CN110910341B - Method and device for detecting defects of rusted areas of power transmission line - Google Patents
Method and device for detecting defects of rusted areas of power transmission line Download PDFInfo
- Publication number
- CN110910341B CN110910341B CN201910823411.3A CN201910823411A CN110910341B CN 110910341 B CN110910341 B CN 110910341B CN 201910823411 A CN201910823411 A CN 201910823411A CN 110910341 B CN110910341 B CN 110910341B
- Authority
- CN
- China
- Prior art keywords
- image
- target
- rust
- hardware
- area
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000005540 biological transmission Effects 0.000 title claims abstract description 43
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims abstract description 53
- 238000007689 inspection Methods 0.000 claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000012549 training Methods 0.000 description 4
- 230000006378 damage Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method for detecting defects of a rust area of a power transmission line, which comprises the following steps: acquiring aerial images and inertial navigation information data; determining the geographic coordinates of each image through the time information of the inertial navigation data of the unmanned aerial vehicle and the time information of the aerial image; detecting hardware fitting by using a deep convolutional neural network model, screening an image containing the hardware fitting as a target image, and simultaneously giving out information of an external rectangular area of a hardware fitting target; dividing the target circumscribed rectangular area to obtain a target small image; carrying out graying treatment on the target small image by adopting a hyper red method; a rust area is obtained by adopting a threshold method; adopting a connected domain to calculate to obtain a rust defect detection image; and generating a patrol defect report. The invention has the beneficial effects that: and (3) carrying out foreground segmentation on the inspection data image, eliminating background interference, and detecting rust defects by using a reddish method, so that the rapid detection of hardware rust is realized, and the defect analysis efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of power transmission line detection, and particularly relates to a method and a device for detecting defects of a rust area of a power transmission line.
Background
The transmission line contains various metal parts, including hardware tools such as damper, which can be operated in the field for a long time, and is corroded by various severe environments, so that corrosion damage is easy to occur, and great harm is caused to the safe operation of the transmission line.
The development of modern remote sensing technology and remote sensing data acquisition modes, especially the rapid development of unmanned aerial vehicle application, provides a safe, rapid and effective mode for the fine inspection of small targets of transmission line equipment, and enables us to conveniently acquire image data of small target areas of the transmission line equipment. For a large amount of image data generated by once inspection of the power transmission line, an intelligent defect identification method is provided, the problems of manually reading pictures and recording defects are solved by using a computer vision method, the inspection efficiency is greatly improved, and the labor and time are saved.
In the paper "detection of rusted region of power transmission line based on color and texture features" (Dai Yujing, etc., industrial control computer, 2018, 09), a detection method of rusted region of power transmission line based on color and texture features is provided for the problems of complex background and lack of effective detection means of rusted defect of power transmission line. Because the rust generated by important parts in the high-voltage transmission line is red, the rust has more remarkable color characteristics, the rust and other areas are distinguished by setting S component and H component thresholds of the HIS color model, and the rust area and the non-rust area are further distinguished by analyzing the texture characteristics of the rust.
In the paper 'study of a helicopter inspection transmission line rust defect recognition method' (Zhang Hongcai, university of Dalian maritime, 2009), aiming at the complexity and rust characteristics of aerial images, converting a color image with rust into a gray image, comparing different image graying methods, applying a hyper-red method proposed by the paper to carry out graying on the rust image, applying a plurality of rust gray images to carry out least square fitting on errors existing in a graying image threshold segmentation method, determining a segmentation threshold range of rust defects according to fitting data, segmenting the image by using a threshold determined by a maximum inter-class variance method constrained by the segmentation threshold range, carrying out morphological processing on the segmented rust area, extracting geometric features of the segmentation area, removing the segmented non-rust area, marking the rust area as red in the color image, and determining rust parts through geometric feature analysis, thereby realizing the transmission line rust defect recognition system.
However, in the prior art, complex background interference parts are not removed, hardware targets such as damper in a power transmission line are not considered, whether a large number of aerial images have hardware components is not judged, rust detection is directly carried out on the basis of the images, screening of target images of a large number of data and rapid and accurate positioning of target areas are not realized, and the safety operation of the power transmission line is greatly compromised.
