shortened, the safety risk can be reduced, and the high-frequency detection can be easily extended to a single spiral track; therefore, the gap problem can be found timely.

Description

Technical Field

[0001] The invention relates to the technical field of crack measurement, in particular to an automatic bridge crack detection system based on an unmanned aerial vehicle. Background Art

[0002] Drone wall detection is the main means of bridge crack detection. After attaching to the wall, the camera is at a short distance from the target object, so the collection area is small but the image clarity is high. At this time, the number and size of cracks can be obtained through image processing calculations, thereby improving the safety of the bridge.

[0003] The more times a bridge is inspected and the shorter the frequency, the easier it is to find safety hazards. However, due to the small collection area of ​​wall-climbing flight, if a drone conducts a complete and comprehensive collection, the flight distance is too long and high-frequency inspection is not possible.

[0004] Because the detection track of the bridge deck is fixed and single, the road surface can be collected by a collection vehicle and multiple lenses can be collected at a time. Because the detection track under the bridge is fixed and single, a track can be set on the side of the bridge or under the bridge to control the movement of the linear collector for collection. However, it is difficult to collect cylindrical bridge piles using linear collectors. When linear collection is used, a closed loop is formed, which makes it difficult to separate from the bridge piles. There are many bridge piles, so the linear collection method is not suitable for bridge piles. As a result, bridge piles still choose single-image track collection for crack detection, so that during comprehensive detection, the flight distance is still very long and high-frequency detection is not possible. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic bridge crack detection system based on a drone to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: An automatic bridge crack detection system based on a drone includes a drone and a collector arranged at the drone, and also includes a trajectory planning module for planning a flight trajectory of the drone around a bridge pile; The trajectory planning module sets the trajectory including a spiral track and an extended track, wherein the spiral track has at least two trajectories, a starting target platform is set at the bottom starting point of each spiral track, and a plurality of the starting target platforms are distributed in a circular manner at equal angles on the bottom surface of the bridge pile, and a plurality of the spiral tracks are staggered with each other, so that the collection trajectory surfaces formed by the UAV along the spiral tracks complement each other to form a complete or overlapping crack collection area; After the data collected by the collector is processed by the target orientation processing module, when a single endpoint appears in any crack in the image, the orientation of the crack in the image is obtained, and the trajectory planning module is used to plan the UAV to move along the crack orientation using the extended track until a complete crack image is obtained and the crack length is measured.

[0007] As a further solution of the present invention: the flight coordinates of the UAV are recorded by a coordinate positioning module, and the coordinate positioning module divides the horizontal ring of the bridge piles into multiple horizontal positioning points through a circular coordinate calculation unit. A fixed-altitude ranging unit is installed at the bottom of the UAV to monitor the real-time height of the UAV from the horizontal plane of the starting target platform. The coordinate positioning module can obtain the current position of the UAV based on the position of the starting target platform where the UAV takes off, combined with the actual height of the UAV monitored by the fixed-altitude ranging unit.

[0008] As a further solution of the present invention: under normal conditions, each time the UAV flies, each pile body selects the starting target platform as the take-off point in sequence. Under abnormal conditions, the initial take-off point of the abnormal pile body selects the starting target platform corresponding to the abnormal spiral crack collection area as the starting take-off point.

[0009] As a further solution of the present invention: the collection marks of the starting target platform of the same pile are different from each other, the marking points of the starting target platform are recorded by the trajectory planning module, and the flight trajectory to the starting target platform is planned.

[0010] As a further solution of the present invention: the flight track of the extended track includes a circular flight track around the pile and a flight track along the axial direction of the pile body.

[0011] As a further solution of the present invention: the target orientation processing module divides the image into four identification areas, and obtains the single-ended gap position and the gap extension azimuth in the four identification areas; the timing inspection unit changes the take-off order of the target platform according to the image recognition information of the coordinate positioning module; the trajectory planning module controls the selection of the spiral orbit or the extended orbit as the flight orbit of the UAV according to the image recognition information of the coordinate positioning module.

[0012] As a further solution of the present invention: the bottom surface of the pile body is fixedly connected to a horizontal plane, the starting target platform is embedded in the horizontal plane, and the top surface of the starting target platform is flush with the horizontal plane.

