CN116645620A - High-precision power grid unmanned aerial vehicle inspection image defect identification method and system - Google Patents
High-precision power grid unmanned aerial vehicle inspection image defect identification method and system Download PDFInfo
- Publication number
- CN116645620A CN116645620A CN202310487646.6A CN202310487646A CN116645620A CN 116645620 A CN116645620 A CN 116645620A CN 202310487646 A CN202310487646 A CN 202310487646A CN 116645620 A CN116645620 A CN 116645620A
- Authority
- CN
- China
- Prior art keywords
- image
- inspection
- unmanned aerial
- aerial vehicle
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 113
- 230000007547 defect Effects 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000009467 reduction Effects 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000012423 maintenance Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 13
- 230000009471 action Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000035800 maturation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a high-precision power grid unmanned aerial vehicle inspection image defect recognition method and system, comprising the steps of firstly, unmanned aerial vehicle flight shooting and uploading flight image data, secondly, unmanned aerial vehicle data acquisition more accurate inspection target images are adjusted according to the flight images, thirdly, noise reduction and denoising processing is carried out on the acquired inspection target images through a Kalman filtering method and a multi-threshold denoising method combining Bayes Shrink threshold and Window Shrink threshold, meanwhile, image feature extraction processing is carried out on the basis of wavelet packet transformation and mathematical morphology methods, fourth, comparison judgment is carried out on the processed images and fault models, recognition results are output, and maintenance is arranged after classification statistics; according to the invention, the image acquired by the unmanned aerial vehicle is subjected to noise reduction and denoising treatment and then is subjected to feature extraction, so that the influence of factors such as environmental weather and the like on the shot image is effectively eliminated, and then the shot image is compared with the fault defect model to identify the inspection target defect type, so that the identification result is more accurate, the identification efficiency is higher, meanwhile, the fault image database of the system is self-updated, and the database is automatically updated and expanded when the new fault type is identified, so that the subsequent fault comparison efficiency is higher.
Description
Technical Field
The invention relates to the technical field of inspection of unmanned aerial vehicles of power grids, in particular to a high-precision inspection image defect identification method and system of unmanned aerial vehicles of power grids.
Background
With the development of society and the rising of new energy carriers, the demands of people for electric power are increased year by year, so that it is particularly important to ensure the safety and smoothness of a power transmission network, the density of a high-voltage power transmission network is continuously increased along with the maturation of an ultra-high voltage technology, so that the electric power inspection task is heavy, and with the gradual maturation of an unmanned aerial vehicle technology, the difficulty of geographic factors can be overcome and the inspection efficiency can be greatly improved by using the unmanned aerial vehicle for electric power inspection instead of manual electric power inspection;
the invention provides a method and a system for identifying the defects of an inspection image of a high-precision power grid unmanned aerial vehicle, which are used for solving the problems in the prior art.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a high-precision power grid unmanned aerial vehicle inspection image defect recognition method and system.
In order to achieve the purpose of the invention, the invention is realized by the following technical scheme: a high-precision power grid unmanned aerial vehicle inspection image defect identification method comprises the following steps:
step one, acquiring images, namely acquiring image data of an inspection object by the inspection unmanned aerial vehicle based on an unmanned aerial vehicle inspection route and a navigation point after flying to a specified position, and uploading the image data;
step two, unmanned aerial vehicle adjustment, after the electric power inspection defect detection system receives the image data of the inspection object, whether the inspection object exists in the image is identified, adaptive adjustment is carried out on the inspection unmanned aerial vehicle and a camera, and the camera shoots and acquires a more accurate and clear inspection object image;
step three, image processing, namely performing noise reduction and denoising processing on the shot clear image through the power inspection defect detection system, and then performing feature extraction on the image to obtain an inspection object feature map;
step four, image comparison and judgment, namely comparing the processed inspection object feature image with a fault defect model of the system, and judging and outputting a fault defect identification result;
and fifthly, classifying, counting and arranging maintenance, namely classifying and counting fault results after all the inspection waypoints on the inspection waylines are inspected and judged by the unmanned aerial vehicle to be inspected, and analyzing and arranging fault defect maintenance according to the statistic results.