Disclosure of Invention
In view of the above, the present invention is directed to a method for detecting defects in a rusted area of a power transmission line, so as to solve the above-mentioned drawbacks.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
a defect detection method for a rust area of a power transmission line comprises the following steps:
A. acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
B. b, obtaining time information of inertial navigation data of the unmanned aerial vehicle and time information of aerial images through the data obtained in the step A, determining geographic coordinates of each image, and randomly selecting a power transmission line section to be analyzed according to the geographic coordinates;
C. b, detecting hardware fittings on the image obtained in the step B by using a deep convolutional neural network model, screening the image containing the hardware fittings as a target image, and simultaneously giving out information of an external rectangular area of a hardware fitting target;
D. c, dividing the target circumscribed rectangular area obtained in the step C to obtain a target small image;
E. d, carrying out graying treatment on the target small image obtained in the step D by adopting a hyper red method;
F. e, obtaining a rust area in the gray level image obtained in the step E by adopting a threshold method;
G. f, carrying out connected domain calculation on the rusted area in the step F to obtain a rusted defect detection image;
H. deleting a part with small area accounting for the target image and a part with large length-width ratio from the image obtained in the step G;
I. generating a patrol defect report;
J. and forwarding the original inspection data and the inspection defect report which are stored in the inspection.
Further, the determining the geographic coordinates of each image in the step B includes: numbering the aerial images according to the time sequence, and corresponding the aerial images to inertial navigation information according to the time axis to obtain a matching list of inertial navigation data and the images, so that geographic coordinates of each image are determined according to the inertial navigation information.
In the step D, the target circumscribed rectangular area is used as an initial area, and 50 pixels are extended in the up-down, left-right directions of the border of the target circumscribed rectangular area, and then segmentation is performed.
Further, the dividing process in the step D is as follows: c, using the target circumscribed rectangular area detected in the step C as a foreground target, using all pixels outside the area as a background, and modeling the target and the background by using a full covariance mixed Gaussian model with k=5 Gaussian components to finish the segmentation.
Furthermore, the target small image obtained in the step D is reacted by the reddish method in the step E, and the gray image is obtained by calculating the color component formula 2R-G-B.
In addition, based on the method for detecting the defects of the rusted areas of the power transmission line, the invention also provides a device for detecting the defects of the rusted areas of the power transmission line, which comprises the following steps:
the data acquisition unit is used for acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
the aerial image positioning unit is used for determining the geographic coordinates of each image in the data acquisition unit;
the hardware target detection unit is used for screening the image containing the hardware in the aerial image positioning unit and giving out information of an external rectangular area of the hardware target;
the hardware fitting region foreground target segmentation unit is used for segmenting the target circumscribed rectangular region obtained in the hardware fitting target detection unit to obtain a target small image;
the hardware target rust analysis unit is used for performing rust analysis on the target small image obtained by the hardware region foreground target segmentation unit to obtain a patrol defect report;
and the routing inspection data and rust defect analysis report forwarding unit is used for forwarding the original routing inspection data and the routing inspection defect report.
Compared with the prior art, the method for detecting the defects of the rust area of the power transmission line has the following advantages:
(1) According to the defect detection method for the rust area of the power transmission line, through the technology of matching the recording time of inertial navigation data with the image shooting time, the geographic position coordinates in the flight path of the unmanned aerial vehicle are corresponding to the aerial images, so that the images can be rapidly positioned on the actual power transmission line on the basis of not carrying out image stitching on a large number of aerial images, the defect finding speed is improved on one hand, the data are queried and stored in a mode of matching with the inertial navigation information on the other hand, the data storage mode is standardized, and the effective management of a large number of aerial images is facilitated; meanwhile, foreground segmentation is carried out on the inspection data image, background interference is removed, rust defect detection is carried out by using a reddish method, quick detection of rust of hardware fittings such as a damper is realized, and defect analysis efficiency is improved;
(2) The method for detecting the defects of the rust areas of the power transmission line can realize the target detection and target image selection of the hardware tools such as the damper and the like on the inspected image, support the rapid analysis of the rust defects and the rust defect marks of the hardware tools such as the damper and the like on the inspected image, automatically position the pole tower area according to the matching relation between the image and inertial navigation, and generate a defect report by combining the rust defect analysis result. The original inspection data such as images, telemetering information and the like stored in inspection are forwarded through network transmission equipment or a data line;
(3) Aiming at the defect of eliminating complex background interference parts, the method for detecting the defects of the rusted area of the power transmission line provided by the invention provides a Grabcut image segmentation method for extracting parts, eliminating the interference of most background factors, and further eliminating the background by utilizing color features, geometric features and the like, so that the rusted detection result is maximized to reflect the parts of the parts.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
fig. 1 is a block diagram of a defect detection device for a rust area of a power transmission line according to an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The invention will be described in detail below with reference to the drawings in connection with embodiments.
