CN108256517A - Laser radar-based insulator string identification method - Google Patents

Laser radar-based insulator string identification method Download PDF

Info

Publication number
CN108256517A
CN108256517A CN201611234430.5A CN201611234430A CN108256517A CN 108256517 A CN108256517 A CN 108256517A CN 201611234430 A CN201611234430 A CN 201611234430A CN 108256517 A CN108256517 A CN 108256517A
Authority
CN
China
Prior art keywords
insulator chain
depth
insulator
laser radar
depth image
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
CN201611234430.5A
Other languages
Chinese (zh)
Other versions
CN108256517B (en
Inventor
姜勇
刘国伟
王洪光
朱正国
宋屹峰
陈鹏
何斌斌
刘澈
胡冉
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.)
Shenzhen Power Supply Co ltd
Shenyang Institute of Automation of CAS
Original Assignee
Shenzhen Power Supply Co ltd
Shenyang Institute of Automation of CAS
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 Shenzhen Power Supply Co ltd, Shenyang Institute of Automation of CAS filed Critical Shenzhen Power Supply Co ltd
Priority to CN201611234430.5A priority Critical patent/CN108256517B/en
Publication of CN108256517A publication Critical patent/CN108256517A/en
Application granted granted Critical
Publication of CN108256517B publication Critical patent/CN108256517B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to an insulator string identification method based on a laser radar, which comprises the following steps: acquiring a depth image: obtaining a depth image through laser radar equipment arranged on the robot; preprocessing of the depth image: preprocessing the depth image with the insulator string to obtain an interested area; feature extraction of the depth image: in the interested region, establishing a depth characteristic curve model, constructing a depth periodic characteristic matrix and a width vector, and extracting insulator string segment number characteristics and disc diameter variation characteristics; identifying the type of an insulator string: and identifying the type of the insulator string according to the extracted features. According to the invention, the insulator string is identified by utilizing the gray scale periodic characteristic and the gray scale threshold characteristic according to the characteristics of the insulator string. The accuracy of the recognition result is high, the working efficiency is improved, and a basis is provided for the inspection robot of the transformer substation to complete the washing task.

Description

Insulator chain recognition methods based on laser radar
Technical field
It is applied to autonomous classification method of the Substation Insulator string based on laser radar the present invention relates to a kind of, specifically It is a kind of insulator chain automatic identifying method based on machine vision.
Background technology
The insulator of on-line operation, in natural environment, by SO2, the big compression ring such as nitrogen oxides and graininess dust The influence in border gradually deposited one layer of dunghill on its surface.In the case of dry weather, these insulators can keep compared with It is approached when high dielectric level, discharge voltage and cleaning, drying regime；When meeting the wet weathers such as mist, dew, rain, Yi Jirong When ice, snow melt, insulator causes the electrolyte dissolution in pollution layer because of surface filth object absorption moisture, causes insulator dielectric water Pancake is low, and flashover fault occurs when serious for leakage current increase.Therefore, insulator chain needs are periodically cleaned.
At this stage, the main means of insulator chain cleaning are cleaned by the professional of substation.It is carrying out clearly It is big there are labor intensity when washing, it is dangerous high the problems such as.
As a kind of advanced technological means, Intelligent Mobile Robot can replace artificial progress insulator chain flushing to appoint Business.To complete this task equipment people automatic identification need to be carried out to insulator chain.Therefore it needs to propose that a kind of the degree of automation is higher Insulator chain automatic identifying method.
Since insulator chain is in outdoor environment, illumination variation is complicated, and is set up in substation complicated.Pass through Laser radar detects, can be to avoid influence of the illumination to sensor, while can overcome the influence of complex background, can be good at Adapt to outdoor environment.And there is not been reported currently based on the insulator chain automatic identifying method of laser radar.
Invention content
It is in view of the above-mentioned problems, high based on laser radar the technical problem to be solved in the present invention is to provide a kind of accuracy of identification Insulator chain automatic identifying method.
The technical solution adopted by the present invention to solve the technical problems is：Insulator chain identification side based on laser radar Method includes the following steps：
The acquisition of depth image：Depth image is obtained by the laser radar apparatus installed in robot；
The pretreatment of depth image：The depth image for carrying insulator chain is pre-processed, obtains interested region；
The feature extraction of depth image：In interested region, depth characteristic curve model is established, builds the depth period Property eigenmatrix and width vector, extract insulator chain hop count feature and disk diameter variation characteristic；
Insulator chain type identification：Insulator chain type is identified according to the feature extracted.
The pretreatment of the depth image includes the following steps：
(2.1) to depth image binary conversion treatment, prospect, background in depth image are isolated, and eliminate background interference；
(2.2) to treated, bianry image uses dilation operation, then using erosion operation, eliminates dry on bianry image Disturb pixel；
(2.3) and then largest connected domain is chosen, extracts area-of-interest, complete pretreatment.
It is described that establish depth characteristic curve model as follows：
Extract target area left hand edge：
lik=k,
Extract target area right hand edge：
rik=k,
In formula D (x, y) be bianry image, the line number of k representative images, the columns of t representative images, lk, rkFor the picture on edge Vegetarian refreshments position；
Position on the center line of target area is determined by left hand edge and right hand edge：
mik=k,
M in formulakFor the coordinate of depth characteristic curve pixel, mikFor depth characteristic curve pixel row coordinate, mjkFor depth Spend indicatrix pixel point range coordinate；nIFor picturedeep；
Establish depth characteristic curve model:
f(xk,yk)=0
Wherein:
xk=mik
xkIt is characterized the abscissa of curve, i.e. picturedeep, ykIt is characterized the ordinate of curve, i.e. depth value；L(mk) table Show depth image.
The structure depth periodic feature matrix：
Depth characteristic curve f (x are first obtainedk,ykMaximum and minimum on)=0；Establish matrix
In formula：
v2kFor depth characteristic curve f (xk,ykThe abscissa of extreme point, v on)=03kFor depth characteristic curve f (xk,yk)= The ordinate of extreme point, i.e. depth value on 0；K=1,2 ... nI；
Given threshold λc1,λc2And λc1﹤ λc2；It is right againTraverse by row, by V3,k+1-V3,k＞ λc1And V3,k+1- V3,k＜ λc2When V1,kWith V2,kIt is recorded；At the end of traversal, the value for the condition that meets is formed into matrix by record sequenceBy v1,kIt is recorded in matrixThe first row, v2,kThe second row of matrix is recorded in, is obtained：
n3For matrix columns；
It is right againIt is traversed, is enabled by row
