Unmanned aerial vehicle patrol survey method and device

Abstract

The invention provides an unmanned aerial vehicle patrol method and device, and relates to the technical field of unmanned aerial vehicles. The method comprises the following steps: acquiring disaster monitoring and early warning results of monitoring equipment and a disaster monitoring and early warning information system arranged in each patrolling and monitoring area; the disaster monitoring and early warning result is that no disaster early warning occurs or disaster early warning occurs; determining an unmanned aerial vehicle patrol plan based on the disaster monitoring and early warning result; acquiring acquisition data obtained by patrolling according to the unmanned aerial vehicle patrolling plan; inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; and determining a patrol result based on the identification result. According to the unmanned aerial vehicle patrol method and device provided by the invention, the unmanned aerial vehicle patrol efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and in particular to a drone inspection method and device. Background Art

[0002] Traditional drone inspections require people to carry drones and collect data in designated areas regularly. After the data is collected, the data is processed, analyzed and compared manually. This method has many disadvantages, which are as follows: ① Low degree of automation: each process requires human participation; ② Low efficiency: people need to take drones to various points to collect data, and a lot of time is wasted on the road; ③ Poor timeliness: when disaster warnings occur, it is often impossible to arrive at the scene in time for data collection, thus missing the best data collection time; ④ High risk: people need to be active frequently in places where disasters may occur, which is more dangerous.

[0003] Therefore, it is urgent to propose a new UAV inspection method. Summary of the invention

[0004] The present application provides a drone inspection method and device to solve the defects of drone inspection in the prior art, such as low automation, low efficiency, poor timeliness and high risk.

[0005] In a first aspect, the present application provides a drone inspection method, comprising: Obtaining disaster monitoring and early warning results of monitoring equipment and disaster monitoring and early warning information systems deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; Determine the drone inspection plan based on the disaster monitoring and early warning results; Acquire collected data obtained by patrolling according to the drone patrol plan; Inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; Based on the identification result, a patrol result is determined.

[0006] Optionally, determining a drone inspection plan based on the disaster monitoring and early warning results includes: In the absence of a disaster warning, the drone inspection plan is determined to be a first inspection plan; the first inspection plan is to inspect each inspection area according to a preset inspection cycle; In the event of a disaster warning, the drone patrol plan is determined to be a second patrol plan; the second patrol plan is different from the first patrol plan in terms of the number of patrols, unmanned flight altitude and route density.

[0007] Optionally, the recognition model is constructed based on the YOLOv8 algorithm; The recognition model includes: A preprocessing module, used for preprocessing the collected data to obtain processed data; A data labeling module, used to label the processed data to obtain labeled data; A data enhancement module, used to perform data enhancement on the labeled data to obtain enhanced data; The recognition module is used to perform data recognition on the enhanced data to obtain the recognition result.

[0008] Optionally, the data enhancement module is specifically used to: Performing data enhancement on the labeled data by randomly flipping, randomly cropping, and increasing brightness; The identification module is specifically used for: Data recognition is performed on the enhanced data based on an anchor frame of a preset size and a detection head of a preset size.

[0009] Optionally, the recognition model is trained in the following manner: The historical collected data is used as a sample, and the recognition results corresponding to the historical collected data are used as labels to train the initial model to obtain the recognition model.

[0010] Optionally, the method further comprises: Each patrol area is determined based on the drone's flight conditions and the distance between each area and the drone hangar.

[0011] In a second aspect, the present application also provides a drone inspection device, comprising: The first acquisition module is used to obtain the disaster monitoring and early warning results of the monitoring equipment and the disaster monitoring and early warning information system deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; A first determination module is used to determine a drone inspection plan based on the disaster monitoring and early warning results; A second acquisition module is used to acquire collected data obtained by patrolling according to the drone patrol plan; A recognition module, used for inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; The second determination module is used to determine the patrol result based on the identification result.

[0012] In a third aspect, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0013] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0014] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0015] The drone inspection method and device provided in this application automatically controls the drone to inspect the warning area by processing geological disaster monitoring and early warning information and combining the monitoring results of the drone flight environment. This method combines the terrain information of the warning area and adopts an automatic route planning algorithm to realize automatic take-off, autonomous flight, automatic landing and intelligent charging of the drone. The camera carried by the drone automatically collects image data of the warning area and transmits it back to the server through the data link. The three-dimensional reconstruction algorithm and artificial intelligence recognition algorithm are used to compare and analyze the data. This method combines geological disaster monitoring and early warning technology, drone technology and data processing technology, which can realize rapid positioning, rapid collection and rapid processing of the warning area, and improve the efficiency and accuracy of inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a flowchart of the drone inspection method provided by this application; Figure 2 It is a structural schematic diagram of the UAV patrol device provided by this application; Figure 3 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] Figure 1 Schematic diagram of the process of the drone inspection method provided by this application. Figure 1 The embodiment of the present application provides a drone inspection method, the execution subject of which may be an electronic device, for example, a controller, and the method may include: Step 110: Obtain disaster monitoring and early warning results of the monitoring equipment and disaster monitoring and early warning information system deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; Step 120: Determine a drone inspection plan based on the disaster monitoring and early warning results; Step 130: Acquire the collected data obtained by patrolling according to the drone patrol plan; Step 140: input the collected data into the recognition model to obtain the recognition result output by the recognition model; Step 150: Determine the inspection result based on the identification result.

[0020] In step 110, a drone hangar can be set up in a designated area, the area around the hangar can be divided into geological disaster areas (various patrol areas), and supporting monitoring equipment and disaster monitoring and early warning information systems can be placed. The controller can obtain the disaster monitoring and early warning results and determine whether a disaster warning occurs.

[0021] In step 120, whether a disaster warning affects the patrol logic of the drone is determined. For example, in the case of a disaster warning, it is necessary to increase the patrol intensity of the disaster warning area.

[0022] In step 130, the controller may obtain the collected data obtained by patrolling according to the drone patrol plan. Specifically, the controller may automatically collect image data of the warning area through the camera carried by the drone. Then, the controller may use a three-dimensional reconstruction algorithm, an artificial intelligence (AI) recognition algorithm, etc. to compare and analyze the collected data. Through the three-dimensional reconstruction algorithm, multi-period three-dimensional model data can be generated, and data from different periods can be compared.

[0023] In step 140, the controller may input the collected data into the recognition model to obtain the recognition result output by the recognition model. The recognition result may include the types of land features such as houses, water areas, cracks, landslides, etc.

[0024] In step 150, the controller may organize and summarize the identification results to form a patrol report, that is, the final patrol result.

[0025] The drone inspection method provided in the embodiment of the present application processes geological disaster monitoring and early warning information, combines the monitoring results of the drone flight environment to make judgments, and automatically controls the drone to inspect the warning area. This method combines the terrain information of the warning area and adopts an automatic route planning algorithm to realize automatic take-off, autonomous flight, automatic landing and intelligent charging of the drone. The camera carried by the drone automatically collects image data of the warning area and transmits it back to the server through the data link. The three-dimensional reconstruction algorithm and artificial intelligence recognition algorithm are used to compare and analyze the data. This method combines geological disaster monitoring and early warning technology, drone technology and data processing technology, and can realize rapid positioning, rapid collection and rapid processing of the warning area, thereby improving the efficiency and accuracy of inspections.

[0026] In one embodiment, based on the disaster monitoring and early warning results, determining a drone inspection plan includes: In the absence of a disaster warning, the drone inspection plan is determined as the first inspection plan; The first inspection plan is to inspect each inspection area according to the preset inspection cycle; In the event of a disaster warning, the drone patrol plan is determined as the second patrol plan; the second patrol plan is different from the first patrol plan in terms of the number of patrols, unmanned flight altitude and route density.

[0027] In the absence of a disaster warning, drone inspections can be conducted regularly (i.e., according to the preset inspection cycle) in each inspection area. In the event of a disaster warning, it is necessary to increase the inspection efforts in the disaster warning area. When drones inspect according to the second inspection plan, the number of inspections can be increased to collect more data for comparison, or the drone's flight altitude can be lowered and the route density can be increased to collect more detailed data.

[0028] The drone inspection method provided in the embodiment of the present application processes geological disaster monitoring and early warning information, combines the monitoring results of the drone flight environment to make a judgment, and uses early warning triggering and timing triggering to automatically control the drone to inspect the warning area. This method combines geological disaster monitoring and early warning technology, drone technology, and data processing technology, and can achieve rapid positioning, rapid collection, and rapid processing of the warning area, thereby improving inspection efficiency and accuracy.

[0029] In one embodiment, the recognition model is built based on the YOLOv8 algorithm; The recognition models include: A preprocessing module is used to preprocess the collected data to obtain processed data; A data labeling module is used to label the processed data to obtain labeled data; A data enhancement module is used to enhance the labeled data to obtain enhanced data; The recognition module is used to perform data recognition on the enhanced data to obtain a recognition result.

[0030] Furthermore, in one embodiment, the data enhancement module is specifically used to: Data augmentation is performed on the labeled data by random flipping, random cropping, and brightness enhancement. The identification module is specifically used for: The enhanced data is recognized based on an anchor frame of a preset size and a detection head of a preset size.

[0031] The recognition model is built based on the YOLOv8 algorithm, which uses AI recognition technology to perform real-time detection on video data of drones in real-time flight: the server obtains the real-time live stream, and after processing by the AI ​​recognition algorithm, it outputs the video screen with the recognition results for visual display; it can also perform large-scale recognition of orthophotos, such as: using the sliding window cropping method to recognize orthophotos of any size, and can identify objects with smaller resolution.