A defect detection method for a rust area of a power transmission line comprises the following steps:
A. acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
B. the data obtained in the step A are obtained, the geographic coordinates of each image are determined through the time information of the inertial navigation data of the unmanned aerial vehicle and the time information of the aerial image, and the power transmission line section to be analyzed is selected at will according to the geographic coordinates;
C. b, detecting hardware fittings on the image obtained in the step B by using a deep convolutional neural network model, screening the image containing the hardware fittings as a target image, and simultaneously giving out information of an external rectangular area of a hardware fitting target;
D. c, dividing the target circumscribed rectangular area obtained in the step C to obtain a target small image;
E. d, carrying out graying treatment on the target small image obtained in the step D by adopting a hyper red method;
F. e, obtaining a rust area in the gray level image obtained in the step E by adopting a threshold method;
G. f, carrying out connected domain calculation on the rusted area in the step F to obtain a rusted defect detection image;
H. deleting a part with small area accounting for the target image and a part with large length-width ratio from the image obtained in the step G;
I. generating a patrol defect report;
J. and forwarding the original inspection data such as the aerial image, the telemetering information and the like stored in the inspection and the inspection defect report.
The process of determining the geographic coordinates of each image in the step B is as follows: numbering the aerial images according to the time sequence, and corresponding the aerial images to inertial navigation information according to the time axis to obtain a matching list of inertial navigation data and the images, so that geographic coordinates of each image are determined according to the inertial navigation information.
The deep convolutional neural network model building process in the step C is as follows: establishing a hardware fitting sample database, and marking the position information of a target image; training the model through a training set and a testing set obtained by marking data; after training the model, performing image detection test, and finally giving out the information of the circumscribed rectangular area of the hardware target. During model training, multi-scale images are randomly introduced to improve the detection capability of the model on hardware fittings with different sizes; the generalization capability of the model in different scenes is improved by means of random illumination change, image rotation, mirror image, random partial shielding and the like; the model reaches the global optimization state through the methods of model transfer learning, parameter fine tuning and the like.
The method comprises the steps of C, establishing a deep convolution neural network model, namely, performing prediction by adopting a multi-scale feature fusion mode, adopting a result after feature fusion of different feature layers, adopting a multi-layer feature map, performing a new prediction on each feature map, obtaining a feature map of each layer on the basis, performing up-sampling on the small feature map by adopting a top-down method, then fusing with the next feature map, performing prediction, and combining with faster-rcnn and ssd, and performing the combination of semantic information of a high layer and position information of a low layer, thereby achieving a remarkable effect in the aspect of small target detection.
In the step D, the target circumscribed rectangular area is used as an initial area, and 50 pixels are respectively expanded in the up-down, left-right directions of the frame of the target circumscribed rectangular area, and then segmentation is performed.
The segmentation process in the step D is as follows: c, using the target circumscribed rectangular area detected in the step C as a foreground target, using all pixels outside the area as a background, and modeling the target and the background by using a full covariance mixed Gaussian model with k=5 Gaussian components to finish the segmentation.
And E, reacting the target small image obtained in the step D by adopting a super red method, and calculating a color component formula 2R-G-B to obtain a gray image.
In addition, based on the method for detecting the defects of the rusted areas of the power transmission line, as shown in fig. 1, the invention also provides a device for detecting the defects of the rusted areas of the power transmission line, which comprises the following steps:
the data acquisition unit is used for acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
the aerial image positioning unit is used for determining the geographic coordinates of each image in the data acquisition unit;
the hardware target detection unit is used for screening the image containing the hardware in the aerial image positioning unit and giving out information of an external rectangular area of the hardware target;
the hardware fitting region foreground target segmentation unit is used for segmenting the target circumscribed rectangular region obtained in the hardware fitting target detection unit to obtain a target small image;
the hardware target rust analysis unit is used for performing rust analysis on the target small image obtained by the hardware region foreground target segmentation unit to obtain a patrol defect report;
and the routing inspection data and rust defect analysis report forwarding unit is used for forwarding the original routing inspection data and the routing inspection defect report.