[0013] Compared with the prior art, the present invention has the following beneficial effects: In order to reduce safety risks, increase the frequency of detection, and utilize the extension characteristics of cracks, large pitch, multi-track routes, and single-track detection are used to increase the detection frequency and reduce the duration of a single detection process. The advantage of high-frequency detection is that it can shorten the detection blank period and reduce safety risks. At the same time, the spiral rising method has bidirectional movement in the horizontal and vertical directions, and the gaps are actually irregular. Most gaps will have horizontal or vertical extensions, so it is easy to extend to a single spiral track, thereby discovering the gap problem in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1 Schematic diagram of the sweep trajectory of the UAV-based bridge crack automatic detection system; Figure 2 The schematic diagram of the three-track extension of the UAV-based bridge crack automatic detection system; Figure 3 Schematic diagram of the double-track extension of the UAV-based bridge crack automatic detection system; Figure 4 This is a diagram of the automatic bridge crack detection system based on drones; Figure 5 It is a graphic partition diagram of the automatic bridge crack detection system based on drone; In the figure: 1. Start the target platform; 100. UAV; 101. Collector; 2. Trajectory planning module; 21. Spiral track; 22. Extended track; 23. Timed inspection unit; 3. Target orientation processing module; 4. Coordinate positioning module; 41. Altitude and distance measurement unit; 42. Circular coordinate calculation unit. DETAILED DESCRIPTION

[0016] See also Figure 1-Figure 5 In this embodiment, it includes a drone 100 and a collector 101 arranged at the drone 100, and also includes a trajectory planning module 2 for planning the flight trajectory of the drone 100 around the bridge piles.

[0017] In this embodiment, the drone currently has a spiral ascending flight function. During the process of the drone spiral ascending and flying close to the bridge pile, the collected image band is a spiral band. Please refer to Figure 1-3 , the image acquisition width is obtained according to the wall spacing, thereby obtaining the width of the spiral band. Figure 1It can be seen that if the UAV conducts a comprehensive collection of the pile body, when the pitch is large, more than two spiral belts are required. If the pitch is reduced, one spiral belt can complete the comprehensive collection, but the flight speed is too slow and the detection cycle is long. In order to reduce safety risks and increase the detection frequency, the extension characteristics of the cracks are used to increase the detection frequency and reduce the duration of a single detection process by using large pitch, multi-track routes, and single-track detection. The advantage of high-frequency detection is that it can shorten the detection blank period and reduce safety risks. At the same time, the spiral rise method has two-way movement in the horizontal and vertical directions, and the gaps are actually irregular. Most of the gaps will have horizontal extensions or vertical extensions, so it is easy to extend to a single spiral track, thereby discovering gap problems in time.

[0018] In this embodiment, the trajectory planning module 2 sets the trajectory including a spiral track 21 and an extended track 22, wherein the spiral track 21 has at least two tracks, and a starting target platform 1 is provided at the bottom starting point of each spiral track 21, and several starting target platforms 1 are distributed in a circular manner at equal angles on the bottom surface of the bridge piles. Several spiral tracks 21 are staggered with each other, so that the collection trajectory surfaces formed by the drone 100 along the spiral track 21 complement each other to form a complete or overlapping crack collection area.

[0019] In this embodiment, in order to accurately distinguish and plan the track of a single detection, a starting target platform 1 is set at the bottom of the bridge pile. The number of starting target platforms 1 is consistent with the number of spiral tracks 21. The existing drone has a target fixed-point hovering function. At present, it is hovering by comprehensively identifying the target object through image recognition combined with image recognition algorithm and flight control algorithm. The hovering also includes fixed-point hovering and fixed-height hovering. The purpose of setting the starting target platform 1 is to facilitate the trajectory planning module 2 to sort the trajectories of multiple pile bodies. The starting target platform 1 is used as the starting point in multiple pile bodies to make the trajectory more accurate, and the trajectory planning module 2 only needs to set the trajectory of the starting target platform 1 from one pile body to another pile body. The trajectory of the flight through the starting target platform 1 is a fixed spiral trajectory.

[0020] In this embodiment, in addition to the spiral track 21, an extension track 22 is also provided. Since it is easy to find the complete gap and the single-ended gap in the image acquisition interface during the flight, please refer to Figure 5 , the complete track has two endpoints, while other cracks will appear as different single-ended cracks, and the fuzzy position of the crack from the drone can be judged by the extension direction of the single-ended crack. Therefore, it is necessary to use the extended track 22 to fully display the crack.

