Airborne camera equipment intelligent control method and system based on edge calculation

Abstract

The invention discloses an airborne camera equipment intelligent control method and system based on edge calculation, and relates to the field of unmanned aerial vehicle intelligent control, and the method comprises the steps: carrying out the self-inspection and initialization of an unmanned aerial vehicle after the unmanned aerial vehicle is started, and planning a flight path and a shooting point according to an inspection task issued by a control station; the unmanned aerial vehicle flies according to a planned path, airborne camera equipment starts to shoot, and an edge calculation unit processes image data in real time and performs fine identification and automatic focusing; a sensor loaded on the unmanned aerial vehicle senses the flight environment in real time, and an edge calculation unit adjusts camera parameters and flight attitudes according to sensed data; and after the inspection task is completed, the unmanned aerial vehicle automatically returns, and the ground control station analyzes and processes the collected data. By automatically planning a flight path and a shooting point, manual intervention is reduced, an edge calculation unit is introduced, automatic focusing and real-time adjustment of camera parameters can be realized according to image data and perception data, high-quality image acquisition is ensured, and secondary re-flight caused by inaccurate focus is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control of unmanned aerial vehicles, in particular to an intelligent control method and system for airborne camera devices based on edge computing. Background Art

[0002] With the continuous expansion and complexity of the power grid scale, the traditional manual inspection method has been difficult to meet the efficient, safe, and accurate operation and maintenance requirements of modern power grids. Unmanned aerial vehicles (UAVs), with their advantages of flexibility, high efficiency, and wide coverage, have shown great application potential in intelligent power grid inspections. By carrying devices such as high-definition cameras and infrared thermal imagers, UAVs can achieve close-range and all-round monitoring of power grid equipment, effectively improving the inspection efficiency and quality.

[0003] In recent years, with the rapid development of UAV technology, its application in the power grid field has shown a significant growth trend. More and more power grid enterprises have begun to use UAVs for daily inspections, fault troubleshooting, and emergency response, promoting the intelligence and modernization of power grid operation and maintenance.

[0004] Although UAVs have played an important role in power grid inspections, the existing intelligent control methods still have many drawbacks:

[0005] Strong dependence: Most of the existing methods rely on ground control stations for remote control, which have high requirements for the stability and real-time performance of the communication link. Once the communication is interrupted or delayed, the inspection effect will be directly affected.

[0006] Insufficient intelligence level: The existing methods have limited intelligence levels and are difficult to achieve autonomous decision-making and adaptive adjustment. There are many situations that require manual intervention, which affects the automation degree of inspections.

[0007] Limited data processing ability: A large amount of data generated during the inspection process by UAVs needs to be processed and analyzed in real time, but the existing methods have limited data processing ability and are difficult to meet the efficient and accurate operation and maintenance requirements.

[0008] In the current power grid operation and maintenance environment, using UAVs for intelligent inspections also faces the following difficulties:

[0009] Difficult to adapt to complex environments: Power grid equipment is often distributed in complex and changeable environments, such as mountainous areas and urban high-rise buildings. When UAVs fly and take pictures in these environments, they are easily affected by factors such as terrain and meteorology, resulting in unstable inspection effects.

[0010] Difficult to ensure safety and privacy protection: UAVs may involve sensitive areas and privacy information during flight. How to ensure flight safety and protect relevant privacy has become an urgent problem to be solved.

[0011] In view of the disadvantages of the above existing methods and the difficulties in the current environment, the present invention aims to provide an intelligent control method and system for airborne camera devices based on edge computing to solve the key problems in the intelligent inspection of unmanned aerial vehicles (UAVs) in the power grid field. By introducing edge computing technology, the present invention realizes the autonomous decision-making, adaptive adjustment, and efficient data processing of UAV airborne camera devices, effectively improving the intelligent, automated, and secure levels of power grid inspection. Summary of the Invention

[0012] In view of the above problems, the present invention is proposed.

[0013] Therefore, the problems to be solved by the present invention are as follows: The existing methods have limited intelligence levels, making it difficult to achieve autonomous decision-making and adaptive adjustment, and requiring a lot of manual intervention, which affects the degree of automation of inspection.

[0014] To solve the above technical problems, the present invention provides the following technical solution: An intelligent control method for airborne camera devices based on edge computing, which includes that after the UAV is started, it conducts self-check and initialization, and plans the flight path and shooting points according to the inspection task issued by the control station; the UAV flies according to the planned path, the airborne camera device starts shooting, and the edge computing unit processes the image data in real time for refined recognition and automatic focusing; the sensors loaded on the UAV sense the flight environment in real time, and the edge computing unit adjusts the camera parameters and flight attitude according to the sensed data; the processed data is transmitted to the ground control station in real time through the communication module and stored in the airborne storage device at the same time; after the inspection task is completed, the UAV automatically returns, and the ground control station analyzes and processes the collected data.

[0015] As a preferred solution of the intelligent control method for airborne camera devices based on edge computing according to the present invention, wherein: the self-check and initialization include that after the UAV is started, it conducts hardware self-check, software self-check, and security self-check; the objects of the hardware self-check include the UAV platform, the edge computing unit, the airborne camera device, the sensor module, and the communication module; the objects of the software self-check include the flight control system software, the edge computing software, the camera control software, and the data transmission software; the objects of the security self-check include flight safety inspection and data security inspection; after the inspection is error-free, loading the preset parameters and conducting initialization include system parameter initialization, software environment initialization, and communication link initialization.

[0016] As a preferred solution of the intelligent control method for airborne camera equipment based on edge computing according to the present invention, the following steps are included: The planned flight path and shooting points include dividing the inspection area into several sub-areas according to the power grid layout and equipment distribution, determining the sub-areas to be inspected according to the inspection tasks, analyzing the terrain features of the sub-areas to be inspected by using topographic maps and the data of the front-mounted sensors of the UAV, and using the path planning algorithm to generate the optimal flight path with the goal of avoiding high-risk areas. The high-risk areas include densely populated areas and high-voltage line intersections. The long path is divided into multiple short path segments, and the length of each path segment is determined according to the endurance of the UAV and the task requirements.

[0017] As a preferred solution of the intelligent control method for airborne camera equipment based on edge computing according to the present invention, the following steps are also included: Using the pre-loaded equipment database to identify the power grid equipment that needs to be inspected, determining the pre-shooting angle and pre-shooting distance of each power grid equipment according to the type of power grid equipment and the inspection requirements, marking the shooting points on the flight path according to the pre-shooting angle and pre-shooting distance, and planning the access order of the shooting points according to the importance of the equipment and the path sequence; Integrating the flight path and shooting points into a complete inspection task plan, including the take-off point, flight path, shooting points and landing point, and estimating the time required for the entire inspection task according to the flight speed of the UAV and the shooting time, ensuring that the required time is within the endurance range of the UAV.

[0018] As a preferred solution of the intelligent control method for airborne camera equipment based on edge computing according to the present invention, the following steps are included: When the UAV flies to the shooting point, the airborne camera equipment is activated, and image data is collected according to the pre-shooting angle, and the collected image data is transmitted to the edge computing unit through the communication module; The edge computing unit performs denoising, enhancement and correction processing on the image data, extracts the key feature points in the image by using the image processing algorithm, identifies and classifies the equipment in the image based on the pre-trained equipment recognition model, measures the distance between the power grid equipment and the UAV by using binocular vision, analyzes the shape of the identified equipment, and determines the specific structure and state of the power grid equipment; Based on the image clarity and the equipment recognition result, evaluate the current focusing state. If the current focusing state is not clear, calculate the focal length and camera position that need to be adjusted, and send the focusing adjustment instruction to the UAV. The UAV adjusts the flight attitude and camera focal length according to the received instruction to achieve automatic focusing.

[0019] As a preferred solution of the intelligent control method for the airborne camera device based on edge computing according to the present invention, wherein: the edge computing unit adjusts the camera parameters and flight attitude according to the perception data, including that the sensors loaded on the UAV collect the perception data in real time, including position information, attitude information, distance information and environmental information, and transmits the collected perception data to the edge computing unit through the communication module; after preprocessing the perception data, the edge computing unit analyzes the environmental light conditions and obstacle distribution, evaluates the impact of the current environment on shooting, analyzes the attitude information of the UAV, evaluates the impact of the current flight attitude on shooting, formulates a camera parameter adjustment strategy according to the environmental light conditions and shooting target, formulates a flight attitude adjustment strategy according to the attitude information of the UAV and shooting requirements, and sends the camera parameter adjustment strategy and flight attitude adjustment strategy to the UAV, and the UAV adjusts the camera parameters and attitude according to the received information.

[0020] As a preferred solution of the intelligent control method for the airborne camera device based on edge computing according to the present invention, wherein: the ground control station analyzes and processes the collected data, including that the ground control station analyzes the data collected by the UAV, judges the operation state of the power grid equipment, and formulates corresponding strategies according to the operation state.

[0021] Another object of the present invention is to provide an intelligent control system for an airborne camera device based on edge computing, which can realize the automatic cruise action of the UAV, collect data in real time, and can also automatically adjust the camera parameters and flight attitude according to the environmental data.

[0022] To solve the above technical problems, the present invention provides the following technical solutions: a system for an intelligent control method for an airborne camera device based on edge computing, including: a planning module, a communication module and an edge computing unit; the planning module plans the flight path and shooting points according to the inspection tasks issued by the control station; the communication module is used to construct data transmission between the UAV and the edge computing unit, and data transmission between the UAV and the ground control station; the edge computing unit processes the collected image data in real time, performs refined recognition and automatic focusing, and adjusts the camera parameters and flight attitude according to the collected perception data.

[0023] A computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the intelligent control method for the airborne camera device based on edge computing as described above are implemented.

[0024] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the intelligent control method for the airborne camera device based on edge computing as described above are implemented.

[0025] The beneficial effects of the present invention are as follows: The existing methods have limited intelligence level, making it difficult to achieve autonomous decision-making and adaptive adjustment, and requiring a lot of manual intervention, which affects the automation degree of inspection. The present invention reduces manual intervention by automatically planning flight paths and shooting points, significantly improving the efficiency of power grid inspection. Moreover, an edge computing unit is introduced, which can automatically focus and adjust camera parameters in real time according to image data and perception data, ensuring high-quality images can be obtained under different environmental conditions, guaranteeing the clarity of the shooting target, and avoiding secondary takeoff due to inaccurate focus.

[0026] The system of the present invention has the ability of autonomous decision-making and can intelligently adjust the shooting strategy and flight attitude according to real-time data, improving the intelligent inspection level. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0028] Figure 1 It is a flowchart of the intelligent control method for airborne camera equipment based on edge computing in Embodiment 1.

[0029] Figure 2 It is a module structure diagram of the intelligent control system for airborne camera equipment based on edge computing in Embodiment 2. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0031] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0032] Embodiment 1, referring to Figure 1 and, is the first embodiment of the present invention. This embodiment provides an intelligent control method for airborne camera equipment based on edge computing, including, as Figure 1 shown:

[0033] S1. After the drone is started, it performs self-check and initialization, and plans the flight path and shooting points according to the inspection task issued by the control station.

[0034] After the drone is started, it performs hardware self-check, software self-check, and safety self-check.

[0035] The objects of hardware self-check include:

[0036] Drone platform: Check the status of key components such as propellers, batteries, motors, and flight control systems to ensure that the drone has the ability to fly.

[0037] Edge computing unit: Detect whether hardware such as processors, memory, and storage devices is working properly to ensure data processing capabilities.

[0038] Onboard camera equipment: Check components such as lenses, sensors, and memory cards to ensure that the camera can take pictures normally.

[0039] Sensor module: Calibrate sensors such as GPS, IMU, and lidar to ensure accurate environmental perception.

[0040] Communication module: Test wireless communication devices to ensure smooth data transmission.

[0041] The objects of software self-check include:

[0042] Flight control system software: Check whether software such as flight control algorithms and navigation systems is running properly.

[0043] Edge computing software: Verify whether algorithm libraries and software frameworks such as image processing, computer vision, and deep learning are ready.

[0044] Camera control software: Ensure that software functions such as camera parameter adjustment and autofocus are normal.

[0045] Data transmission software: Check whether software modules such as data compression, encryption, and transmission are working properly.

[0046] The objects of safety self-check include:

[0047] Flight safety check: Ensure that the drone is in a safe area and there are no flight obstacles.

[0048] Data security check: Verify the security mechanisms for data storage and transmission to prevent data leakage or damage.

[0049] After the checks are completed without errors, load the preset parameters and perform initialization, including system parameter initialization, software environment initialization, and communication link initialization.

[0050] According to the power grid layout and equipment distribution, the inspection area is divided into several sub-areas. The sub-areas to be inspected are determined according to the inspection tasks. Using topographic maps and pre-flight sensor data of the unmanned aerial vehicle (UAV), the topographic features of the sub-areas to be inspected are analyzed, such as height, slope, obstacles, etc. Using path planning algorithms (such as A* algorithm, Dijkstra algorithm, etc.), an optimal flight path is generated with the goal of avoiding high-risk areas. High-risk areas include densely populated areas and high-voltage line intersections. The long path is divided into multiple short path segments, and the length of each path segment is determined according to the UAV's endurance and task requirements.

[0051] Using a pre-loaded equipment database, the power grid equipment to be inspected is identified, such as transmission towers, transformers, insulators, etc. According to the type of power grid equipment and inspection requirements, the pre-shooting angles and pre-shooting distances for each power grid equipment are determined. Shooting points are marked on the flight path according to the pre-shooting angles and pre-shooting distances. According to the importance of the equipment and the path sequence, the access sequence of the shooting points is planned.

[0052] The flight path and shooting points are integrated into a complete inspection task plan, including the take-off point, flight path, shooting points, and landing point. According to the UAV's flight speed and shooting time, the time required for the entire inspection task is estimated to ensure that the required time is within the UAV's endurance range.

[0053] An emergency plan is formulated so that in case of emergencies (such as bad weather, equipment failures, etc.), the flight path and shooting points can be quickly adjusted.

[0054] S2. The UAV flies according to the planned path, and the on-board camera equipment starts shooting. The edge computing unit processes the image data in real time for refined recognition and autofocus.

[0055] When the UAV flies to the shooting point, the on-board camera equipment is activated, and image data is collected according to the pre-shooting angle. The collected image data is transmitted to the edge computing unit through the communication module.

[0056] The edge computing unit preprocesses the image data, including image denoising: denoising the image data to reduce environmental interference and equipment noise.

[0057] Image enhancement: enhancing the image to improve contrast and clarity for subsequent recognition.

[0058] Image correction: performing geometric correction and color correction on the image to ensure the accuracy and consistency of the image.

[0059] Extract key feature points in the image using image processing algorithms (such as SIFT, SURF, ORB, etc.), identify and classify the devices in the image based on a pre-trained device recognition model, measure the distance between the power grid device and the UAV using binocular vision, perform shape analysis on the identified devices, and determine the specific structure and status of the power grid device.

[0060] Based on the image clarity and device recognition results, evaluate the current focus state. If the current focus state is unclear, calculate the focal length and camera position that need to be adjusted, send the focus adjustment command to the UAV, and the UAV adjusts its flight attitude and camera focal length according to the received command to achieve automatic focus. Feed back the results of refined recognition and automatic focus to the ground control station for real-time monitoring by the operator.

[0061] S3. The sensors loaded on the UAV continuously sense the flight environment, and the edge computing unit adjusts the camera parameters and flight attitude according to the sensed data.

[0062] The sensors loaded on the UAV continuously collect sensed data, including position information, attitude information, distance information, and environmental information, and transmit the collected sensed data to the edge computing unit through the communication module.

[0063] After preprocessing the sensed data, the edge computing unit analyzes the environmental light conditions and obstacle distribution, evaluates the impact of the current environment on shooting, analyzes the attitude information of the UAV, evaluates the impact of the current flight attitude on shooting, formulates a camera parameter adjustment strategy according to the environmental light conditions and shooting target, such as exposure, shutter speed, ISO, white balance, etc., formulates a flight attitude adjustment strategy according to the attitude information of the UAV and shooting requirements, such as pitch, roll, yaw, etc., and sends the camera parameter adjustment strategy and flight attitude adjustment strategy to the UAV, and the UAV adjusts the camera parameters and attitude according to the received information.

[0064] S4. The processed data is transmitted to the ground control station in real time through the communication module and stored in the on-board storage device at the same time.

[0065] S5. After completing the inspection task, the UAV automatically returns, and the ground control station analyzes and processes the collected data.

[0066] The ground control station analyzes the data collected by the UAV, judges the operating state of the power grid device, and formulates corresponding strategies according to the operating state.

[0067] Example 2, refer to Figure 2, which is the second embodiment of the present invention and is different from the first embodiment: A system for an intelligent control method of an airborne camera device based on edge computing includes a planning module 100, a communication module 200, and an edge computing unit 300; the planning module 100 plans a flight path and shooting points according to the inspection task issued by the control station; the communication module 200 is used to establish data transmission between the drone and the edge computing unit 300, and data transmission between the drone and the ground control station; the edge computing unit 300 processes the collected image data in real time, performs refined recognition and autofocus, and adjusts the camera parameters and flight attitude according to the collected perception data.

[0068] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0069] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0070] More specific examples (a non-exhaustive list) of computer-readable media include the following: electrical connections (electronic devices) having one or more wirings, portable computer diskettes (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0071] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0072] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An intelligent control method for airborne camera equipment based on edge computing, characterized in that: include, After the drone is started, it will perform self-check and initialization, and plan the flight path and shooting points according to the inspection tasks issued by the control station; The drone flies according to the planned path, the onboard camera starts shooting, and the edge computing unit processes the image data in real time for refined recognition and autofocus. The sensors on the drone sense the flight environment in real time, and the edge computing unit adjusts the camera parameters and flight attitude based on the sensed data; The processed data is transmitted to the ground control station in real time through the communication module and stored in the onboard storage device; After completing the inspection mission, the drone automatically returns, and the ground control station analyzes and processes the collected data.

2. The method for intelligently controlling an airborne camera device based on edge computing according to claim 1, characterized in that: The self-check and initialization include hardware self-check, software self-check and safety self-check after the UAV is started; The objects of the hardware self-test include the drone platform, edge computing unit, airborne camera device, sensor module and communication module; The objects of the software self-check include flight control system software, edge computing software, camera control software and data transmission software; The objects of the safety self-inspection include flight safety inspection and data safety inspection; After checking that everything is correct, load the preset parameters and perform initialization, including system parameter initialization, software environment initialization, and communication link initialization.

3. The method for intelligently controlling an airborne camera device based on edge computing according to claim 2, characterized in that: The planning of flight paths and shooting points includes dividing the inspection area into several sub-areas according to the grid layout and equipment distribution, determining the sub-areas to be inspected according to the inspection tasks, analyzing the terrain characteristics of the sub-areas to be inspected using topographic maps and drone front sensor data, and using a path planning algorithm to generate an optimal flight path with the goal of avoiding high-risk areas, which include densely populated areas and intersections of high-voltage lines. A long path is divided into multiple short path segments, and the length of each path segment is determined based on the drone's endurance and mission requirements.

4. The method for intelligently controlling an airborne camera device based on edge computing according to claim 3, characterized in that: The planning of the flight path and shooting points also includes, using a pre-loaded equipment database, identifying power grid equipment that needs to be inspected, determining a pre-shooting angle and a pre-shooting distance for each power grid equipment according to the type of power grid equipment and the inspection requirements, marking shooting points on the flight path according to the pre-shooting angle and the pre-shooting distance, and planning a visit order of the shooting points according to the importance of the equipment and the order of the path; Integrate the flight path and shooting points into a complete inspection mission plan, including the take-off point, flight path, shooting point and landing point. Estimate the time required for the entire inspection mission based on the drone's flight speed and shooting time to ensure that the required time is within the drone's flight range.

5. The method for intelligently controlling an airborne camera device based on edge computing according to claim 4, characterized in that: The refined recognition and automatic focusing include: when the drone flies to the shooting point, the onboard camera device is started, image data is collected according to the pre-shooting angle, and the collected image data is transmitted to the edge computing unit through the communication module; The edge computing unit performs denoising, enhancement and correction processing on the image data, uses image processing algorithms to extract key feature points in the image, identifies and classifies the devices in the image based on the pre-trained device recognition model, uses binocular vision to measure the distance between the power grid equipment and the drone, performs shape analysis on the identified equipment, and determines the specific structure and status of the power grid equipment; Based on the image clarity and device recognition results, the current focus state is evaluated. If the current focus state is not clear, the focal length and camera position that need to be adjusted are calculated, and the focus adjustment command is sent to the drone. The drone adjusts the flight attitude and camera focal length according to the received command to achieve automatic focus.

6. The method for intelligently controlling an airborne camera device based on edge computing according to claim 5, characterized in that: The edge computing unit adjusts the camera parameters and flight attitude according to the perception data, including that the sensors mounted on the drone collect perception data in real time, including position information, attitude information, distance information and environmental information, and transmits the collected perception data to the edge computing unit through the communication module; After preprocessing the perception data, the edge computing unit analyzes the ambient lighting conditions and obstacle distribution, evaluates the impact of the current environment on shooting, analyzes the drone's attitude information, evaluates the impact of the current flight attitude on shooting, and formulates a camera parameter adjustment strategy based on the ambient lighting conditions and shooting targets. According to the drone's attitude information and shooting requirements, a flight attitude adjustment strategy is formulated, and the camera parameter adjustment strategy and flight attitude adjustment strategy are sent to the drone. The drone adjusts the camera parameters and attitude based on the received information.

7. The method for intelligently controlling an airborne camera device based on edge computing according to claim 6, characterized in that: The ground control station analyzes and processes the collected data, including analyzing the data collected by the drone, determining the operating status of the power grid equipment, and formulating corresponding strategies based on the operating status.

8. A system using the airborne camera device intelligent control method based on edge computing as claimed in any one of claims 1 to 7, characterized in that: It comprises a planning module (100), a communication module (200) and an edge computing unit (300); The planning module (100) plans the flight path and shooting points according to the inspection tasks issued by the control station; The communication module (200) is used to establish data transmission between the drone and the edge computing unit (300), and data transmission between the drone and the ground control station; The edge computing unit (300) processes the collected image data in real time, performs refined recognition and automatic focusing, and adjusts camera parameters and flight attitude according to the collected perception data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligent control of an airborne camera device based on edge computing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent control of an airborne camera device based on edge computing described in any one of claims 1 to 7 are implemented.

Images