The working procedure of this embodiment is as follows:
before an electric power inspection task, an unmanned aerial vehicle needs to arrange an inspection line, known materials such as a tower account and the like of an area to be inspected are collected, after the inspection is started, aerial image data and inertial navigation information data are collected through the data acquisition unit, the inertial navigation information data and the aerial image data are temporarily stored on a visible light camera memory card and an inertial navigation equipment memory card, and after the unmanned aerial vehicle finishes the flight task, the unmanned aerial vehicle is connected through a 4G transmission device or a data line and transmitted to an aerial image positioning unit;
the aerial image positioning unit loads the data stored in the data acquisition unit, numbers the aerial images according to the time sequence, corresponds the aerial images to inertial navigation information according to the time axis, and obtains a matching list of the inertial navigation data and the images, so that geographic coordinates of each image are determined according to the inertial navigation information, image numbers at the corresponding geographic coordinates are displayed, and operators can randomly select a power transmission line section to be analyzed according to line characteristics to detect rust defects;
the hardware target detection unit detects hardware on the image in the aerial image positioning unit by adopting a deep convolutional neural network model, screens the image containing the hardware as a target image, and simultaneously gives out information of an external rectangular area of the hardware target;
the hardware fitting region foreground object segmentation unit takes the object circumscribed rectangular region detected by the hardware fitting object detection unit as an initial region, expands 50 pixels in the upper, lower, left and right directions of the frame of the object circumscribed rectangular region respectively for segmentation, adopts a grabcut image segmentation method during segmentation, takes the object circumscribed rectangular region as a foreground object, takes all pixels outside the region as a background, models the object and the background by using a full covariance Gaussian mixture model with k=5 Gaussian components, and completes segmentation;
the hardware target rust analysis unit is used for performing rust analysis on the target small image obtained by the hardware region foreground target segmentation unit, and the analysis process is as follows: because targets such as hardware fittings and the like are rusted and display certain red characteristics, a hyper red method is adopted to reflect images after foreground targets are segmented, red information is intensively distributed at one part under an RGB color space, a color component of leading red is a red component, under general conditions, the value of the red component is larger than that of a green component and a blue component, a gray image is obtained by calculating a color component formula 2R-G-B (wherein R represents the red component, G represents the green component and B represents the blue component), a rusting area is obtained by adopting a threshold method on the basis of better stability of influences of the hyper red method on illumination, brightness and the like of the images, finally, a part with small area occupation of the target images and a part with large length-width ratio are deleted by adopting a connected domain calculation, the part is mostly a target boundary shadow part, and finally, the rusting defect condition of the segmented target small images is obtained and a patrol defect report is generated;
and finally, forwarding the original inspection data such as the aerial image, the telemetering information and the like stored in the inspection and the inspection defect report to a decision command console and an inspection handheld terminal by utilizing the inspection data and rust defect analysis report forwarding unit, so that inspection command operation and line maintenance personnel operation are facilitated.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The defect detection method for the rust area of the power transmission line is characterized by comprising the following steps of:
A. acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
B. the data obtained in the step A are obtained, the geographic coordinates of each image are determined through the time information of the inertial navigation data of the unmanned aerial vehicle and the time information of the aerial image, and the power transmission line section to be analyzed is selected at will according to the geographic coordinates;
C. b, detecting hardware fittings on the image obtained in the step B by using a deep convolutional neural network model, screening the image containing the hardware fittings as a target image, and simultaneously giving out information of an external rectangular area of a hardware fitting target;
D. c, dividing the target circumscribed rectangular area obtained in the step C to obtain a target small image;
E. d, carrying out graying treatment on the target small image obtained in the step D by adopting a hyper red method;
F. e, obtaining a rust area in the gray level image obtained in the step E by adopting a threshold method;
G. f, carrying out connected domain calculation on the rusted area in the step F to obtain a rusted defect detection image;
H. deleting a part with small area accounting for the target image and a part with large length-width ratio from the image obtained in the step G;
I. generating a patrol defect report;
J. and forwarding the original inspection data and the inspection defect report which are stored in the inspection.
2. The method for detecting defects in a rusted region of a power transmission line according to claim 1, wherein the determining the geographical coordinates of each image in the step B is: numbering the aerial images according to the time sequence, and corresponding the aerial images to inertial navigation information according to the time axis to obtain a matching list of inertial navigation data and the images, so that geographic coordinates of each image are determined according to the inertial navigation information.