[0021] In this embodiment, Figure 1-3The image drawn in the figure is a double-helix and triple-helix splicing covering the pile body. In order to further improve the comprehensiveness of a single acquisition and reduce the process time, a double-helix track is used to reduce the pitch of the single spiral and make the pitch width smaller than the width of the spiral acquisition surface, so that the width of the remaining blank area is smaller than the width of the subsequent double-helix track. The easiest way to adjust the width of the spiral track is to adjust the wall spacing and increase the size of the acquisition image to adjust the width of the spiral surface. At this time, in a single acquisition, the width of the blank spiral surface is narrow, making it easier to find the end point of the crack. When the end point of the crack is found and extended, the complete crack can be obtained, thereby achieving incomplete acquisition while improving the comprehensiveness of the acquisition. In actual operation, the pitch can be adjusted according to the maximum size of the crack allowed.

[0022] In this embodiment, after the data collected by the collector 101 is processed by the target orientation processing module 3, when a single end point appears in any crack in the image, the position of the crack in the image is obtained, and the trajectory planning module 2 is used to plan the drone 100 to move along the crack azimuth using the extended track 22 until a complete crack image is obtained and the crack length is measured. The target orientation processing module 3 divides the image into four identification areas, and obtains the single-end gap position and the gap extension azimuth in the four identification areas. The timing inspection unit 23 changes the take-off order of the start target platform 1 according to the image recognition information of the coordinate positioning module 4. The trajectory planning module 2 controls the selection of the spiral track 21 or the extended track 22 as the flight track of the drone 100 according to the image recognition information of the coordinate positioning module 4. Under normal conditions, each time the drone 100 flies, each pile body selects the start target platform 1 as the take-off point in sequence. Under abnormal conditions, the initial take-off point of the abnormal pile body selects the start target platform 1 corresponding to the abnormal spiral crack collection area as the starting take-off point.

[0023] In this embodiment, the track selection priorities for the double helix and triple helix are explained for ease of understanding: Double helix: Double helix is ​​more convenient when Figure 5 When the problem arises, suppose Figure 5 The direction moves to the upper right. The gap areas in the upper left of area A, the lower right of area C, and the lower left of area D cannot be collected. Therefore, it can be collected during the first inspection. Figure 5 The center crack information and the crack information in the upper right of area B. The priority of the secondary acquisition is to select the second spiral track to acquire the residual image information of A, C, and D.

[0024] Triple Helix: In triple helix, it is assumed Figure 5 If it is located on the b track, the image collected in area A is located on the a track, and the images collected in areas D and C are located on the c track. Therefore, when the number of c tracks is greater than that of a tracks, the priority of the next track collected is c track, and the complete crack image is quickly supplemented through c track.

[0025] In this embodiment, the image extension is explained: Still with the help of Figure 5 The flight track of the extended track 22 includes a circular flight track around the pile and a flight track along the axial direction of the pile body. When there is a problem with the image in area A, the extended track 22 can be used for extension and supplementation. The residual information of image A is collected by horizontal left spiral motion and then upward vertical motion. The gap located on the vertical midline can directly collect the complete crack image by vertical upward motion. This method mainly improves the comprehensiveness of crack detection during single spiral detection. When the extended track 22 flies, it is necessary to fully record the flight coordinates, or perform manual operation, or extend it by using the marker recognition flight method. After finding the other end point of the gap, it is reset. During the extended flight, the image can be measured to obtain the accurate gap length.

[0026] In this embodiment, the image extension is explained: the flight coordinates of the UAV 100 are recorded by the coordinate positioning module 4, the coordinate positioning module 4 divides the horizontal ring of the bridge piles into multiple horizontal positioning points through the circular coordinate calculation unit 42, and the height-fixing and ranging unit 41 is installed at the bottom of the UAV 100 to monitor the real-time height of the UAV 100 from the horizontal plane of the starting target platform 1. The coordinate positioning module 4 can obtain the current position of the UAV 100 based on the position of the starting target platform 1 where the UAV 100 takes off, combined with the actual height of the UAV 100 monitored by the height-fixing and ranging unit 41.

[0027] In this embodiment, after all tracks have been flown once, the area where cracks are collected during the flight can be marked, so the circumferential coordinate calculation unit 42 is used to divide the bridge pile into multiple positioning points, and according to the flight track, combined with the flight altitude position, under the condition of a fixed spiral line, the circular coordinate position of the current drone 100 can be obtained. The circumferential coordinate calculation unit 42 is a computer, which mainly obtains the current coordinates through the fixed height ranging unit 41 combined with the spiral track, and after integrating the coordinates, the coordinates of multiple problem points of the entire bridge body can be marked, so that the marked point inspection can be carried out.

