Unmanned aerial vehicle autonomous inspection method and system for power transmission and distribution tower and inspection unmanned aerial vehicle

Abstract

The invention discloses an unmanned aerial vehicle autonomous inspection method and system for a power transmission and distribution tower and an inspection unmanned aerial vehicle, and relates to the technical field of power transmission line fault detection. The method provided by the invention comprises the following steps: shooting a first image around an inspection starting point through an airborne camera; identifying a first tower according to the first image, and determining the orientation and distance of the first tower relative to the unmanned aerial vehicle; controlling the unmanned aerial vehicle to fly to a first position away from the first tower along the azimuth, and shooting a second image of the first tower at the first position; identifying the tower type of the first tower according to the second image, and determining an inspection point according to the tower type; generating an inspection route according to the plurality of inspection points, controlling the unmanned aerial vehicle to inspect along the inspection route, after the inspection of the first tower is completed, controlling the unmanned aerial vehicle to rise to a first height as a next inspection starting point, and repeating the inspection steps to complete the inspection of the next tower. And multi-tower continuous autonomous inspection is realized, and route planning in advance is not needed.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line fault detection, and in particular to a method and system for autonomous inspection of power transmission and distribution towers by unmanned aerial vehicles (UAVs), and an inspection UAV. Background Art

[0002] The terrain of the power transmission channel is complex, involving altitude areas, densely populated urban areas, and mountainous areas. The single tower structure is complex, there are many inspection points, the workload of manual inspection is extremely large, and it is difficult to ensure the quality of inspection. Drone inspection has many advantages such as high efficiency and safety. However, drone inspection requires manual flight control or advance route planning, but the power system does not record the accurate location coordinates of all transmission lines. It is often necessary to first perform high-precision map modeling, and then import the model into the drone control system. After complex calculations to plan the route, or control the drone for a test flight (manual teaching), obtain more refined positioning information, and plan the inspection route, and then fly again according to the preset route. This results in long route planning time and high inspection costs. Summary of the invention

[0003] The present invention provides a method and system for autonomous inspection of power transmission and distribution towers by unmanned aerial vehicles (UAVs), and an inspection UAV. Machine vision technology and positioning detection are used to realize autonomous cruising of the UAV, without the need to plan inspection routes in advance, so as to solve the problems of long initial route planning time and high flight costs.

[0004] The present invention is achieved through the following technical solutions:

[0005] A first aspect of the present invention provides a method for autonomous inspection of transmission and distribution towers by using a drone, comprising:

[0006] S1, acquiring a first image around the inspection starting point taken by an onboard camera;

[0007] S2, identifying a first pole tower according to the first image, and determining a position and a distance of the first pole tower relative to the drone;

[0008] S3, controlling the drone to fly along the direction to a first position away from the first tower, and capturing a second image of the first tower at the first position;

[0009] S4, identifying the type of pole tower to which the first pole tower belongs according to the second image, and determining an inspection point according to the type of pole tower;

[0010] S5, generating an inspection route according to the plurality of inspection points, and controlling the drone to perform inspection along the inspection route.

[0011] The solution of the present invention automatically identifies the inspection target through image processing technology, and can gradually determine the flight route according to the relative position of the tower and the drone, so there is no need to obtain the geographic coordinates of each tower in advance. After locating the relative position of the tower, first navigate the drone to a position near the tower, and take a clearer image of the tower. The tower type is determined by image recognition, and the tower structure can be determined according to the different tower types. Since each type of tower structure and the power equipment thereon, such as insulators, crossarm hardware, etc., have a fixed setting, the position of these inspection points relative to the drone is determined according to the relative position of the tower and the drone, and the inspection route is planned to inspect these inspection points in turn, completing an autonomous inspection of the tower. The present invention does not require complicated pre-survey or test flight steps, and can complete the inspection task by performing a single flight, reducing the inspection cost.