3. The method for detecting defects in a rusted region of a power transmission line according to claim 1, wherein the method comprises the following steps: in the step D, the target circumscribed rectangular area is used as an initial area, and 50 pixels are respectively expanded in the up-down, left-right directions of the frame of the target circumscribed rectangular area, and then segmentation is performed.
4. The method for detecting defects in a rusted region of a power transmission line according to claim 3, wherein the dividing process in the step D is as follows: c, using the target circumscribed rectangular area detected in the step C as a foreground target, using all pixels outside the area as a background, and modeling the target and the background by using a full covariance mixed Gaussian model with k being 5 Gaussian components to finish the segmentation.
5. The method for detecting defects in a rusted region of a power transmission line according to claim 1, wherein the method comprises the following steps: and E, reacting the target small image obtained in the step D by adopting a super red method, and calculating a color component formula 2R-G-B to obtain a gray image.
6. An apparatus based on the method for detecting defects in a rust area of a power transmission line according to any one of claims 1 to 5, comprising:
the data acquisition unit is used for acquiring aerial images and inertial navigation information data obtained by unmanned aerial vehicle inspection;
the aerial image positioning unit is used for determining the geographic coordinates of each image in the data acquisition unit;
the hardware target detection unit is used for screening the image containing the hardware in the aerial image positioning unit and giving out information of an external rectangular area of the hardware target;
the hardware fitting region foreground target segmentation unit is used for segmenting the target circumscribed rectangular region obtained in the hardware fitting target detection unit to obtain a target small image;
the hardware target rust analysis unit is used for performing rust analysis on the target small image obtained by the hardware region foreground target segmentation unit to obtain a patrol defect report;
and the routing inspection data and rust defect analysis report forwarding unit is used for forwarding the original routing inspection data and the routing inspection defect report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823411.3A CN110910341B (en) | 2019-09-02 | 2019-09-02 | Method and device for detecting defects of rusted areas of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823411.3A CN110910341B (en) | 2019-09-02 | 2019-09-02 | Method and device for detecting defects of rusted areas of power transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110910341A CN110910341A (en) | 2020-03-24 |
| CN110910341B true CN110910341B (en) | 2023-05-30 |
Family
ID=69814476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910823411.3A Active CN110910341B (en) | 2019-09-02 | 2019-09-02 | Method and device for detecting defects of rusted areas of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110910341B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112090869A (en) * | 2020-09-08 | 2020-12-18 | 临沂大学 | Method and device for cleaning rusty spot by using laser of unmanned aerial vehicle and unmanned aerial vehicle |
| CN113191210B (en) * | 2021-04-09 | 2023-08-29 | 杭州海康威视数字技术股份有限公司 | Image processing method, device and equipment |
| CN114581692B (en) * | 2022-03-06 | 2022-12-02 | 扬州孚泰电气有限公司 | Vibration damper fault detection method and system based on intelligent pattern recognition |
| CN115376219A (en) * | 2022-06-28 | 2022-11-22 | 广州番禺电缆集团有限公司 | Cable insulation layer damage inspection device and method, electronic equipment and storage medium |
| CN115436384A (en) * | 2022-11-07 | 2022-12-06 | 国网山东省电力公司荣成市供电公司 | Distribution box surface defect detection system and method based on unmanned aerial vehicle image |
| CN115760858B (en) * | 2023-01-10 | 2023-05-02 | 东南大学附属中大医院 | Deep learning-based kidney pathological section cell identification method and system |
| CN117274723B (en) * | 2023-11-22 | 2024-03-26 | 国网智能科技股份有限公司 | Target identification method, system, medium and equipment for power transmission inspection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941745A (en) * | 2014-03-07 | 2014-07-23 | 国家电网公司 | Movable substation and working method for unmanned aerial vehicle electric transmission line inspection |