The further improvement is that: in the second step, when the inspection target object is identified in the image, the electric inspection defect detection system automatically modifies parameters of the current position of the unmanned aerial vehicle, the focal length and the shooting angle of the camera, and focuses the camera on the inspection target object to obtain a clear image; when no inspection target object is identified in the image, the electric power inspection defect detection system analyzes the current image characteristics, compares the current image characteristics with a 3D model of an unmanned aerial vehicle inspection route, and automatically adjusts parameters of the inspection unmanned aerial vehicle position, the focal length of a camera and the shooting angle after the inspection target object position is acquired, so that an image of the clearly inspection target object is acquired.
The further improvement is that: and in the third step, the acquired image is subjected to noise reduction treatment by a Kalman filtering method, and then the noise-reduced image is subjected to noise reduction treatment again by a multi-threshold noise reduction method combining a Bayes Shrink threshold value and a Window Shrink threshold value, so that the noise-reduced image is obtained.
The further improvement is that: the image feature extraction in the third step is realized based on wavelet packet transformation and mathematical morphology, specifically, binary image conversion is carried out on the image after noise reduction and denoising, a binary image is obtained after the conversion, then the binary image is identified by an edge detector, edge description is carried out by combining with mathematical morphology, an edge image is obtained, and finally, a feature image of a patrol object part is extracted from the obtained edge image.
The further improvement is that: the fault defect model in the fourth step is established based on the defect images obtained through history, training and verification, and when the fault defect model is compared, the inspection object feature image obtained in the third step is used as input to be imported into the fault defect model to automatically identify and output the fault defect type and judge the fault defect grade.
The further improvement is that: and in the fifth step, classifying according to the type, the defect type and the defect grade of the inspection object component when classifying and counting.
The unmanned aerial vehicle inspection image defect recognition system comprises an unmanned aerial vehicle control system and an image recognition processing system, wherein the unmanned aerial vehicle control system comprises an unmanned aerial vehicle control module, a GPS module and a photographing module, the unmanned aerial vehicle control module is used for adjusting the course angle, the flight angle and the unmanned aerial vehicle action of the unmanned aerial vehicle according to an inspection route waypoint and an adjustment control instruction, the GPS module is used for positioning the unmanned aerial vehicle position in real time based on Beidou satellites, and the photographing module is used for realizing inspection obstacle avoidance recognition and inspection object picture acquisition based on an unmanned aerial vehicle camera;
the image recognition processing system comprises an image preprocessing module, a fault defect comparison module and a fault defect classification module, wherein the image preprocessing module is used for carrying out noise reduction and feature extraction on an obtained image, the fault defect comparison module is used for carrying out comparison recognition and judgment on an obtained inspection object feature map based on a fault defect model, and the fault defect classification module is used for carrying out classification statistics on fault defects of an inspection object according to recognition judgment results.
The further improvement is that: the photographing module comprises a camera control submodule, wherein the camera control submodule is used for controlling the focal length, photographing angle, focusing action and photographing and shooting action of a camera; the fault defect comparison module comprises a fault picture database and an extraction comparison sub-module, wherein the fault picture database is based on a data set established by a component fault type picture obtained through history, and the extraction comparison sub-module is used for extracting a history fault picture of a component of the same type from the fault picture database, comparing the history fault picture with a component fault picture to be identified and judging a fault type.
The beneficial effects of the invention are as follows: according to the invention, the image acquired by the unmanned aerial vehicle is subjected to noise reduction and denoising treatment and then is subjected to feature extraction, so that the influence of factors such as environmental weather and the like on the shot image is effectively eliminated, and then the shot image is compared with the fault defect model to identify the inspection target defect type, so that the identification result is more accurate, the identification efficiency is higher, meanwhile, the fault image database of the system is automatically updated and expanded when a new fault type is identified, the subsequent fault comparison efficiency is higher, and a high-precision and high-efficiency identification method is provided for the inspection unmanned aerial vehicle image treatment.
Drawings
FIG. 1 is a flow chart of a method according to embodiment 1 of the present invention.
Fig. 2 is a system architecture diagram of embodiment 2 of the present invention.