[0032] The controller inputs the collected data from the drone inspection into the recognition model. The preprocessing module of the recognition model can preprocess the collected data. Preprocessing can include: data cleaning: removing or correcting noise, outliers and erroneous data in the collected data; missing value processing: filling or deleting missing data to reduce the impact on subsequent analysis; data standardization: converting data into a unified format and dimension for subsequent processing and analysis.

[0033] The data labeling module can perform target labeling on the processed data through labeling software, such as labeling houses, water areas, etc., to obtain labeled data.

[0034] The data enhancement module can enhance data through random flipping, random cropping, increasing brightness and other data enhancement methods to enrich the diversity of data.

[0035] The recognition module is used for data recognition. In order to effectively detect small targets, a smaller anchor frame and a smaller detection head can be added to the recognition module, so that features of smaller pixels can be extracted and the detection probability of small targets can be increased.

[0036] The drone patrol method provided in the embodiment of the present application identifies the collected data through a recognition model to obtain a recognition result, and then analyzes the patrol result, which can achieve rapid positioning, rapid collection and rapid processing of the warning area, improve patrol efficiency and accuracy, and reduce safety risks.

[0037] In one embodiment, the recognition model is trained as follows: The historically collected data is used as samples, and the recognition results corresponding to the historically collected data are used as labels to train the initial model and obtain the recognition model.

[0038] You can use historically collected data samples and the recognition result labels corresponding to the historically collected data, obtain the initial model through iterative training, test it on unknown images to check the recognition effect, and tune the model based on the results. After reaching the preset number of training times or meeting the accuracy requirements, you can obtain the recognition model.

[0039] The drone inspection method provided in the embodiment of the present application obtains a recognition model by training the initial model, which can improve the recognition efficiency and accuracy of the recognition model and improve the robustness of the model.

[0040] In one embodiment, the drone inspection method further includes: Each patrol area is determined based on the drone's flight conditions and the distance of each area from the drone hangar.

[0041] The division of drone inspection areas and planning of inspection routes are automatically calculated through the drone’s flight time, battery power, and flight distance. The total flight distance of the drone is calculated based on the distance from the drone hangar, and the drone inspection routes are planned accordingly, thereby dividing the drone inspection areas.

[0042] The drone inspection method provided in the embodiment of the present application processes geological disaster monitoring and early warning information, combines the monitoring results of the drone flight environment to make judgments, and automatically controls the drone to inspect the warning area. This method combines the terrain information of the warning area and adopts an automatic route planning algorithm to realize automatic take-off, autonomous flight, automatic landing and intelligent charging of the drone. The camera carried by the drone automatically collects image data of the warning area and transmits it back to the server through the data link. The three-dimensional reconstruction algorithm and artificial intelligence recognition algorithm are used to compare and analyze the data. This method combines geological disaster monitoring and early warning technology, drone technology and data processing technology, and can realize rapid positioning, rapid collection and rapid processing of the warning area, thereby improving the efficiency and accuracy of inspections.

[0043] The drone inspection method provided by this application also has the following advantages: High degree of automation: The drone automatically collects data, automatically adjusts the data collection plan according to the early warning situation, and automatically transmits the collected data back for processing; High efficiency: Data is automatically collected according to the early warning situation, and automatically transmitted and processed after collection, completing the entire process quickly; Good timeliness: When a disaster warning occurs, the drone responds quickly and enters the disaster warning area to collect data as soon as possible, without missing the best data collection time; Low risk: Except for equipment installation and regular maintenance, no one is required to enter the site.

[0044] The drone inspection device provided in the present application is described below. The drone inspection device described below and the drone inspection method described above can be referenced to each other.

[0045] Figure 2 Schematic diagram of the structure of the drone inspection device provided by this application. Figure 2 The drone inspection device provided in the embodiment of the present application may include: The first acquisition module 210 is used to obtain the disaster monitoring and early warning results of the monitoring equipment and the disaster monitoring and early warning information system deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; A first determination module 220 is used to determine a drone inspection plan based on the disaster monitoring and early warning results; The second acquisition module 230 is used to acquire the collected data obtained by patrolling according to the drone patrol plan; The recognition module 240 is used to input the collected data into the recognition model to obtain the recognition result output by the recognition model; The second determination module 250 is used to determine the patrol result based on the identification result.

[0046] The drone inspection device provided in the embodiment of the present application processes geological disaster monitoring and early warning information, combines the monitoring results of the drone flight environment to make judgments, and automatically controls the drone to inspect the early warning area. The method combines the terrain information of the early warning area and adopts an automatic route planning algorithm to realize automatic take-off, autonomous flight, automatic landing and intelligent charging of the drone. The camera carried by the drone automatically collects image data of the early warning area and transmits it back to the server through the data link. The three-dimensional reconstruction algorithm and artificial intelligence recognition algorithm are used to compare and analyze the data. The method combines geological disaster monitoring and early warning technology, drone technology and data processing technology, and can realize rapid positioning, rapid collection and rapid processing of the early warning area, thereby improving the efficiency and accuracy of inspections.

[0047] Specifically, the above-mentioned drone patrol device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the above-mentioned execution subject is the controller, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0048] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the drone inspection method, which includes: Obtaining disaster monitoring and early warning results of monitoring equipment and disaster monitoring and early warning information systems deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; Determine the drone inspection plan based on the disaster monitoring and early warning results; Acquire collected data obtained by patrolling according to the drone patrol plan; Inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; Based on the identification result, a patrol result is determined.

[0049] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0050] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the drone inspection method provided by the above methods, the method includes: Obtaining disaster monitoring and early warning results of monitoring equipment and disaster monitoring and early warning information systems deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; Determine the drone inspection plan based on the disaster monitoring and early warning results; Acquire collected data obtained by patrolling according to the drone patrol plan; Inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; Based on the identification result, a patrol result is determined.

[0051] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the drone inspection method provided by the above methods, the method comprising: Obtaining disaster monitoring and early warning results of monitoring equipment and disaster monitoring and early warning information systems deployed in each patrol area; the disaster monitoring and early warning results are no disaster warning and disaster warning; Determine the drone inspection plan based on the disaster monitoring and early warning results; Acquire collected data obtained by patrolling according to the drone patrol plan; Inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; Based on the identification result, a patrol result is determined.

[0052] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0053] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0054] It should also be noted that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0055] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0056] "Determine B based on A" in the embodiments of the present application means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "Determine B based on A and C", "Determine B based on A, C and E", "Determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "When A meets the first condition, use the first method to determine B"; for another example, "When A meets the second condition, determine B", etc.; for another example, "When A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "When A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0057] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A drone inspection method, characterized in that: include: Obtain disaster monitoring and early warning results from monitoring equipment and disaster monitoring and early warning information systems deployed in each patrol area; The disaster monitoring and early warning results are: no disaster warning or disaster warning; Determine the drone inspection plan based on the disaster monitoring and early warning results; Acquire collected data obtained by patrolling according to the drone patrol plan; Inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; Based on the identification result, a patrol result is determined.

2. The drone inspection method according to claim 1, characterized in that: Determining a drone inspection plan based on the disaster monitoring and early warning results includes: In the absence of a disaster warning, the drone inspection plan is determined to be a first inspection plan; the first inspection plan is to inspect each inspection area according to a preset inspection cycle; In the event of a disaster warning, the drone patrol plan is determined to be a second patrol plan; the second patrol plan is different from the first patrol plan in terms of the number of patrols, unmanned flight altitude and route density.

3. The drone inspection method according to claim 1, characterized in that: The recognition model is built based on the YOLOv8 algorithm; The recognition model includes: A preprocessing module, used for preprocessing the collected data to obtain processed data; A data labeling module, used to label the processed data to obtain labeled data; A data enhancement module, used to perform data enhancement on the labeled data to obtain enhanced data; The recognition module is used to perform data recognition on the enhanced data to obtain the recognition result.

4. The drone inspection method according to claim 3, characterized in that: The data enhancement module is specifically used for: Performing data enhancement on the labeled data by randomly flipping, randomly cropping, and increasing brightness; The identification module is specifically used for: Data recognition is performed on the enhanced data based on an anchor frame of a preset size and a detection head of a preset size.

5. The drone inspection method according to claim 3, characterized in that: The recognition model is trained in the following way: The historical collected data is used as a sample, and the recognition results corresponding to the historical collected data are used as labels to train the initial model to obtain the recognition model.

6. The drone inspection method according to claim 1, characterized in that: The method further comprises: Each patrol area is determined based on the drone's flight conditions and the distance between each area and the drone hangar.

7. A drone inspection device, characterized in that: include: The first acquisition module is used to obtain the disaster monitoring and early warning results of the monitoring equipment and disaster monitoring and early warning information system deployed in each patrol area; The disaster monitoring and early warning results are: no disaster warning or disaster warning; A first determination module is used to determine a drone inspection plan based on the disaster monitoring and early warning results; A second acquisition module is used to acquire collected data obtained by patrolling according to the drone patrol plan; A recognition module, used for inputting the collected data into a recognition model to obtain a recognition result output by the recognition model; The second determination module is used to determine the patrol result based on the identification result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the drone inspection method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the drone inspection method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the drone inspection method according to any one of claims 1 to 6 is implemented.

Images