CN111507189A - Insulator string defect rapid detection method based on image processing technology - Google Patents

Insulator string defect rapid detection method based on image processing technology Download PDF

Info

Publication number
CN111507189A
CN111507189A CN202010188034.3A CN202010188034A CN111507189A CN 111507189 A CN111507189 A CN 111507189A CN 202010188034 A CN202010188034 A CN 202010188034A CN 111507189 A CN111507189 A CN 111507189A
Authority
CN
China
Prior art keywords
insulator
straight line
image processing
fitting
insulator string
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.)
Granted
Application number
CN202010188034.3A
Other languages
Chinese (zh)
Other versions
CN111507189B (en
Inventor
尚方
孙立业
张雷
樊永新
刘生
王孝余
林扬
姚越
李奇
侴海洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Heilongjiang Electric Power Co Ltd Electric Power Research Institute
State Grid Corp of China SGCC
Original Assignee
State Grid Heilongjiang Electric Power Co Ltd Electric Power Research Institute
State Grid Corp of China SGCC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Heilongjiang Electric Power Co Ltd Electric Power Research Institute, State Grid Corp of China SGCC filed Critical State Grid Heilongjiang Electric Power Co Ltd Electric Power Research Institute
Priority to CN202010188034.3A priority Critical patent/CN111507189B/en
Publication of CN111507189A publication Critical patent/CN111507189A/en
Application granted granted Critical
Publication of CN111507189B publication Critical patent/CN111507189B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Insulators (AREA)

Abstract

The invention discloses a method for rapidly detecting defects of an insulator string based on an image processing technology, relates to the technical field of image processing, and mainly researches the identification and fault detection of insulators in automatic inspection of a power transmission line aiming at the problem of low accuracy in the process of detecting the insulators and identifying faults of the insulators from high-resolution aerial images with complex backgrounds. The method can effectively avoid redundant calculation, fully considers the shearing of non-core areas, the judgment of insulator string direction straight lines, the calculation simplification of insulator distances, the judgment of fault parameters and the like, gives experience values, can effectively avoid missing detection and false detection, simultaneously works efficiently and accurately, and can effectively detect the insulator from high-resolution aerial images with complex backgrounds and identify the fault of the insulator.

Description

Insulator string defect rapid detection method based on image processing technology
Technical Field
The invention relates to the technical field of image processing, in particular to a method for rapidly detecting insulator chain defects based on an image processing technology.
Background
According to the 'compilation of statistical data of electric power industry', the length of a transmission line with more than 220kV in China is more than 54 ten thousand kilometers in 2013. The workload of line inspection is very large. Take Heilongjiang province company as an example, mountainous regions have many terrains and forests are dense. One line is hundreds of kilometers at any moment, mountain turning and mountain crossing are performed, and the vast majority of the lines pass through the river by adopting an artificial line patrol mode at present. Few detections can be patrolled by inspection vehicles, unmanned aerial vehicle equipment, and the like. The manual inspection has high difficulty, low efficiency and poor accuracy. In summer, the snow cover needs to penetrate through trees and swamps, and in winter, the snow cover is deep in waist. Bringing a lot of risks to the patrolling workers. Therefore, unmanned aerial vehicle patrols and examines to be the trend of development, and the insulator state is one of the key index that transmission line patrolled and examined, and the most main way of patrolling and examining at present is to judge the state of insulator through visible light. Therefore, the method for automatically detecting the state of the insulator, which is economical and efficient, is explored and is a research direction with wide development prospect and important application value.
The insulator is shot in a short distance by the unmanned aerial vehicle, the contour of the insulator in the aerial image is identified by the image processing algorithm, and the defect of the contour is detected, so that a new way is provided for inspecting the insulator in a patrol way, and a certain difficulty is provided for automatically and accurately detecting the insulator from the high-resolution aerial image with a complex background and identifying the fault of the insulator. At present, the result of automatic processing by a computer is easy to report by mistake and report by exposition, so that the mode of manual review is introduced after the automatic processing by the computer is adopted in reality.
Disclosure of Invention
The purpose of the invention is: aiming at the problem that the accuracy is low when an insulator is detected from a high-resolution aerial image with a complex background and a fault is identified in the prior art, a method for rapidly detecting the defects of the insulator string based on an image processing technology is provided.
The technical scheme adopted by the invention to solve the technical problems is as follows:
a method for rapidly detecting insulator string defects based on an image processing technology comprises the following steps:
the method comprises the following steps: acquiring an aerial image;
step two: filtering non-core insulator string information in the aerial image;
step three: positioning each insulator sheet region;
step four: calculating the central position point C of each insulator sheetk；
Step five: centering the insulator sheet at point CiFitting, wherein i ∈ (1, k), then obtaining a straight line L in the direction of the insulator string through function calculation, and finally marking the number and the position of the fitting straight line L at the moment;
step six: respectively calculating the direct distances d of all adjacent insulators on the same straight lineijI.e. AiAjThe length of the line segment;
step seven: traverse all the direct distances d of the adjacent insulators on the same straight lineijFind the minimum value dmin；
Step eight: traverse all dijAnd determining whether d is presentij>1.5×dminIf the central point A exists, the central point A of the insulator is judgedi(xi,yi) And Aj(xj,yj) There is an insulator fault between them;
step nine: on line segment AiAjThe middle point Fault of (1) is marked;
and step ten, executing the step six to the step nine until all the fitting straight lines L in the step five are processed.
Furthermore, positioning each insulator sheet area in the third step is performed by using an ellipse operator detection method.
Further, the fitting function of the straight line L in the step five is:
Cost＝n×10-m×1
wherein n is the number of the fitting straight lines under the scheme, and m is the number of the central position points of the insulator sheets which are included in the fitting straight lines under the scheme.
Further, the method for marking the number and the position of the fitting straight line in the step five comprises the following steps:
every more straight line is fitted, Cost plus 10,
the center point of each insulator sheet enters a fitting straight line, Cost minus 1,
the center position point of each insulator sheet can enter the fitting straight line only once,
when the Cost value is minimum, the scheme is considered to be optimal, and the number and the positions of the fitting straight lines at the moment are marked.
Further, the distance d between adjacent insulators is directijThe calculation formula of (2) is as follows:
Figure BDA0002414879890000021
wherein x isiIs the pixel horizontal coordinate, yiIs the pixel vertical coordinate.
Further, the line segment AiAjThe horizontal and vertical coordinates of the middle point Fault are respectively:
Figure BDA0002414879890000022
wherein x isiIs the pixel horizontal coordinate, yiIs the pixel vertical coordinate.
The invention has the beneficial effects that:
the invention mainly researches the insulator identification and fault detection in the automatic inspection of the power transmission line, and designs a high-efficiency and rapid detection method based on color and space distance, which fully utilizes prior information, on the basis of investigating a large number of aerial image characteristics. The method can effectively avoid redundant calculation, fully considers the shearing of non-core areas, the judgment of insulator string direction straight lines, the calculation simplification of insulator distances, the judgment of fault parameters and the like, gives experience values, can effectively avoid missing detection and false detection, simultaneously works efficiently and accurately, and can effectively detect the insulator from high-resolution aerial images with complex backgrounds and identify the fault of the insulator.