Description of the embodiments
The present invention will be further described in detail with reference to the following examples, which are only for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Examples
According to the embodiment shown in fig. 1, a method for identifying defects of a high-precision inspection image of a power grid unmanned aerial vehicle is provided, which comprises the following steps:
step one, acquiring images, namely acquiring image data of an inspection object by the inspection unmanned aerial vehicle based on the unmanned aerial vehicle inspection route and the navigation point after flying to a specified position, and uploading the image data.
Step two, unmanned aerial vehicle adjustment, after the electric power inspection defect detection system receives the image data of the inspection object, whether the inspection object exists in the image is identified, adaptive adjustment is carried out on the inspection unmanned aerial vehicle and a camera, and the camera shoots and acquires a more accurate and clear inspection object image;
when the inspection target object is identified in the image, the electric power inspection defect detection system automatically modifies parameters of the current position of the unmanned aerial vehicle, the focal length of the camera and the shooting angle, and focuses the camera on the inspection target object to obtain a clear image;
when no inspection target object is identified in the image, the electric power inspection defect detection system analyzes the current image characteristics, compares the current image characteristics with a 3D model of an unmanned aerial vehicle inspection route, and automatically adjusts parameters of the inspection unmanned aerial vehicle position, the focal length of a camera and the shooting angle after the inspection target object position is acquired, so that an image of the clearly inspection target object is acquired.
Step three, image processing, namely performing noise reduction and denoising processing on the shot clear image through the power inspection defect detection system, and then performing feature extraction on the image to obtain an inspection object feature map;
because the image shot by the unmanned aerial vehicle is influenced by other factors such as environmental weather or an electric field, the image is interfered with unclear, the image is required to be subjected to noise reduction and denoising treatment, the acquired image is subjected to noise reduction and denoising treatment by a Kalman filtering method during noise reduction and denoising, and then the denoised image is subjected to denoising treatment again by a multi-threshold denoising method combining a Bayes Shrink threshold value and a Window Shrink threshold value, so that the denoised image is obtained;
the multi-threshold denoising method for the Bayes Shrink threshold and the Window Shrink threshold specifically comprises the following steps: let the noise image variance beNoise variance is->The initial image variance is +.>Then there is
Wherein the method comprises the steps ofIs the average value of the low frequency coefficients after wavelet transformation, < >>Image noise variance of (a) is
The variance of the original image is
The original image variance is estimated using bayes srink, then usingCalculate->I.e.
Can obtain shrinkage factor
The denoised ultra wavelet coefficient is
Will beAnd obtaining the denoised image through the inverse conversion of the contourlet.
The image feature extraction is realized based on wavelet packet transformation and mathematical morphology, specifically, the method comprises the steps of firstly carrying out binary image conversion on an image subjected to noise reduction and denoising, obtaining a binary image after the conversion, then carrying out identification processing on the binary image by using an edge detector, carrying out edge description by combining the mathematical morphology, obtaining an edge image, and finally extracting a feature image of a patrol object part from the obtained edge image.
Step four, image comparison and judgment, namely comparing the processed inspection object feature image with a fault defect model of the system, and judging and outputting a fault defect identification result;
firstly acquiring images of a historical fault defect type, then carrying out processing in the step three, after processing, finishing all the images into data sets, then dividing the data sets into a training set and a verification set, then establishing an identification model, firstly acquiring the images of the historical fault defect type when the model is established, then combining the historical judgment results of the corresponding images to obtain an initial fault defect model, wherein the constant value of the initial fault defect model is unknown, firstly training a plurality of groups of historical fault defect type images and the corresponding identification results to obtain a constant value, then importing the constant value into the initial model, and taking the fault defect type images, namely the identification results as unknown values to obtain the fault defect type images;
and then training and verifying by using a training set and a verifying set, wherein the training is to introduce pictures of the training set and corresponding identification results into the model for performing iteration optimization of a constant value, the model after iteration optimization is verified by using the verifying set, the pictures of the verifying set are taken as input during verification, the identification results are output by the model, finally, the identification results are compared with the historical identification results of the pictures corresponding to the verifying set to determine the optimization effect, namely, a fault defect model is obtained, and the inspection object feature map obtained in the third step is taken as input into the fault defect model for automatically identifying and outputting the fault defect type and judging the fault defect grade during comparison.
The fault defect model is internally divided into a plurality of sub-models which are different according to the types of detection objects, such as rust of screws, loosening of screws, falling of screws, overheating and reddening of joints, and the like.
When the detected fault type is not within the definition range of the model data set, the fault defect is manually confirmed by a person, a new fault type data set is automatically created by the system, and a fault defect image is included in the created data set so that the same defect can be generated for comparison later.
And fifthly, classifying, counting and arranging maintenance, namely classifying fault results according to the type of the part to be inspected, the defect type and the defect grade after all the inspection points on the inspection route are inspected and judged by the unmanned aerial vehicle to be inspected, and analyzing and arranging fault defect maintenance according to the counted results.
The image acquired by the unmanned aerial vehicle is subjected to noise reduction and denoising treatment and then is subjected to feature extraction, so that the influence of factors such as environmental weather on a shot picture is effectively eliminated, and then the image is compared with a fault defect model to identify the type of the inspection target defect, so that the identification result is more accurate, and the identification efficiency is higher.
Examples
According to the illustration in fig. 2, this embodiment provides a high accuracy electric wire netting unmanned aerial vehicle inspection image defect identification system, its characterized in that: the unmanned aerial vehicle image processing system comprises an unmanned aerial vehicle control system and an image recognition processing system, wherein the unmanned aerial vehicle control system comprises an unmanned aerial vehicle control module, a GPS module and a photographing module, and the image recognition processing system comprises an image preprocessing module, a fault defect comparison module and a fault defect classification module.
The unmanned aerial vehicle control module is used for adjusting the course angle, the flight angle and the unmanned aerial vehicle action of unmanned aerial vehicle according to the route waypoint of patrolling and examining and regulation control instruction, GPS module is based on big dipper satellite real-time positioning unmanned aerial vehicle position, the module of shooing realizes patrolling and examining the obstacle recognition and patrol and examine the object picture and obtain based on the unmanned aerial vehicle camera, the module of shooing contains camera control submodule, camera control submodule is used for controlling the focus of camera, take a photograph the angle, focus action and take a photograph the action.
The image preprocessing module is used for carrying out noise reduction and feature extraction on the acquired image, the fault defect comparison module is used for carrying out comparison, identification and judgment on the acquired inspection object feature image based on the fault defect model, the fault defect comparison module comprises a fault picture database and an extraction comparison sub-module, the fault picture database is used for establishing a data set based on the historically acquired part fault type picture and has a self-updating function, when the system cannot identify the fault defect type, the system can manually confirm the fault defect, and a new fault type data set is automatically established by the system to bring the fault defect image into the established data set so as to facilitate the subsequent comparison of the same fault.
The extraction comparison sub-module is used for extracting historical fault diagrams of the same type of components from the fault picture database, comparing the historical fault diagrams with the component fault diagrams to be identified and judging the fault types.
And the fault defect classification module is used for carrying out classification statistics on the fault defects of the inspection object according to the identification and judgment results.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The high-precision power grid unmanned aerial vehicle inspection image defect identification method is characterized by comprising the following steps of:
step one, acquiring images, namely acquiring image data of an inspection object by the inspection unmanned aerial vehicle based on an unmanned aerial vehicle inspection route and a navigation point after flying to a specified position, and uploading the image data;
step two, unmanned aerial vehicle adjustment, after the electric power inspection defect detection system receives the image data of the inspection object, whether the inspection object exists in the image is identified, adaptive adjustment is carried out on the inspection unmanned aerial vehicle and a camera, and the camera shoots and acquires a more accurate and clear inspection object image;
step three, image processing, namely performing noise reduction and denoising processing on the shot clear image through the power inspection defect detection system, and then performing feature extraction on the image to obtain an inspection object feature map;
step four, image comparison and judgment, namely comparing the processed inspection object feature image with a fault defect model of the system, and judging and outputting a fault defect identification result;
and fifthly, classifying, counting and arranging maintenance, namely classifying and counting fault results after all the inspection waypoints on the inspection waylines are inspected and judged by the unmanned aerial vehicle to be inspected, and analyzing and arranging fault defect maintenance according to the statistic results.
