CN105701484A - Insulator explosion algorithm based on image identification technology - Google Patents
Insulator explosion algorithm based on image identification technology Download PDFInfo
- Publication number
- CN105701484A CN105701484A CN201610116181.3A CN201610116181A CN105701484A CN 105701484 A CN105701484 A CN 105701484A CN 201610116181 A CN201610116181 A CN 201610116181A CN 105701484 A CN105701484 A CN 105701484A
- Authority
- CN
- China
- Prior art keywords
- insulator
- region
- ith
- image
- coordinate
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 186
- 238000005516 engineering process Methods 0.000 title claims abstract description 38
- 238000004880 explosion Methods 0.000 title abstract 10
- 230000007547 defect Effects 0.000 claims abstract description 29
- 238000005336 cracking Methods 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 13
- 238000009413 insulation Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 238000000638 solvent extraction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 14
- 238000012360 testing method Methods 0.000 description 14
- 230000000694 effects Effects 0.000 description 8
- 238000007689 inspection Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012015 optical character recognition Methods 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
- G06V20/13—Satellite images
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Insulators (AREA)
Abstract
The present invention discloses an insulator explosion algorithm based on an image identification technology capable of accurately identifying the explosion defect of the insulator and accurately positioning the position of the insulator generating the explosion defect. A partitioning algorithm is employed to perform linear fitting of an insulator string in an image to obtain a fitting linear equation, regional coordinates and central coordinates of each insulator are calculated, the statistics of the proportion of effective pixel points in each insulator region is performed, and the region where the insulator explosion happens and positioning the region where the explosion fault generates are determined. The insulator explosion algorithm is able to accurately identify the explosion defect of an insulator, accurately locate the position, of the insulator, where the explosion defect happens, provide basis for polling decisions, plans and the like and reduce risks, therefore the insulator explosion algorithm is suitable for popularization and application in the field of the transmission line polling technology.
Description
Technical Field
The invention relates to the technical field of power transmission line inspection, in particular to an insulator cracking algorithm based on an image recognition technology.
Background
In recent years, with the rapid development of information technology, video recognition technology has grown, and recognition of faces, behaviors, patterns and the like by using the recognition technology is increasing, but the application to fault recognition of power transmission lines is rare. Video recognition technology has a long history of development, and since the beginning of the 50 th 20 th century, people have begun to research two-dimensional image analysis and recognition technology, and the work at that time mainly focuses on works such as optical character recognition, workpiece surface, microscopic picture and aerial picture analysis and interpretation. In the 60 s, people began to conduct three-dimensional structure analysis and three-dimensional machine vision research work, and in the 70 s, some vision application systems have appeared. Until today, new concepts, methods and theories of image recognition technology are still emerging continuously, and are always a very active field. It is now well recognized that image processing and recognition technology is an important means of understanding and modifying the world. Video recognition technology is becoming more sophisticated.
At present, in many occasions, the insulator cracking detection is realized by manually checking an image of the insulator or by using equipment or instruments such as ultrasonic waves, infrared rays and the like to assist in detecting the fault of the insulator. This would greatly increase the labor burden and equipment costs. At present, unmanned aerial vehicle tours and has been put into practical application, utilizes unmanned aerial vehicle easily to reach the characteristics of easily hovering and easily controlling, and unmanned aerial vehicle can carry out the detail to the target of touring in a flexible way and shoot. The value of the image data for the inspection of the power transmission line is exerted. Transmission line patrols and examines, no matter be artifical tour, unmanned aerial vehicle tour, tour line equipment tour, or other video equipment carry out the circuit and patrol, and what come with will be a large amount of image data, and if these image data rely on the manual work to carry out the analysis and look over, will increase the intensity of work greatly, reduce work efficiency. If one person needs 30 seconds to carefully view one image, then 3000 seconds to 50 minutes are required to view 100 images, and uninterrupted viewing for 50 minutes will not only increase fatigue, but also affect the accuracy of the analysis. However, by using the computer technology and the image technology, the analysis time of 100 images is shortened by several minutes, so that the efficiency can greatly improve the existing problems of manual observation, avoid the misjudgment and missing judgment caused by artificial experience or working strength fatigue, improve the overall working efficiency, improve the fine management mode and improve the intelligent degree. The method saves a large amount of manpower viewing time, saves a lot of economic investment, strengthens data management and embodies the value of each piece of patrol image data. The method provides basis for routing inspection decision, plan and the like, reduces risks and has great social and economic benefits.
When the computer is used for judging and processing the insulator image, an effective insulator burst algorithm for judging the insulator is very critical, and is directly related to whether the computer can accurately identify the burst defect of the insulator, whether the position of the insulator with the burst defect can be accurately positioned, whether the basis for routing inspection decision, plan and the like can be provided for reducing risks, and until now, no effective insulator burst algorithm which can accurately identify the burst defect of the insulator and accurately position the position of the insulator with the burst defect exists.
Disclosure of Invention
The invention aims to provide an insulator cracking algorithm based on an image recognition technology, which can accurately recognize the cracking defect of an insulator and accurately position the position of the insulator with the cracking defect.
The technical scheme adopted by the invention for solving the technical problems is as follows: the insulator cracking algorithm based on the image recognition technology comprises the following steps:
A. performing linear fitting on the insulator string in the image to obtain a fitted linear equation;
B. calculating the area coordinate and the center coordinate of each insulator;
C. and (4) counting the proportion of effective pixel points in each insulation sub-region, judging the region where the insulator is cracked by using a threshold function, and positioning the region where the crack fault occurs.
Further, in step a, the fitted linear equation is y ═ kx + b,
Further, in step B, the area coordinates and the center coordinates of each insulator are calculated by the following method: firstly, determining the coordinates S (X) of the starting point of the insulator string according to a fitted linear equation of the insulator strings，Ys) Determining the end point coordinate E (X) of the insulator stringe，Ye) Determining insulator stringsLength ofThe included angle between the fitting straight line and the horizontal direction is theta, theta is arctank, and the coordinate of the center point of the ith insulator is recorded as O (X)o，Yo) And one vertex coordinate of the rectangular area where the ith insulator is located is marked as A (X)A，YA) (ii) a The length of the rectangular area where the ith insulator is located is m, the width of the rectangular area is n, the distance between the center of the ith insulator and the coordinate of the starting point is recorded as | SO |,n is the number of insulators;
the coordinates of the central point of the ith insulator are as follows:
one of the vertex coordinates of the ith insulator is as follows:
the length of the rectangular area where the ith insulator is located is m:
the width of the rectangular area where the ith insulator is located is n,
further, in step C, a specific method for judging the region where the insulator cracks and locating the region where the crack fault occurs by using the threshold function is as follows: firstly, the proportion rate of effective pixel points in the region of the insulator is counted, wherein the proportion rate is used for counting the effective pixel points in the region of the insulatorN is the number of insulators, m is the length of a rectangular area where the ith insulator is located, the length is the length of the insulator string, count (i) represents the ith white pixel point counted along the direction of the insulator string fitting straight line, and then a proportional threshold is set to judge the defect, wherein the threshold is When the rate is greater than the threshold, the insulator is defect-free, and when the rate is less than or equal to the threshold, the insulator is defect-free.
The invention has the beneficial effects that: the insulator cracking algorithm based on the image recognition technology obtains a fitting linear equation by performing linear fitting on an insulator string in an image; then calculating the area coordinate and the center coordinate of each insulator; and then, the proportion of effective pixel points in each insulation sub-region is counted, the region where the insulator cracks is judged by using a threshold function, the region where the crack fault occurs is positioned, the crack defect of the insulator can be accurately identified by using the insulator crack algorithm, meanwhile, the position of the insulator where the crack defect occurs can be accurately positioned, a basis can be provided for routing inspection decision, planning and the like, and risks can be reduced.
Drawings
FIG. 1 is a regional mathematical model diagram of an insulator;
FIG. 2 is a mathematical model diagram of region coordinates and center coordinates of an insulator string;
FIG. 3 is a first original aerial insulator image;
FIG. 4 is a diagram showing the test effect of detecting a first original aerial insulator image using the insulator break algorithm based on the image recognition technology according to the present invention;
FIG. 5 is a second original aerial insulator image;
FIG. 6 is a diagram showing the test effect of detecting a second original aerial insulator image using the insulator crack algorithm based on the image recognition technology according to the present invention;
FIG. 7 is a third original aerial insulator image;
FIG. 8 is a diagram showing the test effect of detecting a third original aerial insulator image using the insulator cracking algorithm based on the image recognition technology according to the present invention;
FIG. 9 is a fourth original aerial insulator image;
FIG. 10 is a graph illustrating the test results of detecting a fourth original aerial insulator image using the insulator cracking algorithm based on image recognition techniques according to the present invention;
FIG. 11 is a fifth original aerial insulator image;
FIG. 12 is a diagram showing the test effect of detecting a fifth original aerial insulator image using the insulator cracking algorithm based on the image recognition technology according to the present invention;
FIG. 13 is a sixth original aerial insulator image;
FIG. 14 is a diagram showing the test effect of detecting a sixth original aerial insulator image using the insulator cracking algorithm based on the image recognition technology according to the present invention;
FIG. 15 is a seventh original aerial insulator image;
fig. 16 is a test effect diagram of detecting a seventh original aerial insulator image by using the insulator burst algorithm based on the image recognition technology according to the present invention.
Detailed Description
The invention relates to an insulator cracking algorithm based on an image recognition technology, which comprises the following steps:
the insulator cracking algorithm based on the image recognition technology comprises the following steps:
A. performing linear fitting on the insulator string in the image to obtain a fitted linear equation;
B. calculating the area coordinate and the center coordinate of each insulator;
C. and (4) counting the proportion of effective pixel points in each insulation sub-region, judging the region where the insulator is cracked by using a threshold function, and positioning the region where the crack fault occurs.
The insulator cracking algorithm based on the image recognition technology obtains a fitting linear equation by performing linear fitting on an insulator string in an image; then calculating the area coordinate and the center coordinate of each insulator; and then, the proportion of effective pixel points in each insulation sub-region is counted, the region where the insulator cracks is judged by using a threshold function, the region where the crack fault occurs is positioned, the crack defect of the insulator can be accurately identified by using the insulator crack algorithm, meanwhile, the position of the insulator where the crack defect occurs can be accurately positioned, a basis can be provided for routing inspection decision, planning and the like, and risks can be reduced.
In step a, the fitted linear equation is y ═ kx + b,
Further, in step B, the area coordinates and the center coordinates of each insulator are calculated by the following method: as shown in fig. 1, fig. 1 is a mathematical model diagram of a region of an insulator, and fig. 2 is a mathematical model diagram of region coordinates and center coordinates of an insulator string; firstly, determining the coordinates S (X) of the starting point of the insulator string according to a fitted linear equation of the insulator strings，Ys) Determining the end point coordinate E (X) of the insulator stringe，Ye) Determining the length of the insulator stringThe included angle between the fitting straight line and the horizontal direction is theta, theta is arctank, and the coordinate of the center point of the ith insulator is recorded as O (X)o，Yo) And one vertex coordinate of the rectangular area where the ith insulator is located is marked as A (X)A，YA) (ii) a The length of the rectangular area where the ith insulator is located is m, the width of the rectangular area is n, the distance between the center of the ith insulator and the coordinate of the starting point is recorded as | SO |,n is the number of insulators;
the coordinates of the central point of the ith insulator are as follows:
one of the vertex coordinates of the ith insulator is as follows:
the length of the rectangular area where the ith insulator is located is m:
the width of the rectangular area where the ith insulator is located is n,
by the method, the region coordinate and the center coordinate of each insulator can be quickly and accurately determined, and the region coordinate of the insulator can be quickly and conveniently obtained by determining a vertex, the length and the width of the rectangular region.
