Video analysis method, device and system based on UAV power inspection

Through the drone video analysis method, high-definition cameras and reference models are used to identify transmission lines and accessories, solving the problems of low efficiency and insufficient safety in manual inspection, and achieving efficient and accurate power transmission line monitoring, which can detect faults in a timely manner.

CN118692012BActive Publication Date: 2024-11-19CCCC MECHANICAL & ELECTRICAL ENG +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411163426.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-19
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

The existing artificial power transmission lines have low patrol efficiency and cannot be guaranteed. Especially in complex terrain and harsh environments, it is difficult to effectively monitor the faults and damage of transmission lines.

Method used

Using a drone-based video analysis method, the video images of power lines and accessories are obtained through high-definition cameras, the images are segmented, and the preset benchmark model is used for identification and analysis, the shape, grayscale and position parameter values ​​are calculated, and the differences are detected to output. Fault location.

Benefits of technology

It significantly improves the efficiency and accuracy of power inspection, reduces the consumption of computing resources, enhances the monitoring accuracy of transmission lines and accessories, and can promptly detect insulator wear, wire breakage and other faults.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118692012B_ABST
    Figure CN118692012B_ABST
Patent Text Reader

Abstract

The present invention discloses a video analysis method, device and system based on unmanned aerial vehicle power inspection, including: S1, obtaining the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the unmanned aerial vehicle; S2, dividing into multiple sections of video images according to preset nodes, selecting at least one frame of image sequence, calling the preset benchmark model of the power transmission line and its accessories as the benchmark analysis to identify the image of the power transmission line and its accessories, and calculating the shape parameter value, gray parameter value and position parameter value; S3, comparing the shape parameter value, gray parameter value and position parameter value of the image of the power transmission line and its accessories obtained in the previous inspections to calculate the shape difference, gray difference and position difference, and when the threshold is reached, output the corresponding section video image and the difference position. The present invention has the beneficial effects of reducing the amount of image video analysis data, improving the recognition accuracy of the power transmission line and its accessories, and improving the inspection efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power inspection, and more specifically, to a video analysis method, device and system based on unmanned aerial vehicle power inspection. Background Art

[0002] At present, long-distance power transmission mainly adopts high-voltage and ultra-high-voltage overhead transmission lines, and the transmission lines usually pass through hills, mountains, forests, lakes, rivers and other complex and changeable bad areas, and the transmission lines are exposed to the wild for a long time. They are not only under pressure from the power load, but also under long-term influence of the adverse external environment, such as lightning, rainstorm and other bad weather, such as dirt and corrosion, which may cause the insulators of the transmission lines to wear, missing, wire strands to break, and accessories to be missing, such as the loss of shock-proof hammers. These faults will seriously threaten the safe operation of power transmission and power grids. For example, accidents such as line flashing, power outages, and forest fires caused by tree discharge. Therefore, it is necessary to conduct regular inspections of transmission lines to reduce the occurrence of accidents. The existing manual transmission line inspections are far from meeting the actual needs, the efficiency is too low, and the safety of manual inspections in complex terrain cannot be guaranteed. Based on the fact that the existing drones have accurate positioning and cruising functions, and can fly stably after carrying a certain amount of heavy objects, and the video image processing technology has also been significantly improved, the target objects in the video images can be identified, and the position and grayscale value can be calculated. Therefore, it is possible and worth considering to study a system that can be adapted to power inspections based on drones and video image processing technology to improve inspection efficiency and safety. Summary of the invention

[0003] An object of the present invention is to solve at least the above problems and to provide at least the advantages which will be described hereinafter.

[0004] In order to achieve these purposes and other advantages according to the present invention, a video analysis method based on UAV power inspection is provided, comprising the following steps:

[0005] S1, obtaining the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone;

[0006] S2. Segment the current video image into multiple sections of video images according to preset nodes, select at least one frame of image sequence from each section of the video image, and adjust the selected image sequence according to the preset orientation, size and light intensity, and then call the preset benchmark model of the power transmission line and its accessories as the benchmark analysis to obtain the image of the power transmission line and its accessories in the current video image, and calculate its shape parameter value, grayscale parameter value and position parameter value accordingly;

[0007] S3. Calculate the shape difference, grayscale difference and position difference of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories in the current video image obtained by identification and the corresponding image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories obtained in previous inspections. When the shape difference or grayscale difference calculation reaches the corresponding preset threshold, output the corresponding section video image and difference position.

[0008] Preferably, the transmission line and its accessories include a transmission line, an anti-vibration hammer accessory, a spacer rod accessory, an insulator accessory, and a transmission tower;

[0009] The method for establishing the benchmark model specifically includes: manually processing and separating the transmission line and its accessories in each section of the video image, and eliminating the surrounding environment to obtain independent images of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, that is, obtaining a benchmark model of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, wherein the benchmark model includes shape parameters, grayscale parameters, and position parameters.

[0010] Preferably, the method for establishing the benchmark model includes enhancement processing, denoising processing and edge detection;

[0011] The enhancement process includes: setting the gray value interval to [a, c], enhancing the pixels in the gray value interval [a, c], and keeping the gray values ​​of the pixels in the gray value interval [a, c] unchanged; wherein the gray value interval [a, c] is adaptively set to the pixels of the transmission line and its accessories;

[0012] The denoising process includes: setting a denoising threshold T and a neighborhood range S, calculating the difference between a certain point pixel and the average value of the grayscale values ​​of each pixel in its neighborhood range S, if the difference is greater than the denoising threshold T, then replacing the grayscale value of the point pixel with the average value, if the difference is not greater than the denoising threshold T, then the grayscale value of the point pixel remains unchanged;

[0013] The edge detection adopts the Sobel operator edge detection method.

[0014] Preferably, the route setting method for the drone equipped with a high-definition camera to shoot video images in step S1 includes: the drone pre-flies from the starting section to the end section, the high-definition camera synchronously acquires the corresponding video images, and the drone stands by at the end section;

[0015] Select the video images in which the grayscale value difference between the image of the power line and its accessories and its surrounding environment is less than a preset threshold, adjust the flight direction of the UAV from the end segment to the starting segment and the shooting direction of the high-definition camera to obtain the video image again, and repeatedly compare the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image until the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image obtained in the one-way flight route of the UAV is not less than the preset threshold, so as to obtain the flight route of the UAV.

[0016] A video analysis device for executing the video analysis method based on UAV power inspection is provided, comprising:

[0017] An image acquisition module, which is used to acquire the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone;

[0018] An image processing module is used to divide the current video image into multiple sections according to preset nodes, select at least one frame of image sequence from each section of the video image, and adjust the selected image sequence according to the preset orientation, size and light intensity, and then call the preset benchmark model of the power transmission line and its accessories as the benchmark analysis to obtain the image of the power transmission line and its accessories in the current video image, and calculate its shape parameter value, gray parameter value and position parameter value accordingly;

[0019] The difference output module is used to calculate the shape difference, grayscale difference and position difference of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories in the current video image obtained by identification and the corresponding image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories obtained in the previous inspections. When the shape difference or grayscale difference calculation reaches the corresponding preset threshold, the corresponding section video image and difference position are output.

[0020] A video analysis system based on UAV power inspection is provided, comprising:

[0021] A drone equipped with a flight control system, a high-definition camera, and a wireless transmission system, wherein the high-definition camera is used to capture video images of the power transmission line and its surroundings;

[0022] A ground remote control system, which is in communication with the flight control system, and is used to control the UAV to fly according to a flight route;

[0023] The video analysis device based on UAV power inspection;

[0024] A display is connected to the ground remote control system and the video analysis device, and the display is used to display the video images received by the video analysis device, the flight data of the flight control system and the ground remote control system, and the output of the video analysis device.

[0025] An electronic device is provided, comprising:

[0026] one or more processors;

[0027] Memory; and

[0028] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for executing the method.

[0029] A computer-readable storage medium is provided, storing a computer program used in combination with an electronic device, wherein the computer program can be executed by a processor to implement the method described.

[0030] The present invention includes at least the following beneficial effects: by dividing the video images obtained by inspection into multiple sections of video images, and then extracting one or several frames of image sequences that match the geographical location from the section video images, the processing amount of the video images can be significantly reduced, saving the consumption of computer resources. After that, due to the small amount of image sequences, the computer can simultaneously process and analyze multiple frame image sequences, thereby significantly improving the image processing efficiency. Then, by pre-setting a benchmark model for each section of the inspection range based on the geographical location differences in the early stage, the noise caused by the different shapes of the surrounding environment, power lines and their accessories can be filtered out, thereby significantly improving the accuracy of video analysis.

[0031] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a framework diagram of a video analysis method according to one of the technical solutions of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0034] It should be noted that the experimental methods described in the following embodiments are conventional methods unless otherwise specified, and the reagents and materials are commercially available unless otherwise specified; in the description of the present invention, the orientation or positional relationship indicated by the terms is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0035] like Figure 1 As shown, the present invention provides a video analysis method based on UAV power inspection, comprising the following steps:

[0036] S1, obtaining the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone;

[0037] S2, divide the current video image into multiple sections according to the preset nodes, select at least one frame of image sequence from each section of the video image, adjust it according to the preset orientation, size and light intensity, then call the preset transmission line and its accessories benchmark model as the benchmark analysis to identify the image of the transmission line and its accessories in the current video image, and calculate its shape parameter value, grayscale parameter value and position parameter value accordingly; divide the inspection range into multiple sections according to the geographical location order, each inspection range corresponds to a section of the video image, because the video image is a continuous multi-frame static image sequence, therefore, select at least one frame of image matching the geographical location of each inspection range from each section of the video image, thereby saving a lot of video image processing and significantly improving processing efficiency. Although the drone flies according to the preset route, so that the orientation and angle of each shooting are basically the same, due to weather reasons (wind force, light intensity), it cannot remain exactly the same, therefore, the orientation, size and light intensity of the selected image sequence are fine-tuned to improve accuracy. Then, grayscale enhancement processing, smoothing and denoising processing, straight line extraction, edge detection, etc. are performed on each frame of the selected image sequence to obtain a processed image of the power transmission line and its accessories in each frame of the image sequence, and its corresponding shape parameter value, grayscale parameter value and position parameter value;

[0038] S3. The image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the transmission line and its accessories in the current video image obtained by identification are respectively compared with the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the corresponding transmission line and its accessories obtained in the previous inspections, and when the shape difference or grayscale difference calculation reaches the corresponding preset threshold value, the corresponding section video image and difference position are output. The thresholds of the image shape difference, grayscale difference and position difference of the transmission line and its accessories are adjusted and set according to the actual situation. When one of the shape parameter value, grayscale parameter value and position parameter value is greater than the corresponding threshold value, it means that in the current inspection result, the transmission line and its accessories have a large change from the previous inspection result or the previous inspection results. This change may be due to wear and loss of insulators, broken wire strands, missing anti-vibration hammers, dirt attached to the wires, etc., so that the corresponding one-frame image sequence and section video image can be selected and output for further verification. In order to avoid accidental inspection errors, and some faults require a certain amount of time to accumulate before they can be distinguished (such as insulator wear and dirt attached to the wire), the inspection results of the previous several times are also selected as comparison objects during calculation. In addition, in order to further improve the accuracy of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the transmission line and its accessories, a benchmark model is accurately pre-set for the video images of each inspection range with different geographical locations in the early stage. The benchmark model includes specific calculation parameters for grayscale enhancement processing, smoothing denoising processing, straight line extraction, and edge detection. Because the geographical location is different, the surrounding environment presented in the transmission line and its accessories is also different, and the form of the transmission line and its accessories in each video image is also different. In addition, since the video images of each section are processed separately, only one frame or more image sequences are selected in each video image. Therefore, it will not only not increase the consumption of computer resources, but also enable multiple video images to be processed simultaneously, significantly improving the image processing efficiency.

[0039] In the above technical solution, by dividing the video images obtained by the inspection into multiple sections of video images, and then extracting a sequence of one or more frames of images that match the geographical location from the section video images, the processing amount of the video images can be significantly reduced, saving the consumption of computer resources. After that, due to the small amount of image sequences, the computer can simultaneously process and analyze multiple frame image sequences, thereby significantly improving the image processing efficiency. Then, by pre-setting a benchmark model for each section of the inspection range based on the geographical location differences in the early stage, the noise caused by the different shapes of the surrounding environment, power lines and their accessories can be filtered out, thereby significantly improving the accuracy of video analysis.

[0040] In another technical solution, the transmission line and its accessories include a transmission line, an anti-vibration hammer accessory, a spacer rod accessory, an insulator accessory, and a transmission tower;

[0041] The method for establishing the benchmark model specifically includes: manually processing and separating the transmission line and its accessories in each section of the video image, and eliminating the surrounding environment to obtain independent images of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, that is, obtaining a benchmark model of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, wherein the benchmark model includes shape parameters, grayscale parameters, and position parameters.

[0042] In the above technical solution, manual processing and separation are used when establishing the benchmark model in the early stage. Although it takes some manpower and time in the early stage, after the establishment is completed, the benchmark models of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers are stored in the video analysis device. Each time the video image obtained by the inspection is processed, only the corresponding benchmark model needs to be called, which significantly improves the accuracy and analysis efficiency for the later inspection application. When the surrounding environment of a certain segment changes, only the benchmark model of the segment needs to be updated accordingly.

[0043] Specifically, the method for establishing the benchmark model includes enhancement processing, denoising processing, and edge detection. Specific options: set the gray value interval to [a, c], enhance the pixels within the gray value interval [a, c], and keep the gray values ​​of the pixels outside the gray value interval [a, c] unchanged, wherein the gray value interval [a, c] is set as the pixel points of the transmission line, so that the image of the transmission line in the image sequence is enhanced; the gray value interval [a, c] is set as the pixel points of the attachment, so that the image of the attachment in the image sequence is enhanced, so that when processing the same frame image sequence, different targeted enhancement processing outputs are obtained;

[0044] Set the denoising threshold T and the neighborhood range S, calculate the difference between the average grayscale value of a certain pixel and each pixel in its neighborhood range S, if the difference is greater than the denoising threshold T, then use the average value to replace the grayscale value of the pixel at the point, if the difference is not greater than the denoising threshold T, then the grayscale value of the pixel at the point remains unchanged, which plays a role in removing random noise. At the same time, due to the setting of the denoising threshold T, the edge information blur of the transmission line in the image can be reduced; the setting of the denoising threshold T can be the same, or it can be set separately according to the different attachments;

[0045] The Sobel operator is the preferred choice for edge detection. The Sobel operator is obtained by convolution based on the grayscale value gradient change. Therefore, it can be organically combined with the previous enhancement processing and denoising processing to improve the accuracy of edge detection, thereby providing a basis for the subsequent calculation of the grayscale value differences of each transmission line and its accessories.

[0046] In another technical solution, the route setting method for obtaining the video image captured by the high-definition camera carried by the drone in step S1 includes: the drone pre-flies from the starting section to the end section, the high-definition camera synchronously obtains the corresponding video image, and the drone stands by at the end section;

[0047] Select the video images in which the grayscale value difference between the image of the power line and its accessories and its surrounding environment is less than a preset threshold, adjust the flight direction of the UAV from the end segment to the starting segment and the shooting direction of the high-definition camera to obtain the video image again, and repeatedly compare the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image until the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image obtained in the one-way flight route of the UAV is not less than the preset threshold, so as to obtain the flight route of the UAV.

[0048] In the above technical solution, due to the long-distance power transmission and the fact that the transmission lines usually pass through complex and changeable adverse areas such as hills, mountains, forests, lakes, and large rivers, it is inevitable that flying and shooting from only one direction and angle cannot meet the complete acquisition of the transmission lines and their accessories within the entire inspection range. Therefore, when designing the flight route, the flight direction and angle, as well as the shooting angle, are adjusted according to the actual situation. Ultimately, a complete video image of the transmission line and its accessories can be obtained in one inspection flight, thereby improving the inspection efficiency.

[0049] Based on the same inventive concept, the present invention also provides a video analysis device based on drone power inspection. The video analysis device based on drone power inspection can be a personal computer, a server, or other devices that implement the aforementioned video analysis method based on drone power inspection.

[0050] The video analysis device based on UAV power inspection includes:

[0051] An image acquisition module, which is used to acquire the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone;

[0052] The image processing module is used to divide the current video image into multiple sections according to the preset nodes, select at least one frame of image sequence from each section of the video image, and adjust the selected image sequence according to the preset orientation, size and light intensity, and then call the preset transmission line and its accessories benchmark model as the benchmark analysis to identify the image of the transmission line and its accessories in the current video image, and calculate its shape parameter value, gray parameter value and position parameter value accordingly; the inspection range is divided into multiple sections according to the geographical location order, and each inspection range corresponds to a section of the video image. Since the video image is a continuous multi-frame static image sequence, at least one frame of image matching the geographical location of each inspection range is selected from each section of the video image, thereby saving a lot of video image processing and significantly improving processing efficiency. Although the drone flies according to the preset route, so that the orientation and angle of each shooting are basically the same, due to weather reasons (different wind force and light intensity), it cannot remain exactly the same. Therefore, the orientation, size and light intensity of the selected image sequence are fine-tuned to improve accuracy. Then, grayscale enhancement processing, smoothing and denoising processing, straight line extraction, edge detection, etc. are performed on each frame of the selected image sequence to obtain a processed image of the power transmission line and its accessories in each frame of the image sequence, and its corresponding shape parameter value, grayscale parameter value and position parameter value;

[0053] The difference output module is used to calculate the shape difference, grayscale difference and position difference of the image shape parameter value, grayscale parameter value and position parameter value of the transmission line and its accessories in the current video image obtained by identification and the corresponding image shape parameter value, grayscale parameter value and position parameter value of the transmission line and its accessories obtained in the previous inspections. When the shape difference or grayscale difference calculation reaches the corresponding preset threshold, the corresponding section video image and difference position are output. The thresholds of the image shape difference, grayscale difference and position difference of the transmission line and its accessories are adjusted and set according to the actual situation. When one of the shape parameter value, grayscale parameter value and position parameter value is greater than the corresponding threshold, it means that in the current inspection result, the transmission line and its accessories have a large change from the previous inspection result or the previous inspection results. This change may be due to wear and loss of insulators, broken wire strands, missing anti-vibration hammers, dirt attached to the wires, etc., so that the corresponding one-frame image sequence and section video image can be selected and output for further verification. In order to avoid accidental inspection errors, and some faults require a certain amount of time to accumulate before they can be distinguished (such as insulator wear and dirt attached to the wire), the inspection results of the previous several times are also selected as comparison objects during calculation. In addition, in order to further improve the accuracy of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the transmission line and its accessories, a benchmark model is accurately pre-set for the video images of each inspection range with different geographical locations in the early stage. The benchmark model includes specific calculation parameters for grayscale enhancement processing, smoothing denoising processing, straight line extraction, and edge detection. Because the geographical location is different, the surrounding environment presented in the transmission line and its accessories is also different, and the form of the transmission line and its accessories in each video image is also different. In addition, since the video image of each section is processed separately, only one or several frames of image sequences are selected in each video image. Therefore, it will not only not increase the consumption of computer resources, but also enable multiple video images to be processed simultaneously, significantly improving the image processing efficiency.

[0054] In the above technical solution, by dividing the video images obtained by the inspection into multiple sections of video images, and then extracting a sequence of one or more frames of images that match the geographical location from the section video images, the processing amount of the video images can be significantly reduced, saving the consumption of computer resources. After that, due to the small amount of image sequences, the computer can simultaneously process and analyze multiple frame image sequences, thereby significantly improving the image processing efficiency. Then, by pre-setting a benchmark model for each section of the inspection range based on the geographical location differences in the early stage, the noise caused by the different shapes of the surrounding environment, power lines and their accessories can be filtered out, thereby significantly improving the accuracy of video analysis.

[0055] All relevant contents of each step involved in the aforementioned embodiment of the video analysis method based on drone power inspection can be referred to the functional description of the functional module corresponding to the video analysis device based on drone power inspection in the embodiment of the present application, and will not be repeated here.

[0056] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0057] The present invention also provides a video analysis system based on UAV power inspection, comprising:

[0058] A drone equipped with a flight control system, a high-definition camera, and a wireless transmission system, wherein the high-definition camera is used to capture video images of the power transmission line and its surroundings;

[0059] A ground remote control system, which is in communication with the flight control system, and is used to control the UAV to fly according to a flight route;

[0060] Video analysis device based on UAV power inspection;

[0061] A display is connected to the ground remote control system and the video analysis device, and the display is used to display the video images received by the video analysis device, the flight data of the flight control system and the ground remote control system, and the output of the video analysis device. In the above technical solution, the UAV is controlled by the ground remote control system to fly according to the flight route under the control of the flight control system, and the high-definition camera correspondingly captures the video images of the power transmission line and its surrounding environment; the video images of the power transmission line and its surrounding environment are transmitted to the video analysis device through a wireless transmission system; the video analysis device analyzes and processes the video images of the power transmission line and its surrounding environment, and then displays them on the display for the operator to view.

[0062] The present invention also provides an electronic device, comprising: at least one processor, and a memory connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor executes the above-mentioned video analysis method based on UAV power inspection. The electronic device can be any terminal device including a mobile phone, a laptop computer, a desktop computer, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a vehicle-mounted computer, etc.

[0063] The present invention also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned video analysis method based on unmanned aerial vehicle power inspection is implemented.

[0064] Through the description of the above implementation mode, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present invention, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, RandomAccess Memory), a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0065] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A video analysis method based on UAV power inspection, characterized in that: The following steps are involved: S1, obtaining the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone; S2. Segment the current video image into multiple sections of video images according to preset nodes, select at least one frame of image sequence from each section of the video image, and adjust the selected image sequence according to the preset orientation, size and light intensity, and then call the preset benchmark model of the power transmission line and its accessories as the benchmark analysis to obtain the image of the power transmission line and its accessories in the current video image, and calculate its shape parameter value, grayscale parameter value and position parameter value accordingly; S3, respectively, calculating the shape difference, grayscale difference and position difference of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories in the current video image obtained by identification and the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the corresponding power transmission line and its accessories obtained in previous inspections, and when the shape difference or grayscale difference calculation reaches the corresponding preset threshold, output the corresponding section video image and difference position; The transmission line and its accessories include transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers; The method for establishing the benchmark model specifically includes: manually processing and separating the transmission line and its accessories in each section of the video image, and eliminating the surrounding environment to obtain independent images of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, that is, obtaining a benchmark model of the transmission line, anti-vibration hammer accessories, spacer rod accessories, insulator accessories, and transmission towers, wherein the benchmark model includes shape parameters, grayscale parameters, and position parameters.

2. The video analysis method based on UAV power inspection as claimed in claim 1 is characterized in that: The method of establishing the benchmark model includes enhancement processing, denoising processing and edge detection; The enhancement process includes: setting the gray value interval to [a, c], enhancing the pixel points within the gray value interval [a, c], and keeping the gray value of the pixel points outside the gray value interval [a, c] unchanged; wherein the gray value interval [a, c] is adaptively set to the pixel points of the transmission line and its accessories; The denoising process includes: setting a denoising threshold T and a neighborhood range S, calculating the difference between a certain point pixel and the average value of the grayscale values ​​of each pixel in its neighborhood range S, if the difference is greater than the denoising threshold T, then replacing the grayscale value of the point pixel with the average value, if the difference is not greater than the denoising threshold T, then the grayscale value of the point pixel remains unchanged; The edge detection adopts the Sobel operator edge detection method.

3. The video analysis method based on UAV power inspection as claimed in claim 1 is characterized in that: The route setting method for the drone equipped with a high-definition camera to shoot video images in step S1 includes: the drone pre-flies from the starting section to the end section, the high-definition camera synchronously obtains the corresponding video image, and the drone stands by at the end section; Select the video images in which the grayscale value difference between the image of the power line and its accessories and its surrounding environment is less than a preset threshold, adjust the flight direction of the UAV from the end segment to the starting segment and the shooting direction of the high-definition camera to obtain the video image again, and repeatedly compare the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image until the grayscale value difference between the image of the power line and its accessories and its surrounding environment in the video image obtained in the one-way flight route of the UAV is not less than the preset threshold, so as to obtain the flight route of the UAV.

4. A video analysis device for executing the video analysis method based on UAV power inspection according to any one of claims 1 to 3, characterized in that: include: An image acquisition module, which is used to acquire the current video image of the power transmission line and its surrounding environment taken by the high-definition camera carried by the drone; An image processing module is used to divide the current video image into multiple sections according to preset nodes, select at least one frame of image sequence from each section of the video image, and adjust the selected image sequence according to the preset orientation, size and light intensity, and then call the preset benchmark model of the power transmission line and its accessories as the benchmark analysis to obtain the image of the power transmission line and its accessories in the current video image, and calculate its shape parameter value, gray parameter value and position parameter value accordingly; The difference output module is used to calculate the shape difference, grayscale difference and position difference of the image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories in the current video image obtained by identification and the corresponding image shape parameter values, grayscale parameter values ​​and position parameter values ​​of the power transmission line and its accessories obtained in the previous inspections. When the shape difference or grayscale difference calculation reaches the corresponding preset threshold, the corresponding section video image and difference position are output.

5. The video analysis system based on UAV power inspection is characterized by: include: A drone equipped with a flight control system, a high-definition camera, and a wireless transmission system, wherein the high-definition camera is used to capture video images of the power transmission line and its surroundings; A ground remote control system, which is in communication with the flight control system, and is used to control the UAV to fly according to a flight route; The video analysis device as claimed in claim 4; A display is connected to the ground remote control system and the video analysis device, and the display is used to display the video images received by the video analysis device, the flight data of the flight control system and the ground remote control system, and the output of the video analysis device.

6. An electronic device, characterized in that include: one or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising a method for executing any one of claims 1 to 3.

7. A computer-readable storage medium, characterized in that A computer program stored in a computer program used in combination with an electronic device, wherein the computer program can be executed by a processor to implement the method described in any one of claims 1 to 3.