2. The high-precision power grid unmanned aerial vehicle inspection image defect identification method according to claim 1, wherein the method comprises the following steps of: in the second step, when the inspection target object is identified in the image, the electric inspection defect detection system automatically modifies parameters of the current position of the unmanned aerial vehicle, the focal length and the shooting angle of the camera, and focuses the camera on the inspection target object to obtain a clear image; when no inspection target object is identified in the image, the electric power inspection defect detection system analyzes the current image characteristics, compares the current image characteristics with a 3D model of an unmanned aerial vehicle inspection route, and automatically adjusts parameters of the inspection unmanned aerial vehicle position, the focal length of a camera and the shooting angle after the inspection target object position is acquired, so that an image of the clearly inspection target object is acquired.
3. The high-precision power grid unmanned aerial vehicle inspection image defect identification method according to claim 1, wherein the method comprises the following steps of: and in the third step, the acquired image is subjected to noise reduction treatment by a Kalman filtering method, and then the noise-reduced image is subjected to noise reduction treatment again by a multi-threshold noise reduction method combining a Bayes Shrink threshold value and a Window Shrink threshold value, so that the noise-reduced image is obtained.
4. The high-precision power grid unmanned aerial vehicle inspection image defect identification method according to claim 1, wherein the method comprises the following steps of: the image feature extraction in the third step is realized based on wavelet packet transformation and mathematical morphology, specifically, binary image conversion is carried out on the image after noise reduction and denoising, a binary image is obtained after the conversion, then the binary image is identified by an edge detector, edge description is carried out by combining with mathematical morphology, an edge image is obtained, and finally, a feature image of a patrol object part is extracted from the obtained edge image.
5. The high-precision power grid unmanned aerial vehicle inspection image defect identification method according to claim 1, wherein the method comprises the following steps of: the fault defect model in the fourth step is established based on the defect images obtained through history, training and verification, and when the fault defect model is compared, the inspection object feature image obtained in the third step is used as input to be imported into the fault defect model to automatically identify and output the fault defect type and judge the fault defect grade.
6. The high-precision power grid unmanned aerial vehicle inspection image defect identification method according to claim 1, wherein the method comprises the following steps of: and in the fifth step, classifying according to the type, the defect type and the defect grade of the inspection object component when classifying and counting.
7. A high-precision unmanned aerial vehicle inspection image defect recognition system for a power grid is characterized in that: the unmanned aerial vehicle inspection system comprises an unmanned aerial vehicle control system and an image recognition processing system, wherein the unmanned aerial vehicle control system comprises an unmanned aerial vehicle control module, a GPS module and a photographing module, the unmanned aerial vehicle control module is used for adjusting the course angle, the flight angle and the unmanned aerial vehicle action of an unmanned aerial vehicle according to the inspection route waypoints and the adjustment control instructions, the GPS module is used for positioning the unmanned aerial vehicle position in real time based on Beidou satellites, and the photographing module is used for realizing inspection obstacle avoidance recognition and inspection object picture acquisition based on an unmanned aerial vehicle camera;
the image recognition processing system comprises an image preprocessing module, a fault defect comparison module and a fault defect classification module, wherein the image preprocessing module is used for carrying out noise reduction and feature extraction on an obtained image, the fault defect comparison module is used for carrying out comparison recognition and judgment on an obtained inspection object feature map based on a fault defect model, and the fault defect classification module is used for carrying out classification statistics on fault defects of an inspection object according to recognition judgment results.
8. The high-precision power grid unmanned aerial vehicle inspection image defect recognition system according to claim 7, wherein: the photographing module comprises a camera control submodule, wherein the camera control submodule is used for controlling the focal length, photographing angle, focusing action and photographing and shooting action of a camera; the fault defect comparison module comprises a fault picture database and an extraction comparison sub-module, wherein the fault picture database is based on a data set established by a component fault type picture obtained through history, and the extraction comparison sub-module is used for extracting a history fault picture of a component of the same type from the fault picture database, comparing the history fault picture with a component fault picture to be identified and judging a fault type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310487646.6A CN116645620A (en) | 2023-05-04 | 2023-05-04 | High-precision power grid unmanned aerial vehicle inspection image defect identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310487646.6A CN116645620A (en) | 2023-05-04 | 2023-05-04 | High-precision power grid unmanned aerial vehicle inspection image defect identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116645620A true CN116645620A (en) | 2023-08-25 |
Family
ID=87639005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310487646.6A Pending CN116645620A (en) | 2023-05-04 | 2023-05-04 | High-precision power grid unmanned aerial vehicle inspection image defect identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116645620A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197700A (en) * | 2023-11-07 | 2023-12-08 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
| CN117612047A (en) * | 2024-01-23 | 2024-02-27 | 国网湖北省电力有限公司信息通信公司 | Unmanned aerial vehicle inspection image recognition method for power grid based on AI large model |
| CN117807558A (en) * | 2024-02-26 | 2024-04-02 | 武汉邢仪新未来电力科技股份有限公司 | Comprehensive fault detection method, system and storage medium for power transmission line |
-
2023
- 2023-05-04 CN CN202310487646.6A patent/CN116645620A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197700A (en) * | 2023-11-07 | 2023-12-08 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
| CN117197700B (en) * | 2023-11-07 | 2024-01-26 | 成都中轨轨道设备有限公司 | Intelligent unmanned inspection contact net defect identification system |
| CN117612047A (en) * | 2024-01-23 | 2024-02-27 | 国网湖北省电力有限公司信息通信公司 | Unmanned aerial vehicle inspection image recognition method for power grid based on AI large model |
| CN117612047B (en) * | 2024-01-23 | 2024-04-12 | 国网湖北省电力有限公司信息通信公司 | Unmanned aerial vehicle inspection image recognition method for power grid based on AI large model |
| CN117807558A (en) * | 2024-02-26 | 2024-04-02 | 武汉邢仪新未来电力科技股份有限公司 | Comprehensive fault detection method, system and storage medium for power transmission line |
| CN117807558B (en) * | 2024-02-26 | 2024-05-03 | 武汉邢仪新未来电力科技股份有限公司 | Comprehensive fault detection method, system and storage medium for power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116645620A (en) | High-precision power grid unmanned aerial vehicle inspection image defect identification method and system | |
| CN108647655B (en) | Low-altitude aerial image power line foreign matter detection method based on light convolutional neural network | |
| CN109753929B (en) | High-speed rail insulator inspection image recognition method | |
| CN110570454B (en) | Method and device for detecting foreign matter invasion | |
| Ghanta et al. | Wavelet domain detection of rust in steel bridge images | |
| CN108804992B (en) | Crowd counting method based on deep learning | |
| CN111507145A (en) | Method, system and device for detecting barrier at storage position of embedded vehicle-mounted all-round looking system | |
| CN109360179B (en) | Image fusion method and device and readable storage medium | |
| CN109460722B (en) | Intelligent license plate recognition method | |
| CN111079724B (en) | Unmanned aerial vehicle-based sea floating garbage identification method | |
| CN113177947B (en) | Multi-module convolutional neural network-based complex environment target segmentation method and device | |
| WO2020238790A1 (en) | Camera positioning | |
| Kenk et al. | Visibility enhancer: adaptable for distorted traffic scenes by dusty weather | |
| CN113569981A (en) | Power inspection bird nest detection method based on single-stage target detection network | |
| Nejati et al. | License plate recognition based on edge histogram analysis and classifier ensemble | |
| CN111915558A (en) | Pin state detection method for high-voltage transmission line | |
| Zotin et al. | Animal detection using a series of images under complex shooting conditions | |
| CN117197700B (en) | Intelligent unmanned inspection contact net defect identification system | |
| CN111340833B (en) | Power transmission line extraction method for least square interference-free random Hough transformation | |
| CN117409083A (en) | Cable terminal identification method and device based on infrared image and improved YOLOV5 | |
| CN112949584A (en) | Image screening method and device, electronic equipment and storage medium | |
| CN108288041B (en) | Preprocessing method for removing false detection of pedestrian target | |
| CN116665077A (en) | Power transmission line detection shooting method and system based on AI (advanced identification) recognition technology | |
| CN115272284A (en) | Power transmission line defect identification method based on image quality evaluation | |
| Bhupathi et al. | An augmented sliding window technique to improve detection of curved lanes in autonomous vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |