Intelligent inspection data acquisition system

Abstract

The invention relates to the technical field of electric power inspection, in particular to an intelligent inspection data acquisition system, which comprises a route planning module for generating a flight path diagram based on the position of an electric power line; the unmanned aerial vehicle module is used for adopting an unmanned aerial vehicle to fly based on the flight path diagram; the line data acquisition module is used for being installed on the unmanned aerial vehicle module to capture line images of the power line and the surrounding environment thereof; the GPS positioning module is used for recording geographic position information in real time during line image acquisition; the image blurring detection module is used for automatically marking an image blurring area on the image by using GPS positioning data and an image analysis technology to obtain a blurred image and corresponding geographical location information; and the rechecking module is used for recollecting the corresponding line image based on the geographic position information corresponding to the blurred image. Therefore, the power line data can be collected more accurately, the labor burden is reduced, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power inspection, and in particular to an intelligent inspection data acquisition system. Background Art

[0002] Manual inspection, as the most traditional method in the field of power line monitoring, relies on experienced line inspectors to conduct field surveys. These line inspectors either walk through rugged wild environments or drive along the lines. During this process, they need to use their keen observation and professional knowledge to directly check the status of key components such as wires, towers, insulators, etc. with their naked eyes to ensure that there are no damage, corrosion, vegetation intrusion or other hidden dangers that may affect the safety of power transmission. Line inspectors also need to manually record the problems they find, including location information, description of the degree of damage, and possible maintenance suggestions, and then organize and report these data so that relevant departments can arrange maintenance work.

[0003] However, the limitations of manual inspection methods cannot be ignored. First, from the perspective of efficiency, due to its complete reliance on manual labor, its coverage and speed are greatly limited. For long-distance, multi-branch power grid systems, completing a comprehensive inspection is often time-consuming and laborious. Secondly, in the face of complex terrain such as areas surrounded by mountains, dense forests or waters, as well as extreme climatic conditions such as heavy rain, heavy snow, high temperatures and other severe weather, manual inspections are not only much more difficult, but may also endanger the personal safety of line inspectors. In addition, purely manual inspection methods are difficult to meet high-precision requirements, and some minor damage or potential risks may be missed due to visual blind spots or human negligence, affecting the accuracy and reliability of inspections. Therefore, although manual inspections have certain advantages in intuitiveness and flexibility, in the face of the demand for efficient, safe and intelligent management of modern power systems, its limitations have prompted the industry to continuously explore and adopt more advanced and automated inspection methods. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent inspection data acquisition system to solve the problems existing in the prior art.

[0006] (II) Technical solution

[0007] The purpose of the present invention is to provide an intelligent inspection data collection system, which aims to collect power line data more accurately, reduce manual burden and improve work efficiency.

[0008] To achieve the above-mentioned purpose, the present invention provides an intelligent inspection data acquisition system, including a route planning module, a drone module, a line data acquisition module, a GPS positioning module, an image blur detection module and a re-inspection module; the route planning module is used to generate a flight path map based on the position of the power line; the drone module is used to use the drone to fly based on the flight path map; the line data acquisition module is used to be installed on the drone module to capture the line image of the power line and its surrounding environment; the GPS positioning module is used to record the geographical location information when the line image is collected in real time; the image blur detection module is used to use GPS positioning data and image analysis technology to automatically mark the image blur area on the image, and obtain the blurred image and the corresponding geographical location information; the re-inspection module is used to re-collect the corresponding line image based on the geographical location information corresponding to the blurred image.

[0009] Among them, the intelligent inspection data collection system also includes a preliminary fault detection module, and the preliminary fault detection module is used to perform preliminary fault detection on the collected images.

[0010] Among them, the route planning module includes a line information acquisition unit, a map data acquisition unit, a path generation unit, and a path optimization unit; the line information acquisition unit is used to collect geographic information of power lines; the map data acquisition unit is used to collect map data of inspection areas; the path generation unit is used to generate multiple candidate flight paths on a digital map according to the location of power lines; the path optimization unit is used to select the preliminarily planned flight path using a particle swarm optimization algorithm to obtain a flight path map.

[0011] The specific steps of using the particle swarm optimization algorithm to optimize the preliminarily planned flight path and obtain the flight path diagram include: setting the number and initial parameters of the particle swarm; setting a fitness function to evaluate the position of each particle; using an evaluation function to calculate the fitness value of each particle; for each particle, comparing its fitness value with its historical best fitness value, and if the current fitness is better, updating the individual best position; updating the speed of each particle according to the current speed, the individual best position and the global best position; using the updated speed to adjust the position of the particle to generate a flight path diagram.

[0012] Among them, the line data acquisition module includes a camera unit, an environmental parameter acquisition unit and an infrared imaging unit; the camera unit is used to automatically adjust the focal length according to the flight altitude and target distance to ensure high definition of the image; the environmental parameter acquisition unit is used to monitor environmental parameters during flight; the infrared imaging unit is used to capture thermal imaging information of the power line.

[0013] Among them, the camera unit includes a focal length setting subunit, a flight parameter acquisition subunit and a matching subunit; the focal length setting subunit is used to determine the ideal focal length range under different flight altitudes and target distances, and obtain a focal length adjustment mechanism; the flight parameter acquisition subunit is used to use the flight control system of the unmanned aerial vehicle to detect the flight altitude and target distance in real time; the matching subunit is used to calculate the required focal length according to the flight altitude and target distance detected in real time using the designed focal length adjustment mechanism.

[0014] Among them, the image blur detection module includes an association unit, an analysis unit and a marking unit; the association unit is used to synchronize the GPS positioning system of the drone with the image acquisition system so that each route image is associated with the corresponding geographic location data; the analysis unit is used to analyze the collected route images using a frequency domain analysis method to evaluate the clarity of each area in the image; the marking unit is used to automatically mark the detected blurred area on the image.

[0015] Among them, the specific steps of using the frequency domain analysis method to analyze the collected line image and evaluate the clarity of each area in the image include: denoising the collected line image; converting the pre-processed image to the frequency domain using Fourier transform; evaluating the distribution of high-frequency energy by calculating the power spectral density of the frequency domain image; setting a clarity index according to the distribution of high-frequency energy, and using the defined clarity index to evaluate the clarity of each area in the image.

[0016] (III) Beneficial effects

[0017] In the intelligent inspection data acquisition system of the present invention, the route planning module uses an algorithm to automatically generate the optimal UAV flight path map. The UAV module is equipped with a high-precision navigation control system, and the UAV strictly performs tasks according to the flight path formulated by the route planning module. The line data acquisition module is responsible for capturing high-resolution images and video data of the power line and the surrounding environment. The GPS positioning module tracks the precise location of the UAV in real time and associates these geographic coordinate information with each image or video clip collected. This not only provides an accurate geographic reference for image blur detection and subsequent re-inspection, but also helps to establish a detailed inspection track record for easy tracing and management. The image blur detection module uses image processing technology combined with GPS positioning data. The module can automatically identify and mark the image blur area caused by UAV vibration, rapid movement or other factors. By analyzing the sharpness, contrast and motion blur characteristics of the image, the system can accurately judge the image quality and mark the corresponding precise geographic location for each blurred image, indicating the direction for the subsequent re-inspection work. According to the geographic location information provided by the image blur detection module, the re-inspection module dispatches the UAV to fly back to the marked blur area for re-shooting. Through such an iterative mechanism, the system can effectively improve the integrity and reliability of inspection data and provide strong support for power line maintenance decisions. This enables refined management and monitoring of power lines, greatly reduces the workload of manual inspections, and improves the quality and efficiency of inspections, providing a strong guarantee for the safe and stable operation of the power system. 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 structural diagram of the intelligent inspection data acquisition system of the first embodiment of the present invention.

[0020] Figure 2 It is a structural diagram of a route planning module according to the second embodiment of the present invention.

[0021] Figure 3 It is a structural diagram of a line data acquisition module according to a second embodiment of the present invention.

[0022] Figure 4 is a structural diagram of an image pickup unit according to a second embodiment of the present invention.

[0023] Figure 5It is a structural diagram of an image blur detection module according to a second embodiment of the present invention.

[0024] Route planning module 101, drone module 102, line data acquisition module 103, GPS positioning module 104, image blur detection module 105, fault initial inspection module, line information acquisition unit 202, map data acquisition unit 203, path generation unit 204, path optimization unit 205, camera unit 206, environmental parameter acquisition unit 207, infrared imaging unit 208, focal length setting subunit 209, flight parameter acquisition subunit 210, matching subunit 211, association unit 212, analysis unit 213, marking unit 214. DETAILED DESCRIPTION

[0025] 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.

[0026] See also Figure 1-5 The present invention provides a technical solution: an intelligent inspection data acquisition system,

[0027] It includes route planning module, drone module, route data acquisition module, GPS positioning module, image blur detection module and re-inspection module;

[0028] The route planning module is used to generate a flight path diagram based on the power line location;

[0029] The drone module is used to use the drone to fly based on the flight path map;

[0030] The line data acquisition module is used to be installed on the drone module to capture line images of the power line and its surrounding environment;

[0031] The GPS positioning module is used to record the geographical location information when the route image is collected in real time;

[0032] The image blur detection module is used to automatically mark the image blur area on the image using GPS positioning data and image analysis technology to obtain the blurred image and corresponding geographical location information;

[0033] The recheck module is used to re-collect the corresponding route image based on the geographical location information corresponding to the blurred image;

[0034] The intelligent inspection data collection system further includes a fault preliminary detection module, which is used to perform preliminary fault detection on the collected images;

[0035] The route planning module includes a line information acquisition unit, a map data acquisition unit, a path generation unit, and a path optimization unit;

[0036] The line information acquisition unit is used to collect geographical information of the power line;

[0037] The map data acquisition unit is used to collect map data of the inspection area;

[0038] The path generation unit is used to generate a plurality of candidate flight paths on a digital map according to the locations of the power lines;

[0039] The path optimization unit is used to select the flight path initially planned by using a particle swarm optimization algorithm to obtain a flight path diagram;

[0040] The specific steps of optimizing the initially planned flight path using the particle swarm optimization algorithm to obtain the flight path diagram include:

[0041] Set the number and initial parameters of the particle swarm;

[0042] Set the fitness function to evaluate the position of each particle;

[0043] Use the evaluation function to calculate the fitness value of each particle;

[0044] For each particle, compare its fitness value with its historical best fitness value. If the current fitness is better, update the individual best position.

[0045] Update the velocity of each particle based on the current velocity, individual best position, and global best position;

[0046] Use the updated velocity to adjust the particle position and generate a flight path diagram;

[0047] The line data acquisition module includes a camera unit, an environmental parameter acquisition unit and an infrared imaging unit;

[0048] The camera unit is used to automatically adjust the focal length according to the flight altitude and target distance to ensure high definition of the image;

[0049] The environmental parameter acquisition unit is used to monitor environmental parameters during flight;

[0050] The infrared imaging unit is used to capture thermal image information of the power line;

[0051] The camera unit includes a focus setting subunit, a flight parameter acquisition subunit and a matching subunit;

[0052] The focal length setting subunit is used to determine the ideal focal length range under different flight altitudes and target distances, and obtain a focal length adjustment mechanism;

[0053] The flight parameter acquisition subunit is used to detect the flight altitude and target distance in real time using the flight control system of the UAV;

[0054] The matching subunit is used to calculate the required focal length using the designed focal length adjustment mechanism according to the flight altitude and target distance detected in real time;

[0055] The image blur detection module includes an association unit, an analysis unit and a marking unit;

[0056] The association unit is used to synchronize the GPS positioning system of the drone with the image acquisition system so that each route image is associated with corresponding geographic location data;

[0057] The analysis unit is used to analyze the collected line image using a frequency domain analysis method to evaluate the clarity of each area in the image;

[0058] The marking unit is used to automatically mark the detected blurred area on the image;

[0059] The specific steps of analyzing the collected line image using the frequency domain analysis method and evaluating the clarity of each area in the image include:

[0060] Perform denoising on the collected line images;

[0061] Convert the preprocessed image to the frequency domain using Fourier transform;

[0062] The distribution of high-frequency energy is evaluated by calculating the power spectral density of the frequency domain image;

[0063] The sharpness index is set according to the distribution of high-frequency energy, and the sharpness of each area in the image is evaluated using the defined sharpness index.

[0064] Example:

[0065] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0066] First embodiment

[0067] See also Figure 1 The present invention provides an intelligent inspection data acquisition system, including a route planning module 101, an unmanned aerial vehicle module 102, a line data acquisition module 103, a GPS positioning module 104, an image blur detection module 105 and a re-inspection module; the route planning module 101 is used to generate a flight path diagram based on the position of the power line; the unmanned aerial vehicle module 102 is used to use the unmanned aerial vehicle to fly based on the flight path diagram; the line data acquisition module 103 is used to be installed on the unmanned aerial vehicle module 102 to capture the line image of the power line and its surrounding environment; the GPS positioning module 104 is used to record the geographical location information when the line image is collected in real time; the image blur detection module 105 is used to use the GPS positioning data and image analysis technology to automatically mark the image blur area on the image to obtain the blurred image and the corresponding geographical location information; the re-inspection module is used to re-collect the corresponding line image based on the geographical location information corresponding to the blurred image.

[0068] In this embodiment, the route planning module 101 uses an algorithm to automatically generate the optimal UAV flight path map in combination with GIS (geographic information system) data and the actual layout of the power line. The UAV module 102 is equipped with a high-precision navigation control system UAV, which strictly performs tasks according to the flight path formulated by the route planning module 101. The UAV not only has a long endurance, but is also equipped with a high-definition camera and other necessary sensors to ensure stable and efficient data collection during flight. In addition, the UAV module 102 also supports remote control and autonomous flight modes, and is suitable for a variety of operating environments. The line data acquisition module 103 is responsible for capturing high-resolution images and video data of the power line and the surrounding environment. It integrates a wide-angle lens and a zoom lens, and can record the line conditions from macro to micro in an all-round way, including potential problems such as insulator damage, wire hanging objects, and vegetation intrusion, providing a detailed data basis for subsequent analysis. The GPS positioning module 104 tracks the precise location of the UAV in real time and associates these geographic coordinate information with each image or video clip collected. This not only provides accurate geographic reference for image blur detection and subsequent re-inspection, but also helps to establish detailed inspection track records for easy traceability and management. The image blur detection module 105 uses image processing technology combined with GPS positioning data. The module can automatically identify and mark the image blur areas caused by drone vibration, rapid movement or other factors. By analyzing the sharpness, contrast and motion blur characteristics of the image, the system can accurately judge the image quality and mark the corresponding precise geographical location for each blurred image, indicating the direction for subsequent re-inspection work. Re-inspection module: According to the geographical location information provided by the image blur detection module 105, the re-inspection module dispatches the drone to fly back to the marked blurry area for re-shooting. Through such an iterative mechanism, the system can effectively improve the integrity and reliability of the inspection data and provide strong support for power line maintenance decisions. Thereby realizing the refined management and monitoring of power lines, greatly reducing the workload of manual inspections, while improving the quality and efficiency of inspections, and providing a strong guarantee for the safe and stable operation of the power system.

[0069] Second embodiment

[0070] See also Figure 2 to Figure 5 On the basis of the first embodiment, the present invention further provides an intelligent patrol inspection data acquisition system, the intelligent patrol inspection data acquisition system also includes a fault initial detection module, the fault initial detection module is used to perform preliminary fault detection on the collected images.

[0071] The fault initial inspection module uses a pre-trained model to automatically identify various abnormal features in the image, which range from subtle structural damage and component misalignment to more significant cracks, leakage and other signs of faults. Advanced image processing techniques, such as edge detection, object recognition and abnormal color analysis, can effectively improve the accuracy and sensitivity of fault detection even under complex and changing environmental conditions. More specifically, the module first pre-processes the collected images, including denoising, contrast enhancement and perspective correction, to optimize image quality and ensure the accuracy of subsequent analysis. Subsequently, the image is analyzed layer by layer through a deep neural network, with each layer focusing on extracting different feature information, from low-level edges and textures to high-level specific fault modes, layer by layer, to build a multi-level fault judgment framework. In addition, the module also has the ability of self-learning and optimization, and can continuously accumulate cases and learn new fault types in actual operation, thereby continuously improving its detection capabilities.

[0072] The route planning module 101 includes a line information acquisition unit 202, a map data acquisition unit 203, a path generation unit 204, and a path optimization unit 205; the line information acquisition unit 202 is used to collect geographic information of power lines; the map data acquisition unit 203 is used to collect map data of the inspection area; the path generation unit 204 is used to generate multiple candidate flight paths on a digital map according to the location of the power lines; the path optimization unit 205 is used to select the initially planned flight path using a particle swarm optimization algorithm to obtain a flight path map.

[0073] The line information acquisition unit 202 is responsible for collecting and integrating detailed geographic information of power lines from multiple channels. This includes but is not limited to the coordinates of the starting and ending points of the line, the location of the towers along the line, information on important intersections, and specific data on any known obstacles or restricted flight areas. Through the comprehensive application of GPS positioning technology, GIS geographic information system and remote database interface, the unit ensures the real-time and accuracy of the collected information, providing a solid foundation for subsequent planning. The map data acquisition unit 203 focuses on obtaining the latest high-precision map data of the inspection area, covering topography, building distribution, meteorological conditions and dynamic factors affecting drone flight. This part of the work usually involves interface interaction with third-party map service providers, as well as the use of remote sensing technology and satellite image data to supplement, aiming to provide a comprehensive and detailed two-dimensional and three-dimensional spatial reference framework for path planning. The path generation unit 204 works on an advanced digital map platform based on the above-collected line information and map data. Using complex algorithm models, such as the shortest path algorithm, obstacle avoidance algorithm, etc., the unit can generate multiple candidate flight paths from the starting point to the end point according to the actual layout of the power line. These paths must not only ensure that all key checkpoints are covered, but also consider flight efficiency, safety and the endurance of the drone, so as to provide a variety of solutions for subsequent optimization options. The path optimization unit 205 plays the role of a strategic decision maker. It uses the cutting-edge particle swarm optimization algorithm (PSO) to conduct in-depth evaluation and screening of multiple candidate paths provided by the path generation unit 204. The PSO algorithm simulates the behavior pattern of bird flocks foraging in nature, allowing each candidate path to represent a "particle". The flight direction and speed of the "particle" are continuously adjusted in multiple rounds of iterations to find the global optimal or near-optimal solution. After this series of intelligent calculations and simulations, an optimal flight path map that avoids potential risks and meets flight efficiency and safety standards is finally determined. This path map not only intuitively shows the flight trajectory of the drone, but also provides a scientific basis for the final preparations before the mission and dynamic adjustments during the flight.

[0074] The specific steps of using the particle swarm optimization algorithm to optimize the initially planned flight path and obtain the flight path diagram include: setting the number and initial parameters of the particle swarm; setting a fitness function to evaluate the position of each particle; using an evaluation function to calculate the fitness value of each particle; for each particle, comparing its fitness value with its historical best fitness value, and if the current fitness is better, updating the individual best position; updating the speed of each particle according to the current speed, the individual best position and the global best position; using the updated speed to adjust the position of the particle to generate a flight path diagram.

[0075] Specifically, the number of particle swarms needs to be determined, which is usually balanced according to the complexity of the problem and the computational resources. Too many particles will increase the computational burden, while too few particles will not be able to fully explore the search space. Each particle represents a potential flight path solution, and its initial position is randomly distributed in the preset solution space. At the same time, the velocity vector of each particle is initialized. This step is to set a starting point for the search process.

[0076] The fitness function is a measure of the quality of a solution (in this case, the flight path). For flight path optimization, the fitness function takes into account factors such as flight distance, flight time, energy consumption, the ability to avoid no-fly zones and obstacles, and flight stability. An ideal flight path should try to optimize these indicators while satisfying all constraints.

[0077] For each particle, the fitness function is used to evaluate the quality of its current position, that is, to calculate the fitness value of each particle. This value directly reflects the performance of the flight path, and a larger value usually means a better path.

[0078] For each particle, its current fitness value is compared with its own historical best fitness value (individual best). If the current fitness value is better, the individual best position of the particle is updated. At the same time, the best position of all particles is recorded as the global best position, which represents the optimal flight path currently searched.

[0079] Based on the particle's current speed, individual best position, and global best position, the speed of each particle is adjusted through a specific update rule. This process combines individual learning (tending to the individual best) and community learning (tending to the global best) to guide the particle group to move to a better solution area. After the speed is updated, the position of each particle is also adjusted accordingly. This step is the core of the PSO algorithm search mechanism.

[0080] Through the above iterative process, particles continue to explore and optimize, and finally use the updated particle position information to generate a flight path map. This map not only shows the expected flight trajectory of the drone, but also is the result of optimization by the particle swarm optimization algorithm. In theory, it should be more efficient, safer and in line with actual operation requirements than the initially planned path.

[0081] The whole process is a cyclic iterative process until the preset stopping criteria are reached, such as reaching the maximum number of iterations, the fitness value converges to a certain threshold, or a satisfactory flight path optimization degree is achieved. Through such a mechanism, the PSO algorithm can effectively mine the optimal flight path solution in a complex environment.

[0082] The line data acquisition module 103 includes a camera unit 206, an environmental parameter acquisition unit 207 and an infrared imaging unit 208; the camera unit 206 is used to automatically adjust the focal length according to the flight altitude and the target distance to ensure high definition of the image; the environmental parameter acquisition unit 207 is used to monitor environmental parameters during the flight; the infrared imaging unit 208 is used to capture thermal imaging information of the power line.

[0083] The camera unit 206 can automatically adjust the focal length to the optimal state according to the instantaneous flight altitude of the drone and the dynamic distance between it and the inspection target. The environmental parameter acquisition unit 207 integrates a series of environmental perception sensors, such as thermometers, hygrometers, anemometers and barometers, which can continuously monitor and record the real-time parameters of the surrounding environment during the drone's mission. These data are crucial for evaluating inspection conditions, analyzing the causes of abnormal phenomena, and predicting possible environmental impacts in the future. For example, problems such as line overheating warnings under extreme climate conditions and insulation performance degradation caused by humidity can be discovered and prevented in advance through comprehensive analysis of these parameters. The infrared imaging unit 208 uses non-contact infrared thermal imaging technology. This unit can penetrate visual obstacles and capture the temperature distribution on the surface of power lines and equipment. Whether it is a tiny hot spot at the wire connection point, a thermal failure of an insulator, or other thermal anomalies that are difficult to directly observe, the infrared imaging unit 208 can accurately identify and record them.

[0084] The camera unit 206 includes a focal length setting subunit 209, a flight parameter acquisition subunit 210 and a matching subunit 211; the focal length setting subunit 209 is used to determine the ideal focal length range under different flight altitudes and target distances, and obtain a focal length adjustment mechanism; the flight parameter acquisition subunit 210 is used to use the flight control system of the drone to detect the flight altitude and target distance in real time; the matching subunit 211 is used to calculate the required focal length according to the flight altitude and target distance detected in real time using the designed focal length adjustment mechanism.

[0085] The focal length setting subunit 209 is responsible for obtaining the most suitable focal length range based on experience according to different flight altitudes and distances to the target object.

[0086] The flight parameter acquisition subunit 210 is tightly integrated into the flight control system of the UAV. It uses GPS, barometer, ultrasonic sensor and advanced computer vision technology to accurately measure the current flight altitude of the UAV, and uses image recognition and depth perception technology to instantly calculate the precise distance between the target object and the UAV.

[0087] The matching subunit 211 is a key link in integrating and processing the data of the first two parts. After receiving the altitude and distance information transmitted in real time by the flight parameter acquisition subunit 210, it immediately starts the preset focal length adjustment mechanism, and maps these real-time data to the pre-calculated ideal focal length range through numerical matching, thereby obtaining a specific focal length value. This greatly improves the flexibility and imaging quality of drone photography, and provides strong technical support for various application scenarios such as aerial photography, remote sensing detection, and monitoring.

[0088] The image blur detection module 105 includes an association unit 212, an analysis unit 213 and a marking unit 214; the association unit 212 is used to synchronize the GPS positioning system of the drone with the image acquisition system so that each route image is associated with the corresponding geographic location data; the analysis unit 213 is used to analyze the collected route images using a frequency domain analysis method to evaluate the clarity of each area in the image; the marking unit 214 is used to automatically mark the detected blurry area on the image.

[0089] The association unit 212 is the starting point of the image blur detection process, and realizes the seamless connection between the drone GPS positioning system and the image acquisition system. Whenever the drone is performing an inspection task, the unit will ensure that each line image taken is accurately marked with the geographical location information at the time of shooting, including multi-dimensional coordinate data such as longitude, latitude, and altitude. This instant embedding of spatial information not only gives the image data a geographical reference, but also facilitates subsequent image analysis and on-site review, so that each image can find its exact location in the huge geographic information system, greatly improving the efficiency of data management and problem tracking. The analysis unit 213 uses the frequency domain analysis method to conduct in-depth mining of the line image associated with geographic information. Frequency domain analysis is an image processing method based on the frequency characteristics of the signal. It can effectively reveal the distribution of different frequency components in the image, especially for the clarity assessment of fine structures and textures. By performing Fourier transform on the image, the analysis unit 213 can separate high-frequency detail information and low-frequency background structure, and then evaluate the clarity level of each area in the image. This method can accurately identify blurred image areas caused by camera shake, improper shutter speed or poor lighting conditions, providing a scientific basis for subsequent maintenance decisions. The marking unit 214 automatically highlights or marks the detected blurred areas on the original image based on the clarity evaluation results output by the analysis unit 213. This automated process eliminates the tediousness of manual screening and significantly improves work efficiency. The marking unit 214 can not only intuitively display which areas do not meet the image quality standards, but also use different colors or icons to distinguish them according to the degree of blur, so that technicians can identify the severity of the problem at a glance. In addition, the marking results are usually accompanied by a detailed report that explains the geographic coordinates of the blurred area, the estimated degree of blur and the cause, providing a detailed basis for field inspections and the formulation of maintenance plans.

[0090] The specific steps of analyzing the collected line image using the frequency domain analysis method and evaluating the clarity of each area in the image include: denoising the collected line image; converting the pre-processed image to the frequency domain using Fourier transform; evaluating the distribution of high-frequency energy by calculating the power spectral density of the frequency domain image; setting a clarity index according to the distribution of high-frequency energy, and using the defined clarity index to evaluate the clarity of each area in the image.

[0091] First, the collected line images are subjected to necessary denoising. This step is crucial because the original images often contain various noises, such as random noise, salt and pepper noise, or stripe noise, which will interfere with the accuracy of subsequent analysis. Denoising techniques include median filtering, bilateral filtering, wavelet denoising, or non-local mean denoising. The selection of the appropriate method depends on the image characteristics and noise type. The purpose is to reduce noise while retaining the edge and detail information of the image. After denoising, the pre-processed image is converted from the spatial domain to the frequency domain using Fourier transform. Fourier transform is a mathematical tool that can decompose an image into a combination of different frequency components. The high-frequency part corresponds to the details and edge information in the image, while the low-frequency part represents the overall structure and uniform color area. This conversion makes it intuitive and easy to operate to analyze the texture characteristics and clarity of the image. In the frequency domain, the energy distribution of each frequency component can be quantified by performing power spectral density (PSD) analysis on the converted image. In particular, the power spectral density of the high-frequency part reflects the richness of the fine structure and edges in the image, and is a key indicator for evaluating image clarity. By analyzing the high-frequency energy distribution, it is possible to identify which areas of the image contain rich detail information and which areas are unclear due to blur or low contrast. Based on the analysis results of the high-frequency energy distribution, one or more clarity indicators are further defined. These indicators include the energy ratio within a specific frequency bandwidth, the location of the peak frequency, or the energy concentration. Then, the clarity of each area in the image is quantitatively evaluated based on these indicators. This usually involves dividing the image into multiple sub-areas, calculating the frequency domain characteristics of these areas respectively, and comparing their clarity indicators to identify the parts with the highest and lowest clarity in the entire image. This partitioned evaluation method helps to accurately locate the problem areas of image clarity and provide precise guidance for subsequent image optimization or fault diagnosis.

[0092] In summary, the route planning module of the intelligent inspection data acquisition system of the present invention uses an algorithm to automatically generate the optimal UAV flight path map. The UAV module is equipped with a high-precision navigation control system, and performs tasks strictly in accordance with the flight path formulated by the route planning module. The line data acquisition module is responsible for capturing high-resolution images and video data of the power lines and the surrounding environment. The GPS positioning module tracks the precise location of the UAV in real time and associates these geographic coordinate information with each image or video clip collected. This not only provides an accurate geographic reference for image blur detection and subsequent re-inspection, but also helps to establish a detailed inspection track record for easy tracing and management. The image blur detection module uses image processing technology combined with GPS positioning data. The module can automatically identify and mark the image blur area caused by UAV vibration, rapid movement or other factors. By analyzing the sharpness, contrast and motion blur characteristics of the image, the system can accurately judge the image quality and mark the corresponding precise geographic location for each blurred image, indicating the direction for the subsequent re-inspection work. According to the geographic location information provided by the image blur detection module, the re-inspection module dispatches the UAV to fly back to the marked blur area for re-shooting. Through such an iterative mechanism, the system can effectively improve the integrity and reliability of inspection data and provide strong support for power line maintenance decisions. This enables refined management and monitoring of power lines, greatly reduces the workload of manual inspections, and improves the quality and efficiency of inspections, providing a strong guarantee for the safe and stable operation of the power system.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent inspection data collection system, characterized by: It includes route planning module, drone module, route data acquisition module, GPS positioning module, image blur detection module and re-inspection module; The route planning module is used to generate a flight path diagram based on the power line location; The drone module is used to use the drone to fly based on the flight path map; The line data acquisition module is used to be installed on the drone module to capture line images of the power line and its surrounding environment; The GPS positioning module is used to record the geographical location information when the route image is collected in real time; The image blur detection module is used to automatically mark the image blur area on the image using GPS positioning data and image analysis technology to obtain the blurred image and corresponding geographical location information; The re-inspection module is used to re-collect the corresponding route image based on the geographical location information corresponding to the blurred image.

2. The intelligent inspection data collection system according to claim 1, characterized in that: The intelligent inspection data collection system also includes a fault initial detection module, which is used to perform preliminary fault detection on the collected images.

3. The intelligent inspection data collection system according to claim 2, characterized in that: The route planning module includes a line information acquisition unit, a map data acquisition unit, a path generation unit, and a path optimization unit; The line information acquisition unit is used to collect geographical information of the power line; The map data acquisition unit is used to collect map data of the inspection area; The path generation unit is used to generate a plurality of candidate flight paths on a digital map according to the locations of the power lines; The path optimization unit is used to select the initially planned flight path using a particle swarm optimization algorithm to obtain a flight path diagram.

4. The intelligent inspection data collection system according to claim 3, characterized in that: The specific steps of optimizing the initially planned flight path using the particle swarm optimization algorithm to obtain the flight path diagram include: Set the number and initial parameters of the particle swarm; Set the fitness function to evaluate the position of each particle; Use the evaluation function to calculate the fitness value of each particle; For each particle, compare its fitness value with its historical best fitness value. If the current fitness is better, update the individual best position. Update the velocity of each particle based on the current velocity, individual best position, and global best position; Use the updated velocity to adjust the particle's position and generate a flight path graph.

5. The intelligent inspection data collection system according to claim 4, characterized in that: The line data acquisition module includes a camera unit, an environmental parameter acquisition unit and an infrared imaging unit; The camera unit is used to automatically adjust the focal length according to the flight altitude and target distance to ensure high definition of the image; The environmental parameter acquisition unit is used to monitor environmental parameters during flight; The infrared imaging unit is used to capture thermal imaging information of the power line.

6. The intelligent inspection data collection system according to claim 5, characterized in that: The camera unit includes a focus setting subunit, a flight parameter acquisition subunit and a matching subunit; The focal length setting subunit is used to determine the ideal focal length range under different flight altitudes and target distances, and obtain a focal length adjustment mechanism; The flight parameter acquisition subunit is used to detect the flight altitude and target distance in real time using the flight control system of the UAV; The matching subunit is used to calculate the required focal length using the designed focal length adjustment mechanism according to the flight altitude and target distance detected in real time.

7. The intelligent inspection data collection system according to claim 6, characterized in that: The image blur detection module includes an association unit, an analysis unit and a marking unit; The association unit is used to synchronize the GPS positioning system of the drone with the image acquisition system so that each route image is associated with corresponding geographic location data; The analysis unit is used to analyze the collected line image using a frequency domain analysis method to evaluate the clarity of each area in the image; The marking unit is used to automatically mark the detected blurred area on the image.

8. The intelligent inspection data collection system according to claim 7, characterized in that: The specific steps of analyzing the collected line image using the frequency domain analysis method and evaluating the clarity of each area in the image include: Perform denoising on the collected line images; Convert the preprocessed image to the frequency domain using Fourier transform; The distribution of high-frequency energy is evaluated by calculating the power spectral density of the frequency domain image; The sharpness index is set according to the distribution of high-frequency energy, and the sharpness of each area in the image is evaluated using the defined sharpness index.

Images