c1,k=abs (v11,k+1-v11,k)
c2,k=v12,k+1-v12,k
c3,k=v12,k
Obtain depth periodic feature matrix
Build width vector：
In formula：
I=1,2 ... nI
(xi1,yi1,zi1) be left hand edge point space coordinate, (xi2,yi2,zi2) be right hand edge point space coordinate；nITable Show picturedeep.
It is described to extract insulator chain hop count feature and disk diameter variation characteristic includes the following steps：
(1) byExtract insulator chain hop count feature
Given threshold α firstc, initialization flag position δcIt is 0, segment number information Num (C) is 0；
It is right againIt is traversed by row：
Work as C1,k=1, C2,k＜ αcAnd δcWhen=0, flag bit δ is putcIt is 1, and by C3,kIt is stored in vector T and is used as insulator String top edge；
Work as δc=1 and C1,k=0 or C2,k＞ αcWhen, put flag bit δcIt is 0, by C3,kIt is stored in vector T and is used as insulator String lower edge, and segment number information Num (C) is added 1；
Upper and lower edge of the vector T for insulator chain, wherein odd term element t2n-1For the top edge of insulator chain, even number Item element t2nLower edge for insulator chain；N=1,2 ... k1；k1Length for vector T.
(2) by the disk diameter variation characteristic of W extraction insulator chains
Insulator chain width variance is calculated according to vector T：
Work as d2＜ threshold alphaswWhen, the insulator is waits disks diameter, otherwise, to become disk diameter.
Insulator chain type, which is identified, in the feature that the basis extracts includes the following steps：
If Num (C)=1, and d2＜ threshold alphasw, then insulator chain is the disks diameter insulator chains such as single hop；If Num (C)=2, and d2＜ threshold alphasw, then insulator chain is the disks diameter insulator chains such as double sections, if Num (C)=1, and d2＞ threshold alphasw, then insulator chain Become disk through insulator chain for single hop.
The invention has the advantages that and advantage：
Using laser depth periodic feature, 1. insulator chain pitch characteristics and disk diameter feature are identified the present invention, right The identification accuracy of insulator is high, improves work efficiency, and completing task to Intelligent Mobile Robot later provides foundation.
2. the present invention, as sensor, under backlighting condition, equally can accurately identify insulation using laser radar Substring.In depth image, foreground and background can also be accurately detached, overcomes influence of the complex background to accuracy of identification.
Description of the drawings
Fig. 1 is the flow diagram of the present invention；
Fig. 2 is laser depth map；
Fig. 3 is pretreated depth binary map；
Fig. 4 is depth characteristic curve graph；
Fig. 5 is recognition effect figure.
Specific embodiment
With reference to embodiment, the present invention is described in further detail.
A kind of insulator chain automatic identifying method based on laser radar, includes the following steps：
(1) acquisition of depth image：Laser radar apparatus on Intelligent Mobile Robot is installed, is fixed on holder, Laser radar rotates fixed angle, obtains depth image；
(2) pretreatment of depth image：The depth image for carrying insulator chain is pre-processed, obtains interested area Domain.
(3) feature extraction of depth image：In interested region, depth characteristic curve model is established, builds depth Periodic feature matrix and width vector, extract insulator chain hop count feature and disk diameter variation characteristic.
(4) insulator chain type identification：Insulator chain type is identified according to the feature extracted.
The pretreatment of the depth image includes the following steps：
(2.1) by depth binary conversion treatment, the prospect background in depth image is isolated, and eliminate in depth image and carry on the back Scape interferes.
(2.2) using morphological image process depth bianry image, first using dilation operation, then using erosion operation, Eliminate the interference pixel on depth bianry image.
(2.3) largest connected domain is chosen in depth binary map, extracts interested region, completes pretreatment.
The feature extracting method of the depth image is as follows：
(3.1) depth characteristic curve model is established, the depth characteristic curve of definition can reflect insulator chain feature, method It is as follows：
Extract target area left hand edge：
lik=k,
Extract target area right hand edge：
rik=k,
In formula D (x, y) be depth bianry image, the line number of k representative images, the columns of t representative images, lk, rkFor on edge Pixel position.nIIt is represented as the maximum number of lines of image.It can be determined on the center line of target area by the two set Location sets.
mik=k,
M in formulakFor the coordinate of depth characteristic curve pixel, mikFor depth characteristic curve pixel row coordinate, mjkFor depth Spend indicatrix pixel point range coordinate.
Establish depth characteristic curve model:
f(xk,yk)=0
Wherein:
xk=mik
xkIt is characterized the abscissa of curve, i.e. picturedeep, ykIt is characterized the ordinate of curve, i.e. depth value；L(mk) table Show depth image.
(3.2) depth periodic feature matrix and width vector are built by certain rule, and extracts insulator chain section Number feature and disk diameter variation characteristic.
The insulator chain hop count feature extracted in depth image and width characteristics are analyzed, and are completed to insulation Substring identifies.
Insulator chain automatic identifying method flow chart based on laser radar is as indicated with 1.Idiographic flow is as follows：
1. laser radar gathered data
Laser radar scanning insulator chain region, obtains laser depth image L (x, y), as shown in Figure 2.
2. image preprocessing
Depth image is subjected to binaryzation by formula (1)：
D (x, y) represents binaryzation, and M is threshold value.Dilation erosion operation is carried out again, marks largest connected domain.It is preprocessed Afterwards, prospect background is may separate out, obtains insulator chain and its erection.As shown in Figure 3.
3. establish depth characteristic curve model
The depth cyclically-varying in region, establishes depth characteristic curve model according to residing for insulator chain in depth image, Method is as follows：
Extract target area left hand edge：
lik=k,
Extract target area right hand edge：
rik=k,
In formula D (x, y) be bianry image, the line number of k representative images, the columns of t representative images, lk, rkFor the picture on edge Vegetarian refreshments position.Left and right edge is respectively the left and right edge of insulator chain.Target area can be determined by the two set The location sets of center line.
mik=k,
M in formulakFor the coordinate of depth characteristic curve pixel, mikFor depth characteristic curve pixel row coordinate, mjkFor depth Spend indicatrix pixel point range coordinate.
Establish depth characteristic curve model:
f(xk,yk)=0
Wherein:
xk=mik
As shown in figure 4, abscissa represents picturedeep, ordinate represents depth value.
4. build depth periodic feature and width characteristics vector
(1) depth periodic feature matrix is built：
Depth characteristic curve f (x are first obtainedk,ykMaximum and minimum on)=0.Establish matrix
In formula：
v2kFor depth characteristic curve f (xk,ykThe abscissa of extreme point, v on)=03kFor depth characteristic curve f (xk,yk)= The ordinate of extreme point, i.e. depth value on 0.n1Representing matrixColumns, n2Representing matrixColumns.
Given threshold λc1,λc2, λc1﹤ λc2, the present embodiment takes 3,10 respectively.It is right againTraversed by row, it will v3,k+1-v3,k＞ λc1And v3,k+1-v3,k＜ λc2When v1,kWith v2,kIt is recorded.At the end of traversal, by the value for the condition that meets Matrix is formed by record sequenceBy v1,kIt is recorded in matrixThe first row, v2,kIt is recorded in the second of matrix Row, obtains：
n3For matrix columns.
V1 by row is traversed again, is enabled
c1,k=abs (v11,k+1-v11,k)
c2,k=v12,k+1-v12,k
c3,k=v12,k
Obtain depth periodic feature matrix.
(2) structure width characteristics vector is as follows：
In formula：
I=1,2...nI
(xi1,yi1,zi1) be left hand edge point space coordinate, (xi2,yi2,zi2) be right hand edge point space coordinate.nITable The maximum number of lines of diagram picture.Here
5. extract insulator chain hop count feature and disk diameter feature
(1) byExtract insulator chain hop count feature
Given threshold α firstc, the present embodiment takes 15.Initialization flag position δcIt is 0, segment number information Num (C) is 0.
It is right againIt is traversed by row.Work as C1,k=1, C2,k＜ αcAnd δcWhen=0, flag bit δ is putcIt is 1, and will C3,kIt is stored in vector T and is used as insulator chain top edge.Work as δc=1 and C1,k=0 or C2,k＞ αcWhen, put flag bit δcIt is 0, it will C3,kIt is stored in as insulator chain lower edge in vector T, and segment number information Num (C) is added 1.It traverses to matrix end, completion pair The identification of insulator chain.Lower edges of the vector T for insulator chain, wherein odd term element t2n-1Top for insulator chain Edge, even item element t2nLower edge for insulator chain.N=1,2 ... k1；k1Length for vector T.
(2) by the disk diameter variation characteristic of W extraction insulator chains
Insulator chain width variance is calculated according to vector T：
Work as d2＜ αwWhen, αwFor threshold value, the present embodiment takes 0.01.；Extraction disk diameter such as is characterized as at the disks diameter, otherwise, extracts disk diameter It is characterized as becoming disk diameter.
6. insulator chain type identification
Three kinds of post insulator substrings in substation are identified according to segment number information and disk diameter change information.According to obtaining Hop count feature and disk diameter feature be combined, if Num (C)=1, and d2＜ threshold alphasw, then insulator chain is exhausted for disks diameters such as single hops Edge substring, if Num (C)=2, and d2＜ threshold alphasw, then insulator chain is the disks diameter insulator chains such as double sections, if Num (C)=1, and d2＞ threshold alphasw, then insulator chain is single hop change disk through insulator chain.The identification of three kinds of insulator chains is commonly used substation in completion. As shown in figure 5, for disks diameter insulator chains such as double sections.

Claims (7)

1. the insulator chain recognition methods based on laser radar, which is characterized in that include the following steps：
The acquisition of depth image：Depth image is obtained by the laser radar apparatus installed in robot；
The pretreatment of depth image：The depth image for carrying insulator chain is pre-processed, obtains interested region；
The feature extraction of depth image：In interested region, depth characteristic curve model is established, structure depth is periodically special Matrix and width vector are levied, extracts insulator chain hop count feature and disk diameter variation characteristic；
Insulator chain type identification：Insulator chain type is identified according to the feature extracted.
2. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that the depth map The pretreatment of picture includes the following steps：
(2.1) to depth image binary conversion treatment, prospect, background in depth image are isolated, and eliminate background interference；
(2.2) to treated, bianry image uses dilation operation, then using erosion operation, eliminates the interference picture on bianry image Vegetarian refreshments；
(2.3) and then largest connected domain is chosen, extracts area-of-interest, complete pretreatment.
3. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that described to establish deeply It is as follows to spend indicatrix model：
Extract target area left hand edge：
lik=k,
Extract target area right hand edge：
rik=k,
In formula D (x, y) be bianry image, the line number of k representative images, the columns of t representative images, lk, rkFor the pixel on edge Position；
Position on the center line of target area is determined by left hand edge and right hand edge：
mik=k,
M in formulakFor the coordinate of depth characteristic curve pixel, mikFor depth characteristic curve pixel row coordinate, mjkFor depth spy Levy curve pixel point range coordinate；nIFor picturedeep；
Establish depth characteristic curve model:
f(xk,yk)=0
Wherein:
xk=mik
xkIt is characterized the abscissa of curve, i.e. picturedeep, ykIt is characterized the ordinate of curve, i.e. depth value；L(mk) represent deep Spend image.
4. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that the structure is deep Spend periodic feature matrix：
Depth characteristic curve f (x are first obtainedk,ykMaximum and minimum on)=0；Establish matrix
In formula：
v2kFor depth characteristic curve f (xk,ykThe abscissa of extreme point, v on)=03kFor depth characteristic curve f (xk,ykOn)=0 The ordinate of extreme point, i.e. depth value；K=1,2 ... nI；
Given threshold λc1,λc2And λc1﹤ λc2；It is right againTraverse by row, by V3,k+1-V3,k＞ λc1And V3,k+1-V3,k＜ λc2When V1,kWith V2,kIt is recorded；At the end of traversal, the value for the condition that meets is formed into matrix by record sequence By v1,kIt is recorded in matrixThe first row, v2,kThe second row of matrix is recorded in, is obtained：
n3For matrix columns；
It is right againIt is traversed, is enabled by row
c1,k=abs (v11,k+1-v11,k)
c2,k=v12,k+1-v12,k
c3,k=v12,k
Obtain depth periodic feature matrix
5. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that structure width to Amount：
In formula：
(xi1,yi1,zi1) be left hand edge point space coordinate, (xi2,yi2,zi2) be right hand edge point space coordinate；nIRepresent image Line number.
6. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that described to extract Insulator chain hop count feature and disk diameter variation characteristic include the following steps：
(1) byExtract insulator chain hop count feature
Given threshold α firstc, initialization flag position δcIt is 0, segment number information Num (C) is 0；
It is right againIt is traversed by row：
Work as C1,k=1, C2,k＜ αcAnd δcWhen=0, flag bit δ is putcIt is 1, and by C3,kIt is stored in vector T as on insulator chain Edge；
Work as δc=1 and C1,k=0 or C2,k＞ αcWhen, put flag bit δcIt is 0, by C3,kIt is stored in vector T as under insulator chain Edge, and segment number information Num (C) is added 1；
Upper and lower edge of the vector T for insulator chain, wherein odd term element t2n-1For the top edge of insulator chain, even item element t2nLower edge for insulator chain；N=1,2 ... k1；k1Length for vector T.
(2) by the disk diameter variation characteristic of W extraction insulator chains
Insulator chain width variance is calculated according to vector T：
Work as d2＜ threshold alphaswWhen, the insulator is waits disks diameter, otherwise, to become disk diameter.
7. the insulator chain recognition methods according to claim 1 based on laser radar, which is characterized in that the basis carries Insulator chain type, which is identified, in the feature of taking-up includes the following steps：
If Num (C)=1, and d2＜ threshold alphasw, then insulator chain is the disks diameter insulator chains such as single hop；If Num (C)=2, and d2＜ Threshold alphaw, then insulator chain is the disks diameter insulator chains such as double sections, if Num (C)=1, and d2＞ threshold alphasw, then insulator chain is single Duan Bianpan is through insulator chain.
CN201611234430.5A 2016-12-28 2016-12-28 Laser radar-based insulator string identification method Active CN108256517B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611234430.5A CN108256517B (en) 2016-12-28 2016-12-28 Laser radar-based insulator string identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611234430.5A CN108256517B (en) 2016-12-28 2016-12-28 Laser radar-based insulator string identification method

Publications (2)

Publication Number Publication Date
CN108256517A true CN108256517A (en) 2018-07-06
CN108256517B CN108256517B (en) 2021-05-28

Family

ID=62719369

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611234430.5A Active CN108256517B (en) 2016-12-28 2016-12-28 Laser radar-based insulator string identification method

Country Status (1)

Country Link
CN (1) CN108256517B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112037137A (en) * 2020-07-21 2020-12-04 国网湖北省电力有限公司电力科学研究院 Method and device for eliminating fuzzy region of insulator disc surface edge in infrared image
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
CN113538454A (en) * 2021-06-03 2021-10-22 北京道亨软件股份有限公司 Method for automatically dividing multi-connected insulator string insulation areas

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090019535A (en) * 2007-08-21 2009-02-25 금오테크(주) Non-contact system for measuring insulator aging and disconnection of electric power distribution
CN103714342A (en) * 2013-12-20 2014-04-09 华北电力大学（保定） An aerial-photo insulator chain automatic positioning method based on binary image shape features

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090019535A (en) * 2007-08-21 2009-02-25 금오테크(주) Non-contact system for measuring insulator aging and disconnection of electric power distribution
CN103714342A (en) * 2013-12-20 2014-04-09 华北电力大学（保定） An aerial-photo insulator chain automatic positioning method based on binary image shape features

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
严凯 等: "航拍绝缘子图像的检测与识别方法研究", 《贵州电力技术》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112037137A (en) * 2020-07-21 2020-12-04 国网湖北省电力有限公司电力科学研究院 Method and device for eliminating fuzzy region of insulator disc surface edge in infrared image
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
CN113538454A (en) * 2021-06-03 2021-10-22 北京道亨软件股份有限公司 Method for automatically dividing multi-connected insulator string insulation areas

Also Published As

Publication number Publication date
CN108256517B (en) 2021-05-28

Similar Documents

Publication Publication Date Title
CN107742286B (en) Method for detecting EL test crack defects of polycrystalline silicon solar cell
CN106980816B (en) Automatic insulator string identification method based on optical image
CN109596634B (en) Cable defect detection method and device, storage medium and processor
CN108009591B (en) Contact network key component identification method based on deep learning
Liao et al. Study on power line insulator defect detection via improved faster region-based convolutional neural network
CN107727662B (en) Battery piece EL black spot defect detection method based on region growing algorithm
CN111652857B (en) Infrared detection method for insulator defects
CN111754465B (en) Insulator positioning and string dropping detection method
CN107895376A (en) Based on the solar panel recognition methods for improving Canny operators and contour area threshold value
CN107492094A (en) A kind of unmanned plane visible detection method of high voltage line insulator
CN108256517A (en) Laser radar-based insulator string identification method
CN104318556B (en) Silicon steel plate surface defect image detection method under oil pollution interference
CN107808141A (en) A kind of electric transmission line isolator explosion recognition methods based on deep learning
CN103487729A (en) Electrical equipment defect detection method based on fusion of ultraviolet video and infrared video
CN108734691A (en) A kind of transmission line of electricity defect image recognition methods
CN105957081B (en) A kind of glass insulator falls to go here and there fault detection method
CN108629777A (en) A kind of number pathology full slice image lesion region automatic division method
Li et al. Application of multi-scale feature fusion and deep learning in detection of steel strip surface defect
CN109685788A (en) A kind of flooring defect image automatic testing method based on morphological feature
CN102519846A (en) Hyperspectrum-based composite insulator hydrophobicity detection method
CN104615990A (en) Method for automatically recognizing macula based on Huairou full-disk single-color image
CN105427287A (en) Projection transformation-based connected region marking method
CN113902792A (en) Building height detection method and system based on improved RetinaNet network and electronic equipment
CN117314893A (en) Quality detection method for photovoltaic steel structure component based on image processing
Chen et al. Research on anti-interference detection of 3D-printed ceramics surface defects based on deep learning

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