In order to more accurately identify the burst defect of the insulator, provide basis for routing inspection decision, plan and the like and reduce risks, the invention provides an effective burst defect judgment method, and in the step C, a specific method for judging the region where the insulator bursts and positioning the region where the burst fault occurs by using a threshold function is as follows: firstly, the proportion rate of effective pixel points in the region of the insulator is counted, wherein the proportion rate is used for counting the effective pixel points in the region of the insulatorN is the number of insulators, m is the length of a rectangular area where the ith insulator is located, the length is the length of the insulator string, count (i) represents the ith white pixel point counted along the direction of the insulator string fitting straight line, and then a proportional threshold is set to judge the defect, wherein the threshold is When rate is greater than threshold, the insulator is free of defects, and when rate is less than or equal to threshold, the insulator is absolutely free of defectsThe rim is defective.
FIG. 3 is a first original aerial insulator image; FIG. 4 is a diagram of the test effect of detecting a first original aerial insulator image using the above-mentioned insulator burst algorithm based on image recognition technology, where the positions indicated by red circles are the positions of detected insulators with burst defects; FIG. 5 is a second original aerial insulator image; FIG. 6 is a diagram of the test results of a second original aerial insulator image using the above-described insulator burst algorithm based on image recognition technology, where the positions indicated by red circles are the positions of detected insulators with burst defects; FIG. 7 is a third original aerial insulator image; FIG. 8 is a diagram of the test results of a third original aerial insulator image detected by the above-mentioned insulator burst algorithm based on image recognition technology, wherein the positions indicated by red circles are the positions of detected insulators with burst defects; FIG. 9 is a fourth original aerial insulator image; FIG. 10 is a graph illustrating the test results of a fourth original aerial insulator image using the above-described insulator cracking algorithm based on image recognition technology, wherein the positions indicated by red circles are the positions of detected insulators with cracking defects; FIG. 11 is a fifth original aerial insulator image; fig. 12 is a diagram showing the test effect of detecting a fifth original aerial insulator image by using the insulator burst algorithm based on the image recognition technology, wherein the positions indicated by red circles are the positions of detected insulators with burst defects; FIG. 13 is a sixth original aerial insulator image; FIG. 14 is a graph illustrating the test results of using the above-described insulator burst algorithm based on image recognition technology to detect a sixth original aerial insulator image, where the positions indicated by red circles are the positions of detected insulators with burst defects; FIG. 15 is a seventh original aerial insulator image; FIG. 16 is a graph illustrating the test results of a seventh original aerial insulator image using the above-described insulator burst algorithm based on image recognition technology, wherein the positions indicated by red circles are the positions of detected insulators with burst defects; the comparison graph shows that the insulator cracking algorithm can accurately identify the cracking defects of the insulator, can accurately position the positions of the insulators with the cracking defects, and can provide basis for routing inspection decision, plan and the like and reduce risks.
Claims (4)
1. The insulator cracking algorithm based on the image recognition technology is characterized by comprising the following steps of:
A. performing linear fitting on the insulator string in the image to obtain a fitted linear equation;
B. calculating the area coordinate and the center coordinate of each insulator;
C. and (4) counting the proportion of effective pixel points in each insulation sub-region, judging the region where the insulator is cracked by using a threshold function, and positioning the region where the crack fault occurs.
2. The image recognition technology-based insulator cracking algorithm of claim 1, wherein: in step a, the fitted linear equation is y ═ kx + b,
said xi，yiRespectively are an abscissa value and an ordinate value of the selected observation points, and M is the number of the selected observation points.
3. The image recognition technology-based insulator cracking algorithm of claim 2, wherein: in step B, the area coordinates and center coordinates of each insulator are calculated by the following method: firstly, determining the coordinates S (X) of the starting point of the insulator string according to a fitted linear equation of the insulator strings,Ys) Determining the end point coordinate E (X) of the insulator stringe,Ye) Determining the length of the insulator stringThe included angle between the fitting straight line and the horizontal direction is theta, theta is arctank, and the coordinate of the center point of the ith insulator is recorded as O (X)o,Yo) And one vertex coordinate of the rectangular area where the ith insulator is located is marked as A (X)A,YA) (ii) a The length of the rectangular area where the ith insulator is located is m, the width of the rectangular area is n, the distance between the center of the ith insulator and the coordinate of the starting point is recorded as SO,n-1 ═ 1.2.; n is the number of insulators;
the coordinates of the central point of the ith insulator are as follows:
one of the vertex coordinates of the ith insulator is as follows:
wherein,
the length of the rectangular area where the ith insulator is located is m:
the width of the rectangular area where the ith insulator is located is n,
4. the image recognition technology-based insulator cracking algorithm of claim 2, wherein: in step C, the specific method for judging the region where the insulator cracks and locating the region where the crack fault occurs by using the threshold function is as follows: firstly, the proportion rate of effective pixel points in the region of the insulator is counted, wherein the proportion rate is used for counting the effective pixel points in the region of the insulatorN is the number of insulators, m is the length of a rectangular area where the ith insulator is located,the length is the length of the insulator string,count (i) represents the ith white pixel point counted along the direction of the insulator string fitting straight line, and then a proportional threshold is set to judge the defect, wherein the threshold isWhen the rate is greater than the threshold, the insulator is defect-free, and when the rate is less than or equal to the threshold, the insulator is defect-free.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610116181.3A CN105701484A (en) | 2016-03-02 | 2016-03-02 | Insulator explosion algorithm based on image identification technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610116181.3A CN105701484A (en) | 2016-03-02 | 2016-03-02 | Insulator explosion algorithm based on image identification technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105701484A true CN105701484A (en) | 2016-06-22 |
Family
ID=56222739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610116181.3A Pending CN105701484A (en) | 2016-03-02 | 2016-03-02 | Insulator explosion algorithm based on image identification technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701484A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504247A (en) * | 2016-11-09 | 2017-03-15 | 广东电网有限责任公司电力科学研究院 | A kind of quick-fried automatic testing method of insulator chain based on visible images and device |
| CN106529554A (en) * | 2016-10-28 | 2017-03-22 | 广东电网有限责任公司电力科学研究院 | Insulator semi-automatic extraction method and device based on infrared image |
| CN106780444A (en) * | 2016-12-01 | 2017-05-31 | 广东容祺智能科技有限公司 | A kind of insulator automatic identification analysis system |
| CN110351549A (en) * | 2019-07-23 | 2019-10-18 | Tcl王牌电器(惠州)有限公司 | Screen display state detection method, device, terminal device and readable storage medium storing program for executing |
| CN111507189A (en) * | 2020-03-17 | 2020-08-07 | 国家电网有限公司 | Insulator string defect rapid detection method based on image processing technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620676A (en) * | 2009-07-02 | 2010-01-06 | 浙江省电力公司 | Fast image recognition method of insulator contour |
| CN103605981A (en) * | 2013-12-03 | 2014-02-26 | 国家电网公司 | Insulator defect identification method based on image identification |
| US20150139522A1 (en) * | 2013-11-18 | 2015-05-21 | General Electric Company | Statistical property preserved bad line correction |
-
2016
- 2016-03-02 CN CN201610116181.3A patent/CN105701484A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620676A (en) * | 2009-07-02 | 2010-01-06 | 浙江省电力公司 | Fast image recognition method of insulator contour |
| US20150139522A1 (en) * | 2013-11-18 | 2015-05-21 | General Electric Company | Statistical property preserved bad line correction |
| CN103605981A (en) * | 2013-12-03 | 2014-02-26 | 国家电网公司 | Insulator defect identification method based on image identification |
Non-Patent Citations (4)
| Title |
|---|
| 杨亚明: "基于OpenCV的绝缘子及等电位线故障状态智能识别", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 王银立: "输电线路导线断股及绝缘子自爆的图像识别算法研究", 《万方数据知识服务平台》 * |
| 王银立等: "基于视觉的绝缘子"掉串"缺陷的检测与定位", 《计算机工程与设计》 * |
| 马帅营等: "基于区域定位的绝缘子图像分割", 《电力建设》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529554A (en) * | 2016-10-28 | 2017-03-22 | 广东电网有限责任公司电力科学研究院 | Insulator semi-automatic extraction method and device based on infrared image |
| CN106529554B (en) * | 2016-10-28 | 2019-05-10 | 广东电网有限责任公司电力科学研究院 | A kind of insulator semiautomatic extraction method and device based on infrared image |
| CN106504247A (en) * | 2016-11-09 | 2017-03-15 | 广东电网有限责任公司电力科学研究院 | A kind of quick-fried automatic testing method of insulator chain based on visible images and device |
| CN106504247B (en) * | 2016-11-09 | 2019-05-17 | 广东电网有限责任公司电力科学研究院 | A kind of quick-fried automatic testing method of the insulator chain based on visible images and device |
| CN106780444A (en) * | 2016-12-01 | 2017-05-31 | 广东容祺智能科技有限公司 | A kind of insulator automatic identification analysis system |
| CN110351549A (en) * | 2019-07-23 | 2019-10-18 | Tcl王牌电器(惠州)有限公司 | Screen display state detection method, device, terminal device and readable storage medium storing program for executing |
| CN110351549B (en) * | 2019-07-23 | 2021-11-09 | Tcl王牌电器(惠州)有限公司 | Screen display state detection method and device, terminal equipment and readable storage medium |
| CN111507189A (en) * | 2020-03-17 | 2020-08-07 | 国家电网有限公司 | Insulator string defect rapid detection method based on image processing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106290388B (en) | A kind of insulator breakdown automatic testing method | |
| US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
| CN105701484A (en) | Insulator explosion algorithm based on image identification technology | |
| Sohn et al. | Automatic powerline scene classification and reconstruction using airborne lidar data | |
| Tan et al. | Multialgorithm fusion image processing for high speed railway dropper failure–defect detection | |
| CN110246132A (en) | Rail vehicle bolt looseness detection method and system | |
| CN105740844A (en) | Insulator cracking fault detection method based on image identification technology | |
| CN104268538A (en) | Online visual inspection method for dot matrix sprayed code characters of beverage cans | |
| CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
| CN106340009A (en) | Parallel-binocular-based power line detection method and system | |
| CN109523543A (en) | A kind of wire strand breakage detection method based on Edge Distance | |
| CN104400265A (en) | Feature extraction method applicable to corner weld of laser vision guided welding robot | |
| CN109300118A (en) | A UAV inspection method for high-voltage power lines based on RGB images | |
| CN114119595A (en) | An online monitoring and evaluation method for GMAW welding quality based on integrated deep learning | |
| CN109308448A (en) | A method of using image processing technology to prevent misoperation of power distribution and distribution | |
| CN114973206A (en) | Automatic pavement disease identification and management method | |
| CN104281857A (en) | Insulator detecting method based on orthogonal direction projection | |
| CN119125167A (en) | A photovoltaic aluminum frame surface defect detection system | |
| CN104966302B (en) | A kind of detection localization method of any angle laser cross | |
| CN105528790A (en) | Transmission line small part identification method | |
| CN105987665A (en) | Early warning and monitoring device of ultra high voltage transmission line sag point variation range, and method of the same | |
| CN119338775A (en) | A vision-based gas pipeline appearance quality inspection method | |
| CN109146863A (en) | A kind of pavement marker line defect detection device | |
| CN112991252A (en) | Method for detecting loss of vibration damper on power transmission line | |
| CN117197700A (en) | Intelligent unmanned inspection contact net defect identification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160622 |