| CN106326808A (en) * | 2015-06-23 | 2017-01-11 | 上海深邃智能科技有限公司 | Method for detecting bird nests in power transmission line poles based on unmanned plane images |
| CN106643790A (en) * | 2016-09-26 | 2017-05-10 | 南方电网科学研究院有限责任公司 | Photoelectric pod resolution detection device and detection method |
| CN107703959A (en) * | 2017-10-31 | 2018-02-16 | 成都意町工业产品设计有限公司 | A kind of crusing robot control system and method based on unmanned plane |
| CN108470141A (en) * | 2018-01-27 | 2018-08-31 | 天津大学 | Insulator recognition methods in a kind of distribution line based on statistical nature and machine learning |
| JP2019009919A (en) * | 2017-06-26 | 2019-01-17 | 株式会社東芝 | Patrol inspection support system and patrol inspection support control program |
-
2019
- 2019-09-02 CN CN201910823411.3A patent/CN110910341B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941745A (en) * | 2014-03-07 | 2014-07-23 | 国家电网公司 | Movable substation and working method for unmanned aerial vehicle electric transmission line inspection |
| CN106326808A (en) * | 2015-06-23 | 2017-01-11 | 上海深邃智能科技有限公司 | Method for detecting bird nests in power transmission line poles based on unmanned plane images |
| CN106643790A (en) * | 2016-09-26 | 2017-05-10 | 南方电网科学研究院有限责任公司 | Photoelectric pod resolution detection device and detection method |
| JP2019009919A (en) * | 2017-06-26 | 2019-01-17 | 株式会社東芝 | Patrol inspection support system and patrol inspection support control program |
| CN107703959A (en) * | 2017-10-31 | 2018-02-16 | 成都意町工业产品设计有限公司 | A kind of crusing robot control system and method based on unmanned plane |
| CN108470141A (en) * | 2018-01-27 | 2018-08-31 | 天津大学 | Insulator recognition methods in a kind of distribution line based on statistical nature and machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110910341A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110910341B (en) | Method and device for detecting defects of rusted areas of power transmission line | |
| KR20170056474A (en) | Method, device and storage medium for calculating building height | |
| JP2016223815A (en) | Deterioration diagnostic system and deterioration diagnostic method | |
| CN114627021A (en) | Point cloud and deep learning based defect detection method and system | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| WO2021046726A1 (en) | Method and device for detecting mechanical equipment parts | |
| CN114252884A (en) | Method and device for positioning and monitoring roadside radar, computer equipment and storage medium | |
| CN114941807A (en) | Unmanned aerial vehicle-based rapid monitoring and positioning method for leakage of thermal pipeline | |
| CN115578326A (en) | Road disease identification method, system, equipment and storage medium | |
| CN114035606A (en) | Pole tower inspection system, pole tower inspection method, control device and storage medium | |
| CN116310891A (en) | Cloud-edge cooperative transmission line defect intelligent detection system and method | |
| CN107767366B (en) | A kind of transmission line of electricity approximating method and device | |
| WO2018078582A1 (en) | Method for distinguishing fresh meat from meat subjected to freezing by means of analysis of images of muscle tissue and corresponding system arranged to execute said method | |
| CN113032272A (en) | Automatic parking system test evaluation method, device, equipment and storage medium | |
| CN112184903A (en) | Method, device, equipment and medium for detecting high-voltage line tree obstacle risk points | |
| JP6434834B2 (en) | Inspection object extraction device and inspection object extraction method | |
| JP2014099055A (en) | Detector, detection method, and program | |
| CN116110127A (en) | Multi-linkage gas station cashing behavior recognition system | |
| CN115620079A (en) | Sample label obtaining method and lens failure detection model training method | |
| CN112509041B (en) | Parking-lot-based vehicle positioning method, system and storage medium | |
| CN110910379B (en) | Incomplete detection method and device | |
| CN112241691B (en) | Channel ice condition intelligent identification method based on unmanned aerial vehicle inspection and image characteristics | |
| CN117168467B (en) | Machine room inspection route planning and navigation method, equipment and system | |
| Niblock et al. | Fast model-based feature matching technique applied to airport lighting | |
| CN109740518A (en) | The determination method and device of object in a kind of video |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |