Multi-area coverage inspection system using unmanned aerial vehicle cluster

Abstract

The invention discloses a multi-area coverage inspection system using an unmanned aerial vehicle cluster, and particularly relates to the technical field of unmanned aerial vehicle cluster inspection. The system comprises an inspection area division module, an unmanned aerial vehicle cluster setting module, a road surface damage monitoring module, a traffic sign monitoring module, a monitoring response module, a working state judgment module, an inspection display early warning module and a database. According to the invention, the unmanned aerial vehicle cluster multi-area inspection is adopted, in a cluster mode, a plurality of unmanned aerial vehicles can work cooperatively, large-range and multi-area efficient inspection is realized through cooperative flight and division and cooperation, the inspection speed and precision are greatly improved, and the labor cost and the safety risk are reduced at the same time. According to the method, the inspection areas of the expressway are divided, the inspection speed and precision are improved in a targeted manner, the inspection precision of the risk area is ensured, and the inspection efficiency of the general area is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) cluster inspection, and in particular to a multi-area coverage inspection system using an unmanned aerial vehicle (UAV) cluster. Background Art

[0002] The total length of highways is often very large, and the wide inspection area makes manual inspection very time-consuming, costly, and difficult to ensure comprehensive coverage. Traditional manual inspections often find it difficult to monitor the status of the entire road system in real time and accurately, and it is difficult to meet the growing demand. Therefore, it is necessary to study the multi-area coverage inspection technology of drone clusters on highways.

[0003] The prior art, such as the invention patent application announced as: CN118960752A, discloses a method and system for full-process path planning for multi-UAV inspection of a highway, the method comprising: constructing a static obstacle grid map; in the static obstacle grid map, determining the first path and the second path of the UAV respectively according to the algorithm of the adaptive expansion field; calculating the first path length and the second path length respectively according to the first path and the second path, and judging whether the path length of the entire inspection process meets the cruising distance requirement of the UAV according to the first path length and the second path length; determining whether the section to be inspected can be covered for inspection according to the driving radius of the UAV and the width of the section to be inspected; determining the third path, determining the fourth path, determining the fifth path, and combining the third, fourth and fifth paths of each UAV to obtain the complete path of each UAV.

[0004] The prior art, such as the invention patent application announced as CN118798591A, discloses an intelligent inspection system for highway equipment, which includes: obtaining a parameter Z that can reflect the aging speed of the highway through historical vehicle information and temperature and humidity information running on the highway, and integrating the parameter Z with the maintenance density of each road section, and then further allocating the number of inspections for each monitoring section on the highway on this basis. The invention also analyzes the traffic flow information of each monitoring section in different time periods, and reasonably selects the plan with the smallest traffic flow or the smallest overall traffic flow impact as the final inspection plan, ensuring that the drone inspection unit can reduce the obstruction of the road surface by vehicles on the road surface when performing the inspection work, so that the drone can collect and obtain complete road surface information of each monitoring section as much as possible.

[0005] In combination with the above scheme, it is found that the existing technology for highway inspection ignores the actual highway inspection process. Due to the huge actual length of the highway, relying on a drone for inspection can only solve the inspection of a small part of the area, and cannot cover the inspection of all areas of the highway, resulting in low inspection efficiency, and unable to accurately and quickly inspect the actual road conditions of the highway and check for hidden dangers, resulting in the safety of the highway cannot be guaranteed, increasing the risk of accidents. At the same time, the status judgment of the inspection drone is ignored, and an efficient collaborative system is not established to deal with the abnormal working status of the drone, resulting in working risks of the drone during the inspection process, causing instability in the work of the drone inspection, resulting in low efficiency of highway drone inspection, and it is difficult to replace manual work for efficient and accurate highway inspections. Summary of the invention

[0006] The purpose of the present invention is to provide a multi-area coverage inspection system using a drone cluster, which solves the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solution: a multi-area coverage inspection system using a drone cluster, the system comprising: The inspection area division module is used to obtain the map information of the highway to be inspected and the flight parameters of the drone, divide the inspection areas of the highway to be inspected, and divide the inspection sections according to the division intervals.

[0008] The drone cluster setting module obtains the road damage risk index and traffic sign risk index of each inspection area in each inspection section in history, divides the inspection level of each inspection area in each inspection section, and sets the drone's working mode based on the inspection level of each inspection area in each inspection section.

[0009] The road damage monitoring module is used to analyze the road inspection videos of each inspection area of ​​each inspection section, obtain the road parameters of each inspection area of ​​each inspection section, and calculate the road damage risk index of each inspection area of ​​each inspection section.

[0010] The traffic sign monitoring module is used to analyze the traffic sign inspection videos of each inspection area of ​​each inspection section, obtain the traffic sign parameters of each inspection area of ​​each inspection section, and calculate the traffic sign risk index of each inspection area of ​​each inspection section.

[0011] The monitoring response module is used to calculate the highway risk factor of each inspection area of ​​each inspection section, evaluate the highway risk factor level of each inspection area of ​​each inspection section, and implement response measures corresponding to the damage level of traffic signs in each inspection area of ​​each inspection section.

[0012] The working status judgment module is used to monitor the working status parameters of the inspection drone in each inspection area of ​​each inspection section. If it is judged to be abnormal, the abnormal working status response measures are executed.

[0013] The inspection display and early warning module is used to build a three-dimensional model of the inspection highway, display and warn the inspection data of each inspection area and the working status information of the drone.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention divides the inspection areas of highways, and divides the inspection levels of each inspection area according to the risk levels of the highways in historical inspections, sets specific parameters for inspection drones in inspection areas of different inspection levels, and specifically improves the speed and accuracy of inspections, thereby ensuring the inspection accuracy of high-risk areas and improving the inspection efficiency of low-risk areas.

[0015] 2. The present invention adopts drone cluster multi-area inspection. In cluster mode, multiple drones can work together to achieve efficient inspection of a large range and multiple areas through coordinated flight and division of labor, greatly improving the speed and accuracy of inspection while reducing labor costs and safety risks.

[0016] 3. The present invention uses image recognition to identify the road conditions and traffic signs of expressways, analyze the risk level of expressways, and thus take response measures corresponding to the risk level of expressways, effectively solving the potential safety hazards existing on expressways and ensuring the safety of expressway traffic.

[0017] 4. The present invention sets up a working network architecture of a drone cluster system, which is composed of a control center, a pilot drone and a patrol drone. The pilot drone monitors the working status of each patrol drone and responds to the patrol drone in abnormal working status in time, thereby increasing the stability of the drone cluster inspection and ensuring the controllability of the drone inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the 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 work.

[0019] Figure 1 It is a system structure connection diagram of the present invention.

[0020] Figure 2 Schematic diagram of the network architecture of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Reference Figure 1 The present invention provides a multi-area coverage inspection system using a drone cluster, the system comprising: an inspection area division module, used to obtain map information of the highway to be inspected, various flight parameters of the drone, divide the inspection areas of the highway to be inspected, and divide the inspection sections according to the division intervals.

[0023] The drone cluster setting module obtains the road damage risk index and traffic sign risk index of each inspection area in each inspection section in history, divides the inspection level of each inspection area in each inspection section, and sets the drone's working mode based on the inspection level of each inspection area in each inspection section.

[0024] The road damage monitoring module is used to analyze the road inspection videos of each inspection area of ​​each inspection section, obtain the road parameters of each inspection area of ​​each inspection section, and calculate the road damage risk index of each inspection area of ​​each inspection section.

[0025] The traffic sign monitoring module is used to analyze the traffic sign inspection videos of each inspection area of ​​each inspection section, obtain the traffic sign parameters of each inspection area of ​​each inspection section, and calculate the traffic sign risk index of each inspection area of ​​each inspection section.

[0026] The monitoring response module is used to calculate the highway risk factor of each inspection area of ​​each inspection section, evaluate the highway risk factor level of each inspection area of ​​each inspection section, and implement response measures corresponding to the damage level of traffic signs in each inspection area of ​​each inspection section.

[0027] The working status judgment module is used to monitor the working status parameters of the inspection drone in each inspection area of ​​each inspection section. If it is judged to be abnormal, the abnormal working status response measures are executed.

[0028] The inspection display and early warning module is used to build a three-dimensional model of the inspection highway, display and warn the inspection data of each inspection area and the working status information of the drone.

[0029] The database is used to store the division intervals of inspection sections, store the map information of the highway to be inspected and the flight parameters of the drone, store the grid ratio, store the road damage risk index and traffic sign risk index of each historical inspection of each inspection area in each inspection section, store the judgment threshold of the highway risk factor, store the flight speed and horizontal field of view of the inspection drone in the general area and the risk area, store the influencing factors of the unit number of cracks, the influencing factors of the unit length of cracks, the influencing factors of the unit number of potholes, and the influencing factors of the unit area of ​​potholes, store each interval of highway risk level, and store the corresponding inspection frequency of the response measures for each highway risk level.

[0030] It should be noted that in a specific embodiment, a multi-area coverage inspection system using a drone cluster is provided, wherein the inspection area division module is connected to the drone cluster setting module, the drone cluster setting module is connected to the road damage monitoring module, the road damage monitoring module is connected to the traffic sign monitoring module, the traffic sign monitoring module is connected to the monitoring response module, the monitoring response module is connected to the working status judgment module, the working status judgment module is connected to the inspection display and warning module, and the database is connected to the drone cluster setting module, the road damage monitoring module, the traffic sign monitoring module and the inspection display and warning module.

[0031] In a specific embodiment of the present invention, the inspection areas of the highway to be inspected are divided into the following specific analysis methods: based on the map information of the highway to be inspected, the starting point coordinates, the end point coordinates and the length of the highway to be inspected are extracted. , based on the flight parameters of the drone, including endurance speed And battery life , through the formula: , calculate the drone's endurance inspection distance .

[0032] By formula: , calculate the total number of inspection areas divided by the highway to be inspected , Indicates the symbol for rounding up, with the starting coordinates of the highway to be inspected as the starting point of the first inspection area. is the inspection distance of the inspection area, and the terminal coordinate of the highway to be inspected is the terminal of the last inspection area, which is divided into inspection areas to obtain the inspection areas of the highway to be inspected.

[0033] It should be noted that, in a specific embodiment, Indicates the rounding up symbol. The cruising speed and cruising duration are obtained from the factory specifications of the drone. The cruising speed refers to the suitable flight speed of the drone obtained by the manufacturer's test on the basis of ensuring the cruising duration.

[0034] In a specific embodiment of the present invention, the inspection sections are divided according to the division intervals, and the specific analysis method is: extracting the division intervals in the database , starting from the starting coordinates of the highway to be inspected, and the number The inspection area is divided into an inspection section, denoted by ,in , Indicates the number of each inspection section. Indicates the total number of inspection segments.

[0035] It should be noted that, in a specific embodiment, the division interval is manually set by a technician based on a comprehensive evaluation of the working parameters of the drone, and the division interval is extracted from the database. , then the number of inspection areas contained in each inspection section is set to 5, and the starting point of the expressway is used as the area division point, and 5 inspection areas are divided into one inspection section in sequence. If there are less than 5 inspection areas in the end, the less than 5 inspection areas will be divided into a separate inspection section.

[0036] In a specific embodiment of the present invention, the inspection level of each inspection area of ​​each inspection section is divided, and the specific analysis method is as follows: based on the road surface damage risk index and traffic sign risk index of each inspection area of ​​each inspection section in each historical inspection, average processing is performed respectively to obtain the historical average road surface damage risk index of each inspection area of ​​each inspection section. , Historical average traffic sign risk index , , Indicates the number of each inspection area. Indicates the total number of inspection areas.

[0037] It should be noted that, in a specific embodiment, the road surface damage risk index and traffic sign risk index of each historical inspection of each inspection area of ​​each inspection section are extracted from the database.

[0038] By formula: , calculate the historical highway risk coefficient of each inspection area in each inspection section ,like , then determine the The first inspection section The inspection level of the inspection area is general area, among which is the judgment threshold of the highway risk factor extracted from the database.

[0039] like , then determine the The first inspection section The inspection level of each inspection area is a risk area.

[0040] The inspection level of each inspection area in each inspection section is summarized.

[0041] It should be noted that, in a specific embodiment, the judgment threshold of the highway risk coefficient is divided and set by technical personnel according to the influence of the later highways corresponding to the historical highway risk coefficients.

[0042] The present invention divides the inspection areas of highways, divides the inspection levels of each inspection area according to the risk levels of the highways in historical inspections, sets specific parameters for inspection drones in inspection areas of different inspection levels, and specifically improves the speed and accuracy of inspections, thereby ensuring the inspection accuracy in high-risk areas and increasing the inspection efficiency in low-risk areas.

[0043] In a specific embodiment of the present invention, the working mode of the drone is set based on the inspection level of each inspection area in each inspection section. The specific analysis method is: each inspection section is equipped with a pilot drone, which is responsible for the coordinated command of the inspection drones in each inspection area of ​​each inspection section.

[0044] Based on the inspection level of each inspection area in each inspection section, the pilot drone sets the flight speed of the inspection drone in the general area of ​​each inspection section to the value extracted from the database. , the horizontal field of view is set to the value extracted from the database The flight speed of the inspection drone in the risk area is set to the value extracted from the database. , the horizontal field of view is set to the value extracted from the database .

[0045] It should be noted that in a specific embodiment, the flight speed of the inspection drone in the general area is greater than the flight speed of the inspection drone in the risk area, and the horizontal field of view angle of the inspection drone in the general area is greater than the horizontal field of view angle of the inspection drone in the risk area, which are all pre-set by technical personnel according to the actual environment.

[0046] The flight speed of the inspection drone is such that a slower flight speed can obtain higher quality images, which helps to obtain more detailed inspection results in risk areas, and a faster flight speed can improve the efficiency of the inspection while ensuring the acquisition of inspection information.

[0047] The inspection drone has a wide horizontal field of view for acquiring a wide range of information in a general area, improving inspection efficiency, and a small-angle field of view for performing fine inspection tasks in risk areas, providing higher clarity and details.

[0048] The present invention adopts drone cluster multi-area inspection. In cluster mode, multiple drones can work together to achieve efficient inspection of a large range and multiple areas through coordinated flight and division of labor, greatly improving the speed and accuracy of inspection while reducing labor costs and safety risks.

[0049] In a specific embodiment of the present invention, the pavement parameters of each inspection area of ​​each inspection section are obtained, and the pavement damage risk index of each inspection area of ​​each inspection section is calculated. The specific analysis method is: based on each frame image of the pavement inspection video of each inspection area of ​​each inspection section, a deep learning model is used to automatically identify the number of cracks in each inspection area of ​​each inspection section. , the number of potholes , the total length of cracks in each inspection area of ​​each inspection section , the total area of ​​the pits in each inspection area of ​​each inspection section .

[0050] It should be noted that in a specific embodiment, based on a deep learning model, each frame image of a road inspection video of each inspection area of ​​each inspection section is trained according to a pre-trained model, and contour detection is used to extract the contours of each crack in each inspection area of ​​each inspection section. The actual length of each crack in each inspection area of ​​each inspection section is obtained by calculating the arc length of the contour, and the total length of the cracks in each inspection area of ​​each inspection section is added together. Contour detection is used to extract the contours of each pothole in each inspection area of ​​each inspection section, and the number of pixels of each pothole is counted to obtain the total area of ​​the potholes in each inspection area of ​​each inspection section.

[0051] By formula: , calculate the pavement damage risk index of each inspection area in each inspection section ,in represents the impact factor of the unit number of cracks extracted from the database, represents the influence factor of the crack per unit length extracted from the database, represents the impact factor of the unit number of potholes extracted from the database, Represents the impact factor of potholes per unit area extracted from the database.

[0052] In a specific embodiment of the present invention, the parameters of traffic signs in each inspection area of ​​each inspection section are obtained, and the risk index of traffic signs in each inspection area of ​​each inspection section is calculated. The specific analysis method is: based on each frame image of the traffic sign inspection video in each inspection area of ​​each inspection section, the traffic signs are divided according to the gridding ratio extracted from the database, and the images of traffic signs in each inspection area of ​​each inspection section are automatically identified using a deep learning model, and the RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section is extracted.

[0053] It should be noted that, in a specific embodiment, the division using the grid ratio extracted from the database specifically refers to, for example, gridding each frame image of the traffic sign inspection video of each inspection area of ​​each inspection section at a ratio of 3 times 4, and obtaining the RGB value of each pixel at each grid intersection.

[0054] The contours of the traffic signs in the inspection areas of the inspection sections are extracted, and the inclination angles of the traffic signs in the inspection areas are obtained according to the minimum circumscribed rectangles of the contours of the traffic signs in the inspection areas of the inspection sections.

[0055] It should be noted that, in a specific embodiment, the computer image analysis software obtains the tilt angle of each traffic sign in each inspection area by setting a minimum circumscribed rectangle for the image of each traffic sign in each inspection area of ​​each inspection section.

[0056] By using image analysis software, the RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section is compared with the standard RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section in the database to obtain the color similarity of each traffic sign in each inspection area of ​​each inspection section, and the average value is processed to obtain the average color similarity of the traffic signs in each inspection area of ​​each inspection section. .

[0057] Similarly, the average tilt angle compliance of the traffic signs in each inspection area of ​​each inspection section is obtained. .

[0058] By formula: , calculate the risk index of traffic signs in each inspection area of ​​each inspection section .

[0059] In a specific embodiment of the present invention, the highway risk coefficient of each inspection area of ​​each inspection section is calculated, the highway risk coefficient level of each inspection area of ​​each inspection section is evaluated, and the response measures corresponding to the damage level of the traffic sign in each inspection area of ​​each inspection section are implemented. The specific analysis method is: Road damage risk index for each inspection area based on each inspection section , Risk Index of Traffic Signs , through the formula: , the highway risk coefficient of each inspection area in each inspection section is calculated.

[0060] like If the risk level is in the first interval of the expressway, the The first inspection section The highway risk level in the inspection area is high, and the first-level highway risk response measures are implemented.

[0061] like If the highway is in the second risk level interval, the The first inspection section The highway risk level in the inspection area is medium, and the second-level highway risk response measures are implemented.

[0062] like If the highway is in the third risk level interval, the The first inspection section The risk level of highways in the inspection areas is low.

[0063] The first-level response measure for highway risks is to send the inspection information from the pilot drone of each inspection section to the control center, which will display it in three dimensions and issue early warnings to highway maintenance personnel, who will then carry out on-site maintenance.

[0064] The secondary response measures for highway risks are as follows: The first inspection section The next round of inspection level for each inspection area is set as a risk area.

[0065] It should be noted that, in a specific embodiment, each interval of the highway risk level is preset by a technician based on a comprehensive assessment of the actual impact of the risk coefficient of each historical highway on subsequent highways, and is stored in a database.

[0066] The present invention uses image recognition to identify the road conditions and traffic signs of expressways, analyzes the risk level of expressways, and thus takes response measures corresponding to the risk level of expressways, effectively resolving the potential safety hazards existing on expressways and ensuring the safety of expressway traffic.

[0067] In a specific embodiment of the present invention, the working state parameters of the inspection drones in each inspection area of ​​each inspection section are monitored. If an abnormality is determined, the abnormal working state response measures are executed. The specific analysis method is as follows: the pilot drone of each inspection section obtains the real-time power of the inspection drones in each inspection area it is responsible for. The pilot drone of each inspection section sends a network test signal to the inspection drones of each inspection area it is responsible for, and obtains the response time of the inspection drones of each inspection area of ​​each inspection section. .

[0068] It should be noted that, in a specific embodiment, the pilot drone of each inspection section sends a network test signal to the inspection drones in each inspection area of ​​the area it is responsible for at intervals. After receiving the network test signal, the inspection drones in each inspection area will send a response signal to the pilot drone of the inspection section described in the inspection area. The pilot drone of each inspection section will count the response time of the inspection drones in each inspection area it is responsible for.

[0069] like or , then determine the The first inspection section The working status of the inspection drone in the inspection area is abnormal. The first inspection section The inspection area is recorded as an abnormal inspection area, and the abnormal response measures for the working status are implemented, among which Indicates the power threshold for normal operation of the inspection drone extracted from the database. Indicates the network response time of normal operation of the inspection drone extracted from the database.

[0070] It should be noted that, in a specific embodiment, the power threshold for the normal operation of the inspection drone is to ensure that the drone has sufficient power to return home after completing the inspection mission. It is pre-set by the technician and stored in the database.

[0071] The network response time for the normal operation of the inspection drone is preset by the technicians according to the network response time between the inspection drone with the farthest working distance from the pilot drone and the pilot drone, and a redundancy value is set, and stored in the database.

[0072] The abnormal working status response measures refer to the pilot drone of the inspection section to which the abnormal inspection area belongs, screening the remaining power of the inspection drones in the inspection areas with a screening step of 1 on the left and right sides of the abnormal inspection area after the inspection is completed. If the power demand for the second inspection is met, the pilot drone of the inspection section sends a temporary inspection task to the inspection drones in the inspection area of ​​the abnormal inspection area to perform the inspection of the abnormal inspection area.

[0073] If the power requirement for the second inspection is not met, the pilot UAV of the inspection section increases the screening step size in sequence, and uses the screening step size to screen the inspection UAVs in the inspection areas on the left and right sides of the abnormal inspection area based on the remaining power after the inspection is completed, and repeats the above operation.

[0074] It should be noted that, in a specific embodiment, the pilot drone first screens the remaining power of the inspection drones in the inspection area of ​​the abnormal inspection area in the direction of the highway with a screening step of 1 after the inspection is completed. If the requirement is met, the inspection drones in the inspection area with a screening step of 1 in the direction of the highway will perform the temporary inspection task. If the requirement is not met, the remaining power of the inspection drones in the inspection area in the opposite direction of the highway will be screened after the inspection is completed, and the operation is repeated.

[0075] If the residual current of the inspection drones in adjacent inspection areas after the inspection is not satisfied, then the remaining power of the inspection drones in the inspection area in the direction of the highway with a screening step of 2 after the inspection is completed will be screened again. If it is satisfied, the inspection drones in the inspection area in the direction of the highway with a screening step of 2 will perform temporary inspection tasks. If it is not satisfied, the remaining power of the inspection drones in the inspection area in the opposite direction of the highway after the inspection is screened, and the operation is repeated.

[0076] If there is no inspection area that the inspection section is responsible for in the direction of the highway or the opposite direction of the highway in the abnormal inspection area, the judgment of this direction will be skipped.

[0077] If the inspection drones in each inspection area of ​​the inspection section do not meet the power requirements of the secondary inspection, the pilot drone of the inspection section sends a work abnormality signal to the inspection control center, and the inspection control center wakes up the idle drones to perform temporary inspection tasks in the abnormal inspection areas of the inspection section.

[0078] The screening step increases successively. If all the inspection areas of the inspection section to which the abnormal inspection area belongs have been screened and none of them meet the requirements, the pilot drone of the inspection section will send a work abnormality signal to the inspection control center, and the inspection control center will respond.

[0079] It should be noted that, in a specific embodiment, the drone clusters set up by the system operate in batches. When one batch of drone clusters is conducting multi-area coverage inspections, the remaining batches of drone clusters are idle and can be awakened by the inspection control center to perform temporary inspection tasks.

[0080] The present invention sets up a working network architecture of a drone cluster system, which is composed of a control center, a pilot drone and a patrol drone. The pilot drone monitors the working status of each patrol drone and responds to the patrol drone in abnormal working status in time, thereby increasing the stability of the drone cluster inspection and ensuring the controllability of the drone inspection process.

[0081] In a specific embodiment of the present invention, the inspection data and drone working status information of each inspection area are displayed and warned, and the specific analysis method is as follows: based on the map of the highway in the inspection area, the divided inspection areas and the inspection drones, a three-dimensional display model is generated through three-dimensional modeling software to display the working status of the inspection drones in each inspection area of ​​each inspection section and the risk level of the highway.

[0082] Based on the highway risk level of each inspection area in each inspection section, the color warning corresponding to each risk level is displayed in the three-dimensional display model.

[0083] Based on the working status parameters of the inspection drone in each inspection area of ​​each inspection section, the color warning corresponding to each abnormal working status parameter is displayed in the three-dimensional display model.

[0084] It should be noted that, in a specific embodiment, the color warning corresponding to each risk level is displayed in the three-dimensional display model. For example, if the risk level of the highway is high, it will match the red warning; if the risk level of the highway is medium, it will match the yellow warning; and if the risk level of the highway is low, it will match the green warning.

[0085] The color warning corresponding to each abnormal working status parameter is displayed in the three-dimensional display model. For example, if the real-time power of the inspection drone is abnormal, it will match the blue warning. If the network response time of the inspection drone is abnormal, it will match the purple warning.

[0086] Reference Figure 2As shown, the system architecture of the present invention is divided into three layers, namely, an inspection control center, a pilot drone and an inspection drone. The inspection drones in each inspection area obtain the highway inspection data of each inspection area and send it to the pilot drone of the inspection section to which it belongs. The pilot drone of each inspection section obtains the working status data of the inspection drones in the inspection areas it is responsible for, and determines whether the working status of the inspection drones in each inspection area is abnormal. The pilot drone of each inspection section sends the highway inspection data of each inspection area it is responsible for and the judgment result of whether the working status is abnormal to the inspection control center for display warning and abnormal response.

[0087] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A multi-area coverage inspection system using a drone cluster, characterized in that: The system comprises: The inspection area division module is used to obtain the map information of the highway to be inspected and the flight parameters of the drone, divide the inspection areas of the highway to be inspected, and divide the inspection sections according to the division intervals; The drone cluster setting module obtains the road damage risk index and traffic sign risk index of each inspection area in each inspection section in history, divides the inspection level of each inspection area in each inspection section, and sets the working mode of the drone based on the inspection level of each inspection area in each inspection section; The road damage monitoring module is used to analyze the road inspection videos of each inspection area of ​​each inspection section, obtain the road parameters of each inspection area of ​​each inspection section, and calculate the road damage risk index of each inspection area of ​​each inspection section; Traffic sign monitoring module, used to analyze the traffic sign inspection video of each inspection area of ​​each inspection section, obtain the parameters of the traffic signs of each inspection area of ​​each inspection section, and calculate the traffic sign risk index of each inspection area of ​​each inspection section; The monitoring response module is used to calculate the highway risk factor of each inspection area of ​​each inspection section, evaluate the highway risk factor level of each inspection area of ​​each inspection section, and implement response measures corresponding to the damage level of traffic signs in each inspection area of ​​each inspection section; The working status judgment module is used to monitor the working status parameters of the inspection drones in each inspection area of ​​each inspection section. If it is judged to be abnormal, the abnormal working status response measures are executed; The inspection display and early warning module is used to build a three-dimensional model of the inspection highway, display and warn the inspection data of each inspection area and the working status information of the drone.

2. A multi-area coverage inspection system using a drone cluster according to claim 1, characterized in that: The specific analysis method for dividing the inspection areas of the expressway to be inspected is as follows: Based on the map information of the highway to be inspected, extract the starting coordinates, end coordinates and length of the highway to be inspected , based on the flight parameters of the drone, including endurance speed And battery life , through the formula: , calculate the drone's endurance inspection distance ; By formula: , calculate the total number of inspection areas divided by the highway to be inspected , Indicates the symbol for rounding up, with the starting coordinates of the highway to be inspected as the starting point of the first inspection area. is the inspection distance of the inspection area, and the terminal coordinate of the highway to be inspected is the terminal of the last inspection area, which is divided into inspection areas to obtain the inspection areas of the highway to be inspected.

3. A multi-area coverage inspection system using a drone cluster according to claim 2, characterized in that: The specific analysis method for dividing each inspection section according to the division interval is as follows: Extracting partition intervals from the database , starting from the starting coordinates of the highway to be inspected, and the number The inspection area is divided into an inspection section, denoted as ,in , Indicates the number of each inspection section. Indicates the total number of inspection segments.

4. A multi-area coverage inspection system using a drone cluster according to claim 3, characterized in that: The specific analysis method of the inspection level of each inspection area divided into each inspection section is as follows: Based on the road surface damage risk index and traffic sign risk index of each inspection area in each inspection section, the average value is processed to obtain the historical average road surface damage risk index of each inspection area in each inspection section. , Historical average traffic sign risk index , , Indicates the number of each inspection area. Indicates the total number of inspection areas; By formula: , calculate the historical highway risk coefficient of each inspection area in each inspection section ,like , then determine the The first inspection section The inspection level of the inspection area is general area, among which is the judgment threshold of the highway risk factor extracted from the database; like , then determine the The first inspection section The inspection level of each inspection area is a risk area; The inspection level of each inspection area in each inspection section is summarized.

5. The multi-area coverage inspection system using drone clusters according to claim 4 is characterized in that: The inspection level of each inspection area in each inspection section is used to set the working mode of the drone. The specific analysis method is as follows: Each inspection section is equipped with a pilot drone, which is responsible for the coordinated command of the inspection drones in each inspection area of ​​each inspection section; Based on the inspection level of each inspection area in each inspection section, the pilot drone sets the flight speed of the inspection drone in the general area of ​​each inspection section to the value extracted from the database. , the horizontal field of view is set to the value extracted from the database The flight speed of the inspection drone in the risk area is set to the value extracted from the database. , the horizontal field of view is set to the value extracted from the database .

6. A multi-area coverage inspection system using a drone cluster according to claim 5, characterized in that: The specific analysis method for obtaining the road surface parameters of each inspection area of ​​each inspection section and calculating the road surface damage risk index of each inspection area of ​​each inspection section is as follows: Based on each frame image of the road inspection video of each inspection area of ​​each inspection section, the deep learning model is used to automatically identify the number of cracks in each inspection area of ​​each inspection section. , the number of potholes , the total length of cracks in each inspection area of ​​each inspection section , the total area of ​​the pits in each inspection area of ​​each inspection section ; By formula: , calculate the pavement damage risk index of each inspection area in each inspection section ,in represents the impact factor of the unit number of cracks extracted from the database, represents the influence factor of the crack per unit length extracted from the database, represents the impact factor of the unit number of potholes extracted from the database, Represents the impact factor of potholes per unit area extracted from the database.

7. A multi-area coverage inspection system using a drone cluster according to claim 6, characterized in that: The specific analysis method for obtaining the parameters of the traffic signs in each inspection area of ​​each inspection section and calculating the risk index of the traffic signs in each inspection area of ​​each inspection section is as follows: Based on each frame image of the traffic sign inspection video of each inspection area of ​​each inspection section, the images of each traffic sign in each inspection area of ​​each inspection section are divided according to the gridding ratio extracted from the database, and the images of each traffic sign in each inspection area of ​​each inspection section are automatically identified using a deep learning model, and the RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section is extracted; Extract the contours of each traffic sign in each inspection area of ​​each inspection section, and obtain the inclination angle of each traffic sign in each inspection area according to the minimum circumscribed rectangle of the contours of each traffic sign in each inspection area of ​​each inspection section; By using image analysis software, the RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section is compared with the standard RGB value of each pixel at the cross intersection of the image grid of each traffic sign in each inspection area of ​​each inspection section in the database to obtain the color similarity of each traffic sign in each inspection area of ​​each inspection section, and the average value is processed to obtain the average color similarity of the traffic signs in each inspection area of ​​each inspection section. ; Similarly, the average tilt angle compliance of the traffic signs in each inspection area of ​​each inspection section is obtained. ; By formula: , calculate the risk index of traffic signs in each inspection area of ​​each inspection section .

8. The multi-area coverage inspection system using drone clusters according to claim 7 is characterized in that: The specific analysis method of evaluating the highway risk coefficient level of each inspection area of ​​each inspection section and implementing response measures corresponding to the damage level of traffic signs in each inspection area of ​​each inspection section is as follows: Road damage risk index for each inspection area based on each inspection section , Risk Index of Traffic Signs , through the formula: , calculate the highway risk coefficient of each inspection area in each inspection section; like If the risk level is in the first interval of the expressway, The first inspection section The highway risk level in the inspection area is high, and the first-level highway risk response measures are implemented; like If the highway is in the second risk level interval, the The first inspection section The highway risk level in the inspection area is medium, and the second-level highway risk response measures are implemented; like If the highway is in the third risk level interval, the The first inspection section The risk level of the expressways in the inspection areas is low; The first-level response measure for highway risks is to send the inspection information from the pilot drones of each inspection section to the control center, which will display it in three dimensions and issue early warnings to highway maintenance personnel; The secondary response measures for highway risks are as follows: The first inspection section The next round of inspection level for each inspection area is set as a risk area.

9. A multi-area coverage inspection system using a drone cluster according to claim 8, characterized in that: The working state parameters of the inspection drones in each inspection area of ​​each inspection section are monitored, and if abnormal, abnormal working state response measures are executed. The specific analysis method is as follows: The pilot drone of each inspection section obtains the real-time power of the inspection drones in each inspection area it is responsible for The pilot drone of each inspection section sends a network test signal to the inspection drones of each inspection area it is responsible for, and obtains the response time of the inspection drones of each inspection area of ​​each inspection section. ; like or , then determine the The first inspection section The working status of the inspection drone in the inspection area is abnormal. The first inspection section The inspection area is recorded as an abnormal inspection area, and the abnormal response measures for the working status are implemented, among which Indicates the power threshold for normal operation of the inspection drone extracted from the database. Indicates the network response time of the normal operation of the inspection drone extracted from the database; The abnormal working state response measure refers to the pilot drone of the inspection section to which the abnormal inspection area belongs, screening the remaining power of the inspection drones of the inspection areas with a screening step of 1 on the left and right sides of the abnormal inspection area after the inspection is completed. If the power demand for the second inspection is met, the pilot drone of the inspection section sends a temporary inspection task to the inspection drones of the inspection area of ​​the abnormal inspection area to perform the inspection of the abnormal inspection area; If the power requirement of the second inspection is not met, the pilot drone of the inspection section increases the screening step size in sequence, and uses the screening step size to screen the remaining power of the inspection drones in the inspection areas on the left and right sides of the abnormal inspection area after the inspection is completed, and repeats the above operation; If the inspection drones in each inspection area of ​​the inspection section do not meet the power requirements of the secondary inspection, the pilot drone of the inspection section sends a work abnormality signal to the inspection control center, and the inspection control center wakes up the idle drones to perform temporary inspection tasks in the abnormal inspection areas of the inspection section.

10. The multi-area coverage inspection system using drone clusters according to claim 1, characterized in that: The specific analysis method of displaying the inspection data of each inspection area and the working status information of the drone is as follows: Based on the map of the highway in the inspection area, the divided inspection areas and the inspection drones, a 3D display model is generated through 3D modeling software to display the working status of the inspection drones in each inspection area of ​​each inspection section and the risk level of the highway; Based on the highway risk level of each inspection area in each inspection section, the color warning corresponding to each risk level is displayed in the 3D display model; Based on the working status parameters of the inspection drone in each inspection area of ​​each inspection section, the color warning corresponding to each abnormal working status parameter is displayed in the three-dimensional display model.

Images