[0012] In one embodiment, the first pole tower is the pole tower closest to the inspection starting point in the inspection direction; and identifying the first pole tower according to the first image includes:

[0013] Performing target segmentation on the first image, extracting target contour features, and identifying all tower targets in the first image according to the target contour features;

[0014] Sort each pole tower target in each first image according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image; the pole tower target ranked first is the pole tower target closest to the drone in each first image;

[0015] According to the distance between each of the first-ranked tower targets and the drone, the first-ranked tower target that is closest is determined as the first tower.

[0016] In one embodiment, the step of sorting each pole tower target in each first image according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image includes:

[0017] If the number of pole tower targets in the first image is one, determining the pole tower target in the first image as the pole tower target with the first ranking;

[0018] If the number of pole tower targets in the first image is two, determining the pole tower target with a larger area in the first image as the pole tower target with the first ranking;

[0019] If the number of pole tower targets in the first image is three or more, the pole tower target with a larger area among the two outermost pole tower targets in the first image is determined as the first-ranked pole tower target.

[0020] In one embodiment, determining the inspection point according to the tower type includes:

[0021] Determine multiple inspection targets on the first tower according to the tower type, and determine the inspection point corresponding to each inspection target according to the position of each inspection target on the first tower and the position of the first tower relative to the drone.

[0022] In one embodiment, after inspecting the first tower, the method further includes:

[0023] S6, controlling the drone to rise to a first height as the starting point for the next inspection;

[0024] Repeat the inspection method of S1-S6 to complete the continuous inspection of multiple towers.

[0025] In one embodiment, the first height is higher than the height of the tower.

[0026] In one embodiment, the method further includes: after inspecting a pole tower, counting the number of pole towers inspected and / or the mileage flown, and if the number of pole towers inspected reaches an inspection threshold and / or the mileage flown reaches a flight threshold, controlling the drone to return to the first inspection starting point.

[0027] In one embodiment, controlling the drone to perform inspection along the inspection route includes:

[0028] After controlling the drone to arrive at the target inspection point in sequence, a third image is captured at the target inspection point, wherein the third image includes the inspection target corresponding to the target inspection point;

[0029] Compare the third image with a preset defective device image to determine whether the inspection target is faulty;

[0030] If a fault occurs, the shooting angle and focal length of the camera are adjusted according to the third image to capture a fourth image of the inspection target.

[0031] A second aspect of the present invention provides an unmanned aerial vehicle autonomous inspection system for power transmission and distribution towers, comprising:

[0032] An acquisition unit, used to acquire a first image around the inspection starting point taken by an onboard camera;

[0033] A positioning unit, used to locate the geographic location of a drone in real time, the drone being used to perform transmission and distribution tower inspection tasks;

[0034] A processing unit, used to process images captured during the inspection process and plan the inspection route;

[0035] A control unit is used to control the drone body, the airborne camera, the positioning unit and the processing unit to execute the drone autonomous inspection method for power transmission and distribution towers as described in any one of the first aspects of the present invention.

[0036] In a third aspect of the present invention, there is provided an inspection drone, comprising: a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program and implement the autonomous inspection method of the transmission and distribution tower by the drone as described in any one of the first aspects of the present invention when executing the computer program.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] Automated and efficient inspection: Through visual navigation technology, drones can autonomously identify poles and towers and complete direction positioning, automatically determine the inspection sequence, and plan inspection routes without human intervention, greatly reducing labor costs and time consumption.

[0039] Lightweight implementation: Simplified target recognition algorithm, based on visual sensing characteristics, intelligently judge the next inspection target according to the tower target size and image coordinates, and accurately judge the result, so that the drone can complete the inspection of consecutive towers in order from near to far to avoid omissions. The tower type is recognized through pattern matching technology, and the inspection point is confirmed according to the structure of the preset tower type, and the inspection route is generated. The algorithm does not require complex modeling process and model training, so the processor and algorithm can be lightweight, and can be carried on drones to avoid timeliness problems caused by remote data transmission.

[0040] Real-time defect detection and high-definition imaging: Utilizing lightweight algorithm model technology, the front-end is deployed with detection algorithms for common distribution network defects such as insulator corrosion, breakage, flashover, arrester aging, and bird damage. During the inspection process, the system analyzes the tower status in real time. Once a defect is found, it immediately triggers angle adjustment and adaptive zoom, automatically captures and shoots high-definition images of defective equipment, and provides a strong basis for defect assessment and repair.

[0041] Real-time data recording and route generation: During the inspection process, the system can generate route information for this inspection task based on the real-time tower information and inspection points, provide accurate path planning for subsequent inspections, and enhance the continuity and traceability of the inspection work.

[0042] Enhance safety and reduce risks: After inspecting each pole tower, adjust the initial inspection point of the drone to a position higher than the general pole tower to ensure unobstructed photography. At the same time, avoid interference from power transmission cables or raised obstacles on the ground when flying from one pole tower to another, and reduce the use of obstacle avoidance algorithms during flight.

[0043] Flexible adaptation to complex environments: The autonomous cruising method of the present invention enables the system to flexibly cope with various complex terrains. The autonomous cruising algorithm can be activated by simply navigating the drone to any location near the power transmission channel. The drone automatically identifies the inspection target, which is particularly suitable for tower inspections in remote, difficult-to-reach or dangerous areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0045] Figure 1 This is a schematic diagram of autonomous cruising of a UAV on a power transmission and distribution tower according to an embodiment of the present invention;

[0046] Figure 2 It is a flow chart of a method for autonomous inspection of power transmission and distribution towers by a drone according to an embodiment of the present invention;

[0047] Figure 3 is a flow chart of a multi-tower continuous inspection method according to an embodiment of the present invention;

[0048] Figure 4 The invention relates to an unmanned aerial vehicle autonomous inspection system for power transmission and distribution towers. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0050] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to or inherent to other steps or units of the device.

[0051] The terms used in the various embodiments of the application are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the application. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meanings commonly understood by ordinary technicians in the field of the various embodiments of the application. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the application.

[0052] The embodiments of the present invention provide a method and system for autonomous inspection of transmission and distribution towers by drones, and an inspection drone, which are suitable for inspection and troubleshooting of transmission line faults, and are beneficial to improving the inspection efficiency of drones and reducing inspection costs.

[0053] like Figure 1 The figure shows a schematic diagram of autonomous cruising of a UAV on a power transmission and distribution tower of the present invention. In the autonomous cruising method of the present invention, the UAV can perform inspection tasks from any position of the transmission line. Any position near the transmission line can be manually determined as the initial position, and the UAV is raised to a certain height as the starting point of the inspection. The inspection direction can be specified or not specified according to the direction of the transmission line, and continuous inspection of multiple towers can be automatically completed starting from the inspection starting point.

[0054] The following takes the autonomous inspection of a tower as an example to illustrate the autonomous inspection method of the present invention. Figure 2 The flowchart of a method for autonomous inspection of power transmission and distribution towers by a drone according to an embodiment of the present invention includes the following steps.

[0055] S1, acquiring a first image around the inspection starting point taken by an onboard camera;

[0056] S2, identifying the first tower according to the first image, and determining the orientation and distance of the first tower relative to the drone;

[0057] S3, controlling the drone to fly along the azimuth to a first position away from the first tower, and capturing a second image of the first tower at the first position;

[0058] S4, identifying the type of pole tower to which the first pole tower belongs according to the second image, and determining the inspection point according to the type of pole tower;

[0059] S5, generates an inspection route according to multiple inspection points, and controls the drone to inspect along the inspection route.

[0060] Before step S1, the drone has been manually navigated to the inspection starting point, which can be any location close to the power transmission line, so that the onboard camera can capture images of nearby towers to locate the nearby towers.

[0061] Preferably, the inspection starting point is located at a certain height, higher than the height of an ordinary pole tower, so that the pole tower image can be taken from top to bottom with an inclination without being blocked by the line of sight of protrusions on the ground, so as to better locate the pole tower coordinates through the image, and when flying from the inspection starting point to the pole tower to be inspected, the flight is maintained at a higher position to avoid or reduce obstacles on the flight path.

[0062] The onboard camera can be a gimbal camera, which is installed in an unobstructed position on the belly of the drone body. It can capture the surrounding images in a 360-degree circle and can be adjusted up and down to capture different heights. The maximum range of adjustment is 90 degrees, that is, the lens can be adjusted from parallel to the belly of the drone to pointing to the ground. When the drone is hovering, the camera can be adjusted to achieve the maximum range of shooting.

[0063] In step S2, the first tower can be identified according to the first image. The specific target in the image can be identified as a tower object based on image recognition technology. The identification of the tower target includes preprocessing the collected image, feature extraction, feature recognition and matching, etc., and the tower features need to be annotated in the known samples in advance. AI intelligent recognition can also be used to train a neural network model through annotated tower samples, and the collected image is input into the trained recognition model to obtain the recognition result of the tower target.

[0064] When collecting the first image, the camera is controlled to capture multiple first images that can cover the area within the range of 360° circumferentially and 90° vertically. Some of the first images contain the tower target, while others do not. The first image that is identified as not containing the tower target can be directly discarded, and the image containing the target tower may contain one tower, multiple towers, or a part of a tower. For the first image that only contains a part of the tower, it can be retained or discarded according to whether it contains the top of the tower or the size of the part in the whole, and whether there is a complete image in the adjacent first images. Finally, the first image with a relatively complete tower target is screened out, and then the first tower is identified.

[0065] When the inspection direction is not set, the first pole tower can be the pole tower closest to the current position of the drone, that is, the inspection starting point, and the inspection direction is determined autonomously according to the inspected route. When the inspection direction is set, only the first image in the inspection direction can be captured, and the first pole tower is the pole tower closest to the current position of the drone in the inspection direction.

[0066] In one embodiment, identifying a first tower according to a first image includes the following method.

[0067] Performing target segmentation on the first image, extracting target contour features, and identifying all tower targets in the first image according to the target contour features;

[0068] Sort each pole tower target in each first image according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image; wherein the pole tower target ranked first is the pole tower target closest to the drone in each first image;

[0069] According to the distance of each first-ranked tower target relative to the UAV, the first-ranked tower target closest to the UAV is determined as the first tower.

[0070] In this embodiment, all the pole towers captured in the same image are sorted by distance according to the visual distance characteristics. When there are multiple pole tower targets in the first image, generally, the pole tower targets with a larger area or located at the edge of the image are closer to the drone, but since each first image may only capture a part of the power transmission and distribution pole tower, each image is sorted separately and then comprehensively sorted to determine the first pole tower target.

[0071] According to the built-in parameters and image data of the camera, as well as the location data of the drone, the direction and distance between the image target and the drone can be determined, thereby locating the position of each tower target, such as the monocular laser three-point ranging method or the binocular ranging method.

[0072] Further, each pole tower target in each first image is sorted according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image, including the following method.

[0073] If the number of pole tower targets in the first image is one, then determining the pole tower target in the first image as the pole tower target with the first ranking;

[0074] If there are two pole tower targets in the first image, the pole tower target with a larger area in the first image is determined as the pole tower target with the first ranking;

[0075] If the number of pole tower targets in the first image is three or more, the pole tower target with a larger area among the two outermost pole tower targets in the first image is determined as the first-ranked pole tower target.

[0076] The first image contains tower targets, which can be divided into the case where there is only one tower target or multiple tower targets. When there is only one tower target, there is no object that can be directly compared, so it is directly added to the total sorting. When there are two tower targets, the distance can be determined based on the size of the area. When there are three or more tower targets, the shooting angle is close to the direction of the transmission line, and multiple towers may have partially overlapping areas. It is difficult to judge based on the large area alone. However, since the transmission and distribution towers are built continuously, from the perspective of shooting, the towers at the edge are the closest or farthest, and the closest and farthest towers have an obvious size relationship visually, which can be determined by combining the area comparison.

[0077] The recognition algorithm of this embodiment is simple and accurate in judgment, and can quickly process image data. It can realize a lightweight processor mounted on a drone, and has higher efficiency and real-time performance than remote transmission and processing of data.

[0078] After determining the position of the first tower, the drone is controlled to fly to a first position away from the first tower, and a second image of the first tower is captured at the first position, thereby capturing a clearer and more complete image of the tower, which facilitates planning of inspection routes for the tower.

[0079] In step S4, since there are several fixed types of pole towers, a library of pole tower models of various types is preset, including pole tower structure information and the positions of power equipment that need to be inspected thereon, such as insulators, crossarm fittings, etc. According to their fixed positions in the pole tower structure model and the relative positions of the drone and the real pole tower, they can be converted into the positional relationship between each device to be inspected and the drone, thereby planning the inspection path based on the current position of the drone.

[0080] In one embodiment of the present invention, the method for determining inspection points according to tower types includes: determining multiple inspection targets on a first tower according to the tower type, and determining the inspection point corresponding to each inspection target according to the position of each inspection target on the first tower and the position of the first tower relative to a drone.

[0081] Inspection route planning should be based on the principle of short route, convenient operation and non-repetitive inspection. Inspections should be completed from the first inspection point to the last inspection point. Figure 1 The inspection points and inspection routes described in 1-2-3-4-5-6-7-8.

[0082] Through the above method, a drone autonomous inspection of a tower can be completed. Furthermore, this method can also be used to complete the continuous inspection of multiple towers. Figure 3 The flowchart of the multi-tower continuous inspection method shown includes the following steps.

[0083] S2-1, capturing a first image around the inspection starting point by using an onboard camera;

[0084] S2-2, identifying a first pole tower according to the first image, and determining a position and a distance of the first pole tower relative to the drone;

[0085] S2-3, controlling the drone to fly along the direction to a first position away from the first tower, and capturing a second image of the first tower at the first position;

[0086] S2-4, identifying the type of pole tower to which the first pole tower belongs according to the second image, and determining the inspection point according to the pole tower type;

[0087] S2-5, generating an inspection route according to multiple inspection points, and controlling the UAV to inspect along the inspection route.

[0088] S2-6, after inspecting the first tower, control the drone to rise to a first height as the starting point for the next inspection. Repeat the inspection methods of S2-1 to S2-6 to complete the continuous inspection of multiple towers.

[0089] Among them, the identification steps S2-1 to S2-6 for a single pole tower are the same as those in the above embodiment, and the same control algorithm is reused. After inspecting a pole tower, the position of the drone is at the last inspection point. If a photo is taken at this position to search for the next pole tower, the line of sight is easily interfered by the current pole tower, which increases the difficulty of identification and data processing. Therefore, the drone is raised to a height higher than the ordinary pole tower at the last inspection point to avoid interference from obstacles. When navigating the drone to the vicinity of the next pole tower, interference on the flight path can also be avoided or reduced.

[0090] When the drone inspects the pole tower along the inspection route, after arriving at each target inspection point in turn, the drone is controlled to hover briefly at the inspection point, and the camera angle is adjusted to capture the third image of the corresponding inspection equipment at the inspection point, and the third image is compared with the pre-stored defect image of the corresponding inspection equipment in real time, or the defect discrimination model is input to preliminarily determine whether the current inspection equipment has defects, such as insulator electrical corrosion, damage, flashover, arrester aging, bird damage, etc. Once a defect is found, the system will immediately trigger the adaptive zoom technology, automatically adjust the focal length of the drone according to the third image to capture multiple high-definition images of the defective equipment. Multiple high-definition images reflect the local information of the defective equipment, so as to conduct a more detailed analysis of the equipment, and can also be used as supplementary data for the defective equipment library to continuously optimize fault detection.

[0091] Furthermore, in the above embodiment, after inspecting a pole tower, the number of inspected pole towers is counted. If the number of inspected pole towers reaches the inspection threshold, the drone is controlled to return to the first inspection starting point. In order to ensure that the drone does not run out of power and fall during the inspection process, the number of inspected pole towers is set according to the available power supply, and the drone returns when the target is achieved to ensure that the drone can land safely. When there is a drone charging station near the power transmission line, it can land at a nearby charging station and inspect again after being fully charged.

[0092] After inspecting a pole tower, the flight mileage can be counted. If the flight mileage reaches the flight threshold, the drone is controlled to return to the first inspection starting point. The flight threshold is set according to the real-time power of the drone and the power required to return to the first inspection starting point. The flight mileage threshold and the inspection pole tower number threshold can be used in combination, and the return procedure is started when either reaches the threshold condition.

[0093] When returning, the return path is replanned according to the last position of the drone and the position of the first inspection starting point. If there are no obstacles on the straight path, the straight return strategy is preferred. If there are obstacles, the return path is optimized through the obstacle avoidance algorithm.

[0094] After the drone lands, all inspection data (including tower information, photo locations, defect images, etc.) will be transmitted to the ground control station. Ground staff can further analyze and process this data to evaluate the operating status of the power grid and develop maintenance plans. This data can also be stored as an inspection route for use in the next inspection.

[0095] The embodiment of the present invention also provides a UAV autonomous inspection system for power transmission and distribution towers, such as Figure 4 As shown, including:

[0096] An acquisition unit, used to acquire a first image around the inspection starting point taken by an onboard camera;

[0097] A positioning unit, used to locate the geographic location of a drone in real time, the drone being used to perform transmission and distribution tower inspection tasks;

[0098] A processing unit, used to process images captured during the inspection process and plan the inspection route;

[0099] A control unit is used to control the drone body, the airborne camera, the positioning unit and the processing unit to execute the drone autonomous inspection method of the power transmission and distribution tower described in any one of the above embodiments of the present invention.

[0100] Among them, the processing unit and the control unit can be mounted on the drone body and integrated into the drone system with lightweight hardware, or they can be set up in a ground station. The data collected by the drone can be transmitted back to the ground workstation for processing through efficient data transmission methods such as 5G communication, and the drone can be controlled to perform corresponding inspection steps through control instructions.

[0101] In addition, in order to ensure the continuous and stable operation of the drone inspection system, regular system maintenance and upgrades are required. This includes checking the wear of the drone's mechanical structure, electronic components, sensors and other parts, as well as updating the algorithm model and database of the AI ​​system based on the newly collected data. Through continuous optimization and improvement, the drone adaptive inspection system will play a more important role in power grid maintenance.

[0102] An embodiment of the present invention further provides a drone, comprising a memory and a processor.

[0103] The memory is a computer-readable storage medium that can be used to store software programs, computer executable programs, and modules. The processor executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory, so as to implement the autonomous inspection method of the transmission and distribution tower by drones described in any of the above embodiments of the invention.

[0104] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0105] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for autonomous inspection of power transmission and distribution towers by a drone described in any of the above embodiments of the present invention is implemented. The storage medium may be a ROM / RAM, a magnetic disk, an optical disk, etc.

[0106] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer executes the drone autonomous inspection method for power transmission and distribution towers described in any of the above embodiments of the present invention.

[0107] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for autonomous inspection of transmission and distribution towers by using unmanned aerial vehicles, characterized in that: include: S1, acquiring a first image around the inspection starting point taken by an onboard camera; S2, identifying a first pole tower according to the first image, and determining a position and a distance of the first pole tower relative to the drone; S3, controlling the drone to fly along the direction to a first position away from the first tower, and capturing a second image of the first tower at the first position; S4, identifying the type of pole tower to which the first pole tower belongs according to the second image, and determining an inspection point according to the type of pole tower; S5, generating an inspection route according to the plurality of inspection points, and controlling the drone to perform inspection along the inspection route.