[0028] In this embodiment, the collection marks of the starting target platform 1 of the same pile are different from each other. The marking points of the starting target platform 1 are recorded by the trajectory planning module 2, and the flight trajectory to the starting target platform 1 is planned; identification through different marking points is more convenient for control.

[0029] In this embodiment, the bottom surface of the pile is fixedly connected to a horizontal plane, the starting target platform 1 is embedded in the horizontal plane, and the top surface of the starting target platform 1 is flush with the horizontal plane. In order to avoid errors in the acquisition of the height-fixing and ranging unit 41 when the starting target platform 1 is lower than or higher than the horizontal plane.

[0030] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An automatic bridge crack detection system based on an unmanned aerial vehicle, comprising an unmanned aerial vehicle (100) and a collector (101) arranged at the unmanned aerial vehicle (100), characterized in that: It also includes a trajectory planning module (2) for planning a flight trajectory of the drone (100) around a bridge pile; The trajectory planning module (2) sets a trajectory including a spiral track (21) and an extended track (22), wherein the spiral track (21) has at least two trajectories, a starting target platform (1) is provided at the bottom starting point of each spiral track (21), a plurality of the starting target platforms (1) are distributed in a circular manner at equal angles on the bottom surface of the bridge pile, and a plurality of the spiral tracks (21) are mutually staggered, so that the collection trajectory surfaces formed by the drone (100) along the spiral tracks (21) complement each other to form a complete crack collection area or a crack collection area with overlapping areas; After the data collected by the collector (101) is processed by the target orientation processing module (3), when any crack in the image has a single endpoint, the orientation of the crack in the image is obtained, and the trajectory planning module (2) is used to plan the drone (100) to move along the crack orientation using the extended track (22) until a complete crack image is obtained and the crack length is measured.

2. The automatic bridge crack detection system based on drone according to claim 1 is characterized by: The flight coordinates of the unmanned aerial vehicle (100) are recorded by a coordinate positioning module (4), and the coordinate positioning module (4) comprises a height-fixing distance-measuring unit (41) and a circumferential coordinate calculation unit (42).

3. The automatic bridge crack detection system based on drone according to claim 2 is characterized by: The coordinate positioning module (4) divides the horizontal ring of the bridge pile into a plurality of horizontal positioning points through a circumferential coordinate calculation unit (42), and the height determination and ranging unit (41) is installed at the bottom of the drone (100) to monitor the real-time height of the drone (100) from the horizontal plane of the starting target platform (1).

4. The automatic bridge crack detection system based on drone according to claim 3 is characterized by: The coordinate positioning module (4) obtains the current position of the drone (100) based on the position of the starting target platform (1) from which the drone (100) takes off, combined with the actual height of the drone (100) monitored by the altitude-fixing and ranging unit (41).

5. The automatic bridge crack detection system based on drone according to claim 4 is characterized by: Under normal conditions, each time the drone (100) flies, each pile body sequentially selects the starting target platform (1) as a take-off point. Under abnormal conditions, the initial take-off point of an abnormal pile body selects the starting target platform (1) corresponding to the abnormal spiral crack collection area as the starting take-off point.

6. The automatic bridge crack detection system based on drone according to claim 5 is characterized by: The collection marks of the starting target platform (1) of the same pile body are different from each other, and the marking points of the starting target platform (1) are recorded by the trajectory planning module (2), and a flight trajectory to the starting target platform (1) is planned.

7. The automatic bridge crack detection system based on drone according to claim 1 is characterized by: The flight track of the extension track (22) comprises a circular flight track around the pile and a flight track along the axial direction of the pile body.

8. The automatic bridge crack detection system based on drone according to claim 2 is characterized by: The target orientation processing module (3) divides the image into four identification areas, and obtains the single-end gap position and the gap extension azimuth in the four identification areas. The timing inspection unit (23) changes the take-off order of the start target platform (1) according to the image recognition information of the coordinate positioning module (4). The trajectory planning module (2) controls the selection of the spiral track (21) or the extension track (22) as the flight track of the UAV (100) according to the image recognition information of the coordinate positioning module (4).

9. The automatic bridge crack detection system based on drone according to claim 1 is characterized by: The bottom surface of the pile body is fixedly connected to a horizontal plane, the starting target platform (1) is embedded in the horizontal plane, and the top surface of the starting target platform (1) is flush with the horizontal plane.

Images