Drawings
FIG. 1 is a schematic view of insulator sheet area identification;
FIG. 2 is a schematic diagram showing the sequence attribution of a marked insulator string;
fig. 3 is a schematic diagram of labeling in a salient manner.
Detailed Description
The first embodiment is as follows: the embodiment is specifically described with reference to fig. 1 and fig. 2 and fig. 3, and the method for rapidly detecting the insulator string defects based on the image processing technology in the embodiment includes the following steps:
the method comprises the following steps: acquiring an aerial image;
step two: filtering non-core insulator string information in the aerial image;
filtering non-core insulator string information in the aerial image, marking a core area, inputting an original image, and only marking the area containing the insulator string after image processing. The position of the selection result relative to the original image is selected, and the core area is the horizontal boundary and the vertical boundary of the insulator string.
Step three: positioning each insulator sheet region;
each insulator sheet region is located by means of image recognition (e.g. detection using an ellipse operator). As shown in fig. 1.
Step four: calculating the central position point C of each insulator sheetk(the center point of the first insulator is C)1The central point of the second insulator is C2The central point of the kth insulator is Ck)；
Calculating the central position point C of each insulator sheetk(based on the center of the ellipse) to 1 pixel. The value of k ranges from 1 to the number of all insulator pieces in the region.
Step five: centering the insulator sheet at point CiFitting, wherein i ∈ (1, k), then obtaining a straight line L in the direction of the insulator string through function calculation, and finally marking the number and the position of the fitting straight line L at the moment;
a straight line L fitting the direction of the insulator string, which should be fitted with the center position point C of the insulator sheet.
Designing a calculation function of a fitting straight line, wherein Cost is n × 10-m × 1
In the formula, n is the number of fitted straight lines under the scheme.
m is the number of the central position points of the insulator pieces which are contained in the fitting straight line under the scheme, m is the number, the unit is one, 1 is each part, the unit is 1 part, and the unit of the number per part is a fraction, so as to unify dimensions.
The design principle is as follows:
every more straight line is fitted, Cost plus 10,
the center point of each insulator sheet enters a fitting straight line, Cost minus 1,
the center point of each insulator sheet can only enter the fitting straight line once.
This solution is considered optimal when the Cost value is minimal. The number and position of the straight line that fits at this time are marked. As shown in fig. 2.
After finding the optimal solution, according to the sequence of fitting the straight line direction, marking the marks of the center positions of each insulator one by one as: a. thei(xi,yi) Wherein i is a natural number from 1 to max, and max is the number of the insulator pieces.
xiIs the pixel horizontal coordinate, yiIs the pixel vertical coordinate.
Step six: respectively calculating the direct distances d of all adjacent insulators on the same straight lineijI.e. AiAjThe length of the line segment; and respectively calculating the direct distances between all adjacent insulators on the same straight line. Namely: a. theiAjAnd the length of the line segment, wherein i is a natural number from 1 to max, and max is the number of the insulator pieces. j ═ i + 1.
Note dijIs line segment AiAjTo 1/50, the kernel region image width (unit: number of pixels).
Manner of calculation
Figure BDA0002414879890000041
Step seven: traverse all the direct distances d of the adjacent insulators on the same straight lineijFind the minimum value dmin；
Traverse all dijFind the minimum value
dmin＝min(dij)
Step eight: traverse all dijAnd determining whether d is presentij>1.5×dminIf the central point A exists, the central point A of the insulator is judgedi(xi,yi) And Aj(xj,yj) There is an insulator fault between them;
traverse all dijIf d is presentij>1.5×dminThen, the central point A of the insulator is determinedi(xi,yi) And Aj(xj,yj) In between, there is an insulator fault. (the reasons include the absence of spontaneous explosion, pollution flashover condition and bird droppings accumulation conditionWhen the appearance of the same color or shape is obviously abnormal)
Step nine: on line segment AiAjThe middle point Fault of (1) is marked;
consider that A isi(xi,yi) And Aj(xj,yj) When there is insulator fault between them, it is on line segment AiAjThe middle point Fault of (a), marked in a significant way. As shown in fig. 3, fig. 3 is a view for locating a defect position (showing a red triangle position).
Wherein the horizontal and vertical coordinates of the point Fault are respectively
Figure BDA0002414879890000042
And step ten, executing the step six to the step nine until all the fitting straight lines L in the step five are processed.
And traversing all the insulator strings according to the fitting straight line until all the defect positions are marked.
And (3) actually measuring common aerial insulator images (about 50 thousands of image pixels and 1-3 insulator strings), wherein the detection time does not exceed 1.1 s. When an insulator string is lost, the method has good accuracy, and can also judge insulators with obvious color characteristics (such as affected by pollution flashover and bird droppings).
It should be noted that the detailed description is only for explaining and explaining the technical solution of the present invention, and the scope of protection of the claims is not limited thereby. It is intended that all such modifications and variations be included within the scope of the invention as defined in the following claims and the description.

Claims (6)

1. A method for rapidly detecting insulator string defects based on an image processing technology is characterized by comprising the following steps:
the method comprises the following steps: acquiring an aerial image;
step two: filtering non-core insulator string information in the aerial image;
step three: positioning each insulator sheet region;
step four: calculating the central position point C of each insulator sheetk；
Step five: centering the insulator sheet at point CiFitting, wherein i ∈ (1, k), then obtaining a straight line L in the direction of the insulator string through function calculation, and finally marking the number and the position of the fitting straight line L at the moment;
step six: respectively calculating the direct distances d of all adjacent insulators on the same straight lineijI.e. AiAjThe length of the line segment;
step seven: traverse all the direct distances d of the adjacent insulators on the same straight lineijFind the minimum value dmin；
Step eight: traverse all dijAnd determining whether d is presentij＞1.5×dminIf the central point A exists, the central point A of the insulator is judgedi(xi，yi) And Aj(xj，yj) There is an insulator fault between them;
step nine: on line segment AiAjThe middle point Fault of (1) is marked;
and step ten, executing the step six to the step nine until all the fitting straight lines L in the step five are processed.
2. The method according to claim 1, wherein the positioning of each insulator sub-sheet region in the third step is performed by using an ellipse operator detection method.
3. The method for rapidly detecting the insulator string defects based on the image processing technology as claimed in claim 1, wherein the fitting function of the straight line L in the step five is as follows:
Cost＝n×10-m×1
wherein n is the number of the fitting straight lines under the scheme, and m is the number of the central position points of the insulator sheets which are included in the fitting straight lines under the scheme.
4. The method according to claim 3, wherein the step five of marking the number and position of the fitted straight lines comprises:
every more straight line is fitted, Cost plus 10,
the center point of each insulator sheet enters a fitting straight line, Cost minus 1,
the center position point of each insulator sheet can enter the fitting straight line only once,
when the Cost value is minimum, the scheme is considered to be optimal, and the number and the positions of the fitting straight lines at the moment are marked.
5. The method for rapidly detecting the defects of the insulator string based on the image processing technology as claimed in claim 1, wherein the direct distance d between the adjacent insulatorsijThe calculation formula of (2) is as follows:
Figure FDA0002414879880000021
wherein x isiIs the pixel horizontal coordinate, yiIs the pixel vertical coordinate.
6. The method for rapidly detecting insulator string defects based on image processing technology as claimed in claim 1, wherein the line segment AiAjThe horizontal and vertical coordinates of the middle point Fault are respectively:
Figure FDA0002414879880000022
wherein x isiIs the pixel horizontal coordinate, yiIs the pixel vertical coordinate.
CN202010188034.3A 2020-03-17 2020-03-17 Insulator string defect rapid detection method based on image processing technology Active CN111507189B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010188034.3A CN111507189B (en) 2020-03-17 2020-03-17 Insulator string defect rapid detection method based on image processing technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010188034.3A CN111507189B (en) 2020-03-17 2020-03-17 Insulator string defect rapid detection method based on image processing technology

Publications (2)

Publication Number Publication Date
CN111507189A true CN111507189A (en) 2020-08-07
CN111507189B CN111507189B (en) 2022-12-06

Family

ID=71869304

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010188034.3A Active CN111507189B (en) 2020-03-17 2020-03-17 Insulator string defect rapid detection method based on image processing technology

Country Status (1)

Country Link
CN (1) CN111507189B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112444522A (en) * 2020-11-16 2021-03-05 中国科学院沈阳自动化研究所 Method for detecting defects of insulator string of power system
CN113393453A (en) * 2021-06-28 2021-09-14 北京百度网讯科技有限公司 Method, apparatus, device, medium and product for detecting self-bursting insulators
CN113421261A (en) * 2021-08-23 2021-09-21 金成技术有限公司 Structural member production process defect detection method based on image processing

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103605981A (en) * 2013-12-03 2014-02-26 国家电网公司 Insulator defect identification method based on image identification
CN105701484A (en) * 2016-03-02 2016-06-22 成都翼比特自动化设备有限公司 Insulator explosion algorithm based on image identification technology
CN106570853A (en) * 2015-10-08 2017-04-19 上海深邃智能科技有限公司 Shape and color integration insulator identification and defect detection method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103605981A (en) * 2013-12-03 2014-02-26 国家电网公司 Insulator defect identification method based on image identification
CN106570853A (en) * 2015-10-08 2017-04-19 上海深邃智能科技有限公司 Shape and color integration insulator identification and defect detection method
CN105701484A (en) * 2016-03-02 2016-06-22 成都翼比特自动化设备有限公司 Insulator explosion algorithm based on image identification technology

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112444522A (en) * 2020-11-16 2021-03-05 中国科学院沈阳自动化研究所 Method for detecting defects of insulator string of power system
CN113393453A (en) * 2021-06-28 2021-09-14 北京百度网讯科技有限公司 Method, apparatus, device, medium and product for detecting self-bursting insulators
CN113421261A (en) * 2021-08-23 2021-09-21 金成技术有限公司 Structural member production process defect detection method based on image processing
CN113421261B (en) * 2021-08-23 2021-11-05 金成技术有限公司 Structural member production process defect detection method based on image processing

Also Published As

Publication number Publication date
CN111507189B (en) 2022-12-06

Similar Documents

Publication Publication Date Title
CN111507189B (en) Insulator string defect rapid detection method based on image processing technology
CN108280855A (en) A kind of insulator breakdown detection method based on Fast R-CNN
CN108037133A (en) A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image
CN109344905A (en) A kind of transmission facility automatic fault recognition methods based on integrated study
CN106340009B (en) A kind of electric power line detecting method and system based on parallel binocular
CN104764748A (en) Method and system for positioning insulators and method and system for fault detection
CN111914813A (en) Power transmission line inspection image naming method and system based on image classification
CN109829908B (en) Binocular image-based method and device for detecting safety distance of ground object below power line
CN112435208B (en) Insulator region detection method for significant edge guidance
CN103529362A (en) Perception based insulator recognition and defect diagnosis method
CN107179479B (en) Visible light image-based transmission conductor strand scattering defect detection method
CN108288055A (en) Block of bow collector of electric locomotive based on depth network and placement test and arc method for measuring
CN105957073A (en) Fault detection method for scattered strands in power transmission line
Fang et al. Fast detection method of insulator fault based on image processing technology
CN111046950A (en) Image processing method and device, storage medium and electronic device
CN112906620A (en) Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment
Wang et al. Pointer meter recognition in UAV inspection of overhead transmission lines
CN110490261B (en) Positioning method for power transmission line inspection image insulator
CN114694050A (en) Power equipment running state detection method based on infrared image
CN112270234B (en) Power transmission line insulation sub-target identification method based on aerial image
Fang et al. A framework of power pylon detection for UAV-based power line inspection
Fang et al. Detection method of transmission line broken stock defects in aircraft inspection based on image processing technology
CN110070520B (en) Pavement crack detection model construction and detection method based on deep neural network
CN103198326A (en) Electric transmission line helicopter routing inspection image classification method
CN113920450A (en) Method and device for identifying insulator RTV coating based on intrinsic image decomposition

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