2. The autonomous inspection method of transmission and distribution towers by unmanned aerial vehicles according to claim 1 is characterized in that: The first pole tower is the pole tower closest to the inspection starting point in the inspection direction; and the identifying the first pole tower according to the first image includes: Performing target segmentation on the first image, extracting target contour features, and identifying all tower targets in the first image according to the target contour features; Sort each pole tower target in each first image according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image; the pole tower target ranked first is the pole tower target closest to the drone in each first image; According to the distance between each of the first-ranked tower targets and the drone, the first-ranked tower target that is closest is determined as the first tower.

3. The autonomous inspection method of transmission and distribution towers by unmanned aerial vehicles according to claim 2 is characterized in that: The step of sorting each pole tower target in each first image according to the area and position of each pole tower target in the first image to obtain the pole tower target ranked first in each first image includes: If the number of pole tower targets in the first image is one, determining the pole tower target in the first image as the pole tower target with the first ranking; If the number of pole tower targets in the first image is two, determining the pole tower target with a larger area in the first image as the pole tower target with the first ranking; If the number of pole tower targets in the first image is three or more, the pole tower target with a larger area among the two outermost pole tower targets in the first image is determined as the first-ranked pole tower target.

4. The autonomous inspection method of transmission and distribution towers by unmanned aerial vehicles according to claim 1 is characterized in that: Determining the inspection point according to the tower type includes: Determine multiple inspection targets on the first tower according to the tower type, and determine the inspection point corresponding to each inspection target according to the position of each inspection target on the first tower and the position of the first tower relative to the drone.

5. The autonomous inspection method of transmission and distribution towers by unmanned aerial vehicles according to claim 1 is characterized in that: After inspecting the first tower, the method further includes: S6, controlling the drone to rise to a first height as a starting point for the next inspection; Repeat the inspection method of S1-S6 to complete the continuous inspection of multiple towers.

6. The method for autonomous inspection of power transmission and distribution towers by using unmanned aerial vehicles according to claim 5, characterized in that: The first height is higher than the height of the tower.

7. The autonomous inspection method of transmission and distribution towers by unmanned aerial vehicles according to claim 5 is characterized in that: The method also includes: after inspecting a pole tower, counting the number of inspected pole towers and / or the mileage flown, and if the number of inspected pole towers reaches an inspection threshold and / or the mileage flown reaches a flight threshold, controlling the drone to return to the first inspection starting point.

8. The method for autonomous inspection of power transmission and distribution towers by unmanned aerial vehicles according to any one of claims 1 to 7, characterized in that: The controlling the drone to perform inspection along the inspection route includes: After controlling the drone to arrive at the inspection points in sequence, a third image is captured at the inspection points, wherein the third image includes the inspection target corresponding to the inspection point; Compare the third image with a preset defective device image to determine whether the inspection target is faulty; If a fault occurs, the shooting angle and focal length of the camera are adjusted according to the third image to capture a fourth image of the inspection target.

9. The UAV autonomous inspection system for power transmission and distribution towers is characterized by: include: An acquisition unit, used to acquire a first image around the inspection starting point taken by an onboard camera; A positioning unit, used to locate the geographic location of a drone in real time, the drone being used to perform transmission and distribution tower inspection tasks; A processing unit, used to process images captured during the inspection process and plan the inspection route; A control unit is used to control the drone, the airborne camera, the positioning unit and the processing unit to execute the drone autonomous inspection method for power transmission and distribution towers as described in any one of claims 1-8.

10. Inspection drones, including: A memory and a processor, wherein the memory is used to store a computer program, and wherein the processor is used to execute the computer program and, when executing the computer program, implement the drone autonomous inspection method for power transmission and distribution towers as described in any one of claims 1 to 8.

Images