CN112150412A - Insulator self-explosion defect detection method based on projection curve analysis - Google Patents

Insulator self-explosion defect detection method based on projection curve analysis Download PDF

Info

Publication number
CN112150412A
CN112150412A CN202010899222.7A CN202010899222A CN112150412A CN 112150412 A CN112150412 A CN 112150412A CN 202010899222 A CN202010899222 A CN 202010899222A CN 112150412 A CN112150412 A CN 112150412A
Authority
CN
China
Prior art keywords
insulator
pixel
image
insulator string
peak
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
CN202010899222.7A
Other languages
Chinese (zh)
Other versions
CN112150412B (en
Inventor
杨威
潘永贺
宋人杰
李英杰
顾志伟
洪宬
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.)
Northeast Electric Power University
Changshan Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Quzhou Guangming Electric Power Investment Group Co ltd Futeng Technology Branch
Northeast Dianli University
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 Quzhou Guangming Electric Power Investment Group Co ltd Futeng Technology Branch, Northeast Dianli University filed Critical Quzhou Guangming Electric Power Investment Group Co ltd Futeng Technology Branch
Priority to CN202010899222.7A priority Critical patent/CN112150412B/en
Publication of CN112150412A publication Critical patent/CN112150412A/en
Application granted granted Critical
Publication of CN112150412B publication Critical patent/CN112150412B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • 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
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • 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
    • G06T2207/20004—Adaptive image processing
    • 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
    • G06T2207/20024—Filtering details
    • G06T2207/20028—Bilateral filtering
    • 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
    • G06T2207/20036—Morphological image processing
    • 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
    • G06T2207/20048—Transform domain processing
    • G06T2207/20061—Hough transform
    • 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

Landscapes

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

Abstract

The invention discloses an insulator self-explosion defect detection method based on projection curve analysis, which comprises the steps of utilizing a super-pixel segmentation method of local texture characteristics to carry out super-pixel segmentation on a gray image on the basis of extracting an insulator string from an original insulator image obtained by an unmanned aerial vehicle, determining an insulator string candidate region, utilizing Hough transform to carry out angle correction on the insulator string candidate region to obtain a target region of the insulator string to be detected, calculating the pixel proportion of pixel values in an insulator mask between peak sections, carrying out self-explosion defect fault detection on the insulator string region, accurately identifying an insulator string fault point by positioning and identifying through a vertical projection method, and finally accurately identifying the insulator string fault point by positioning and identifying through the vertical projection method to improve the identification rate and accuracy of the insulator fault point.

Description

Insulator self-explosion defect detection method based on projection curve analysis
Technical Field
The invention relates to the field of fault diagnosis of high-voltage wire insulator defects, in particular to an insulator self-explosion defect detection method based on projection curve analysis.
Background
When the power transmission line operates, the insulator is a special insulating control and plays an important role in safe and stable operation of the power transmission line. However, since the insulator is exposed to the open air for a long time, the insulator is very likely to have a failure such as spontaneous explosion and breakage due to the influence of the natural environment and heavy mechanical load. Once the insulator breaks down, hidden danger can be produced to transmission line's operation safety, can reduce transmission line's operating cycle when serious, can cause the power supply to break off even, the accident that takes place to have a power failure on a large scale causes huge loss of property. Therefore, the insulator condition is regularly monitored, insulator faults can be effectively found and timely replacement can be processed, and the method has important significance for safe operation of a power system.
Traditional high voltage transmission equipment patrols and examines the mode and mainly uses the manual work to patrol and examine as the main, and this kind of mode inefficiency of patrolling and examining, some field of vision blind areas can't detect to electric power workman need climb the electricity tower, intensity of labour is too big, and the security is low. At present, the technology for carrying out routing inspection and maintenance on high-voltage line equipment by utilizing an Unmanned Aerial Vehicle (UAV) is relatively mature in developed countries, the technology greatly reduces the labor cost and the labor intensity of workers, and the working efficiency is improved. Compare in traditional artifical pole-climbing mode of patrolling and examining, utilize unmanned aerial vehicle to patrol and examine the line and shoot, carry out analysis processes to the insulator according to image processing technique, and then realize the automated inspection insulator defect, can effectively reduce staff's burden, patrol and examine to transmission line is automatic to have realistic meaning. However, the existing detection technology has the problems of low precision and inaccurate defect positioning.
Disclosure of Invention
Aiming at the problems in the prior art, the invention creatively utilizes a super-pixel segmentation method of local texture characteristics to carry out super-pixel segmentation on a gray image and determine an insulator string candidate area; carrying out angle correction on the insulator string candidate region by using Hough transform to obtain a target region of the insulator string to be detected; and calculating the pixel proportion of pixel values in the insulator mask between the wave peak sections, carrying out self-explosion defect fault detection on the insulator string region, and positioning and identifying through a vertical projection method to accurately identify the fault point of the insulator string, thereby improving the identification rate and accuracy of the fault point of the insulator.
The technical scheme adopted for realizing the invention is as follows: a projection curve analysis-based insulator spontaneous explosion defect detection method is characterized by comprising the following steps:
shooting an insulator string to be detected on an overhead tower power transmission line by an unmanned aerial vehicle to obtain an original image of the insulator string to be detected, wherein the original image of the insulator string to be detected comprises the insulator string and background information thereof, and the insulator string is an insulator assembly formed by connecting insulators with the same shape and size in series through a core rod;
performing graying processing on the original image of the insulator string to be detected in the step I to obtain a grayscale image, performing superpixel segmentation on the grayscale image by using a superpixel segmentation method of local texture characteristics, determining an insulator string candidate region by combining an adaptive threshold method and image morphological operation, and storing the insulator string candidate region in a set I ═ I1,I2,...,InN is the number of candidate regions;
thirdly, angle correction is carried out on the insulator string candidate regions in the second step by utilizing Hough transform to obtain corrected images, vertical projection is carried out on each candidate region to obtain a projection curve graph, and the obtained curve graph is analyzed to obtain a target region of the insulator string to be detected, wherein the method specifically comprises the following steps:
3.1) fitting a main shaft straight line of the candidate region by random consistent sampling, rotating the main shaft of the candidate region to the horizontal direction, and starting traversing the insulator string candidate region set I, knowing that the insulator string candidate region image obtained in the step two is a binary image, knowing that pixel values corresponding to pixel points are only {0, 255} two values, and carrying out accumulated projection on the pixel points with the pixel point value of 255 in the mask of the insulator candidate region image according to the vertical direction to obtain a projection curve, wherein the pixel accumulation formula is as follows:
Figure BDA0002659417990000021
wherein, S (x) represents a cumulative function of non-0 pixel values of the candidate area image mask of the insulator string in each column direction, (I, x) is the pixel point coordinate on the image, I (I, x) represents the pixel value of the pixel point (I, x) of the kth candidate area image, and r is the maximum line number corresponding to the image mask two-dimensional matrix along the horizontal direction;
3.2) in order to determine that the candidate region is an insulator string, a sign determination function sgn (x) is set, and a difference quantity function Δ S (x) ═ S (x +1) -S (x) is calculated and used for searching a projection curve peak. The symbol decision function is formulated as follows:
Figure BDA0002659417990000022
when sgn (x +1) ≧ 0, sgn (x) is set to be 1, otherwise sgn (x) is set to be-1; at this time, the original value of sgn (x) is corrected to 0, so as to extract the peak value of the projection curve in the later period;
performing forward traversal on sgn (x), which means that when sgn (x +1) -sgn (x) -2, (x, s (x)) is a peak coordinate corresponding to the projection curve; storing the horizontal coordinates of the pixel points of all the wave crests to a set xpoint＝{x1,x2...xnIn (c) } the reaction solution is,wherein n is the number of wave crests; computing a set xpointAverage projected cumulative value S of all peak points in the waveX_avgsAnd finding the maximum projected cumulative value SX_max(ii) a Peak point average projected cumulative value SX_avgsAnd a maximum projected cumulative value SX_maxRespectively as follows:
Figure BDA0002659417990000031
SX_max＝max(S(xi))
setting the peak threshold th to 0.75SX_avgs+0.25*SX_maxAll the peak points of S (x) < th are dropped, and the set x is updatedpointAnd the peak mean SX_avgs(ii) a Calculating the variance D of the peak value2The formula is as follows:
Figure BDA0002659417990000032
in the formula, D2Representing the variance of the peak points, wherein n represents the number of the peak points;
setting variance threshold DthAs 5, the candidate region decision formula is:
Figure BDA0002659417990000033
if the candidate area is an insulator string area, continuing to execute the next step, and if the candidate area is a non-insulator string area, returning to the step II to add 1 to the k value for continuing to execute the step II;
fourthly, calculating the pixel proportion of pixel values in the insulator mask between the wave peak sections, and carrying out self-explosion defect fault detection on the insulator string region obtained in the third step, wherein the self-explosion defect fault detection specifically comprises the following steps: considering from the insulator form wave structure, when the candidate area is an insulator string, after the image is vertically projected, the sudden change between two wave peak sections is found out according to a certain criterion as the position of the insulator with the self-explosion defect; from a sequence of peak points (x)1,x2,...xn) Setting the pixel value in the insulator mask between the peak sections as255 is g (x)p) The pixel proportion is used as a characteristic for searching the self-explosion defect interval, and the pixel proportion formula is as follows:
Figure BDA0002659417990000034
in the formula, g (x)p) Represents the pixel ratio, x, of 255 in the insulator mask between the peak sectionspIs the p-th peak point in the sequence of peak points, row (I)k) The width of the candidate region image of the ith insulator string in the set I is taken as the width of the candidate region image of the ith insulator string in the set I;
further, based on the fact that the self-explosion defect of the insulator has a small value of g (x), constructing an algorithm for detecting the self-explosion defect position of the insulator as follows:
4.1) calculate area ═ max (g (x)p))+min(g(xp) 2, where area is the median of g (x);
4.2) if
Figure BDA0002659417990000035
Then the peak band [ x ] is indicatedp,xp+1]The self-explosion defect exists;
image mask I for insulator string in candidate regionkAnd finally, inversely mapping the positions of the insulators detected in the coordinate system to an input image according to the change relation between the image coordinates, and finishing the final positioning of the defects of the insulators of the image when the insulator string candidate region set I is traversed.
The super-pixel segmentation method of the local texture features comprises the following steps:
1) after converting an image from an RGB image into an LAB color space, initializing a clustering center, and calculating the similarity measurement D of two pixel points by combining texture features:
Figure BDA0002659417990000041
in the formula dcIs the color distance, d, of two pixels in Lab spacesIs a spatial distance, dwFor local textureThe characteristic difference distance s, m and c are constants and comprehensively represent the weight of space, color and texture characteristics in similarity measurement;
wherein d isc,ds,dwComprises the following steps:
Figure BDA0002659417990000042
Figure BDA0002659417990000043
Figure BDA0002659417990000044
in the formula, (l, a, b) represents pixel color characteristics, (x, y) is pixel space coordinates, and w is pixel point texture characteristics;
2) and setting an undirected weighted graph G (V, E) according to the obtained superpixel image, wherein V is a superpixel node set, E is an edge set formed by connecting edges of adjacent superpixels, and the shortest path edge weight value accumulation and calculation formula of any two superpixels comprises the following steps:
Figure BDA0002659417990000045
in the formula dg(ri,rj) Cumulative sum of shortest path edge weights, d, representing any two superpixelsc-lab(ri,rj) Is the mean color characteristic Euclidean distance, r, between two superpixelsi、rjRepresenting a superpixel node; computing superpixel boundary connectivity Bcon(r) the calculation formula is as follows:
Figure BDA0002659417990000046
in the formula Bcon(r) super-pixel boundary connectivity strength, E (r) is geodesic distance weight expansion area surfaceB is the number of pixels connected with the boundary in the statistics r, when the superpixel r is connected with the boundary, b is greater than 0, otherwise, b is 0;
Figure BDA0002659417990000051
and E (r) in the formula is as follows:
where norm is a normalization operation, exp denotes an exponential function with a natural constant e as the base, σ is an equilibrium parameter and is set to 10;
3) different weights are distributed according to the difference of the background super pixel characteristics, and the calculation formula is as follows:
Figure BDA0002659417990000052
in the formula Bp(r) is the weight of the background superpixel, which represents the strength of the background attribute. Calculating the saliency C of the superpixel based on the background prior in combination with the weight valuet(ri)：
Figure BDA0002659417990000053
In the formula Ct(ri) Representing the saliency of a super-pixel, Dc(ri,rj) Is a background super pixel riAnd super pixel rjThe color euclidean distance in LAB space of (a); n is a radical ofBIs the number of background superpixels; dspa(ri,rj) Is a background super pixel riAnd super pixel rjThe spatial distance of (a);
4) setting the number of super pixels as K and setting K as three different scales of 150,200 and 600 respectively, so that more local details can be reserved in significance detection while integral structure information is reserved; performing multi-scale fusion on the significance of the three superpixels under different scales, determining a superpixel significance map through normalization, and finally denoising by utilizing bilateral filtering to obtain a final significance map;
5) and after obtaining the saliency map of the insulator image, performing binary segmentation on the image by using a self-adaptive threshold method, removing noise points in the image by combining morphological operation, calculating a connected domain in the map as a candidate region, marking the candidate region, and preparing for next insulator fault detection.
Drawings
FIG. 1 is a flow chart of a method for detecting self-explosion defects of insulators based on projection curve analysis;
FIG. 2 is a result image after super-pixel segmentation processing of local texture features in an embodiment of a projection curve analysis-based insulator spontaneous explosion defect detection method;
FIG. 3 is a result image obtained by binary morphological processing in an embodiment of a projection curve analysis-based method for detecting self-explosion defects of insulators;
FIG. 4 is a schematic diagram of a vertical projection of an insulator/non-insulator candidate region in an embodiment of a projection curve analysis-based insulator spontaneous explosion defect detection method;
fig. 5 is an image of the recognition result of the self-explosion defect position of the insulator in the embodiment of the method for detecting the self-explosion defect of the insulator based on projection curve analysis.
Detailed Description
The present invention will be described in further detail with reference to the accompanying fig. 1 to 5 and the embodiments, which are described herein for illustrative purposes only and are not intended to limit the present invention.
Referring to a flow chart of a projection curve analysis-based insulator spontaneous explosion defect detection method shown in fig. 1, the projection curve analysis-based insulator spontaneous explosion defect detection method comprises the following steps:
shooting an insulator string to be detected on an overhead tower power transmission line by an unmanned aerial vehicle to obtain an original image of the insulator string to be detected, wherein the original image of the insulator string to be detected comprises the insulator string and background information thereof, and the insulator string is an insulator assembly formed by connecting insulators with the same shape and size in series through a core rod;
② opposite stepsGraying the original image of the insulator string to be detected to obtain a gray image, performing superpixel segmentation on the gray image by using a superpixel segmentation method of local texture characteristics, as shown in fig. 2, determining an insulator string candidate region by combining an adaptive threshold method and image morphological operation, and storing the insulator string candidate region in a set I ═ { I ═ I { (I) }1,I2,...,InN is the number of candidate regions;
the super-pixel segmentation method of the local texture features comprises the following steps:
2.1) after the image is converted into an LAB color space from an RGB image, initializing a clustering center, and calculating the similarity measurement D of two pixel points by combining texture features:
Figure BDA0002659417990000061
in the formula dcIs the color distance, d, of two pixels in Lab spacesIs a spatial distance, dwThe difference distance of the local texture features is obtained, s, m and c are constants, and the weights of the space, the color and the texture features in the similarity measurement are comprehensively represented;
wherein d isc,ds,dwComprises the following steps:
Figure BDA0002659417990000062
Figure BDA0002659417990000063
Figure BDA0002659417990000064
in the formula, (l, a, b) represents pixel color characteristics, (x, y) is pixel space coordinates, and w is pixel point texture characteristics;
2.2) setting an undirected weighted graph G ═ V, E } according to the obtained superpixel image, wherein V is a superpixel node set, E is an edge set formed by connecting edges of adjacent superpixels, and the shortest path edge weight value accumulation and calculation formula of any two superpixels comprises:
Figure BDA0002659417990000065
in the formula dg(ri,rj) Cumulative sum of shortest path edge weights, d, representing any two superpixelsc-lab(ri,rj) Is the mean color characteristic Euclidean distance, r, between two superpixelsi、rjRepresenting a superpixel node; computing superpixel boundary connectivity Bcon(r) the calculation formula is as follows:
Figure BDA0002659417990000071
in the formula Bcon(r) the connectivity of the super-pixel boundary is strong and weak, E (r) is the area of the geodesic distance weight expansion area, b is the number of pixels connected with the boundary in the statistical r, when the super-pixel r is connected with the boundary, b is more than 0, otherwise, b is 0;
Figure BDA0002659417990000072
and E (r) in the formula is as follows:
where norm is a normalization operation, exp denotes an exponential function with a natural constant e as the base, σ is an equilibrium parameter and is set to 10;
2.3) distributing different weights according to the background super-pixel characteristic difference, wherein the calculation formula is as follows:
Figure BDA0002659417990000073
in the formula Bp(r) is the weight of the background superpixel, which represents the strength of the background attribute. Combining the weightsValue-based background prior computation of saliency C of superpixelst(ri)：
Figure BDA0002659417990000074
In the formula Ct(ri) Representing the saliency of a super-pixel, Dc(ri,rj) Is a background super pixel riAnd super pixel rjThe color euclidean distance in LAB space of (a); n is a radical ofBIs the number of background superpixels; dspa(ri,rj) Is a background super pixel riAnd super pixel rjThe spatial distance of (a);
2.4) setting the number of the super pixels as K and setting the K as three different scales of 150,200 and 600 respectively, so that more local details can be reserved in significance detection while the overall structure information is reserved; performing multi-scale fusion on the significance of the three superpixels under different scales, determining a superpixel significance map through normalization, and finally denoising by utilizing bilateral filtering to obtain a final significance map;
2.5) after obtaining the saliency map of the insulator image, performing binary segmentation on the image by using an adaptive threshold method, removing noise points in the image by combining morphological operation, and calculating a connected domain in the map as a candidate region and marking the candidate region as shown in fig. 3 to prepare for next insulator fault detection.
Thirdly, angle correction is carried out on the insulator string candidate regions in the second step by using Hough transform to obtain corrected images, vertical projection is carried out on each candidate region to obtain a projection curve graph, and the obtained curve graph is analyzed to obtain a target region of the insulator string to be detected, wherein the method specifically comprises the following steps:
3.1) fitting a main shaft straight line of the candidate region by random consistent sampling, rotating the main shaft of the candidate region to the horizontal direction, and starting traversing the insulator string candidate region set I, knowing that the insulator string candidate region image obtained in the step two is a binary image, knowing that pixel values corresponding to pixel points are only {0, 255} two values, and carrying out accumulated projection on the pixel points with the pixel point value of 255 in the mask of the insulator candidate region image according to the vertical direction to obtain a projection curve, wherein the pixel accumulation formula is as follows:
Figure BDA0002659417990000081
wherein, S (x) represents a cumulative function of non-0 pixel values of the candidate area image mask of the insulator string in each column direction, (I, x) is the pixel point coordinate on the image, I (I, x) represents the pixel value of the pixel point (I, x) of the kth candidate area image, and r is the maximum line number corresponding to the image mask two-dimensional matrix along the horizontal direction;
3.2) in order to determine that the candidate region is an insulator string, a sign determination function sgn (x) is set, and a difference quantity function Δ S (x) ═ S (x +1) -S (x) is calculated and used for searching a projection curve peak. The symbol decision function is formulated as follows:
Figure BDA0002659417990000082
when sgn (x +1) ≧ 0, sgn (x) is set to be 1, otherwise sgn (x) is set to be-1; at this time, the original value of sgn (x) is corrected to 0, so as to extract the peak value of the projection curve in the later period;
performing forward traversal on sgn (x), which means that when sgn (x +1) -sgn (x) -2, (x, s (x)) is a peak coordinate corresponding to the projection curve; storing the horizontal coordinates of the pixel points of all the wave crests to a set xpoint＝{x1,x2...xnIn the formula, n is the number of peaks; computing a set xpointAverage projected cumulative value S of all peak points in the waveX_avgsAnd finding the maximum projected cumulative value SX_max(ii) a Peak point average projected cumulative value SX_avgsAnd a maximum projected cumulative value SX_maxRespectively as follows:
Figure BDA0002659417990000083
SX_max＝max(S(xi))
setting the peak threshold th to 0.75SX_avgs+0.25*SX_maxAll the peak points of S (x) < th are dropped, and the set x is updatedpointAnd the peak mean SX_avgs(ii) a Calculating the variance D of the peak value2The formula is as follows:
Figure BDA0002659417990000091
in the formula, D2Representing the variance of the peak points, wherein n represents the number of the peak points;
setting variance threshold DthAs 5, the candidate region decision formula is:
Figure BDA0002659417990000092
if the candidate area is an insulator string area, continuing to execute the next step, and if the candidate area is a non-insulator string area, returning to the step II to add 1 to the k value for continuing to execute the step II;
fourthly, calculating the pixel proportion of pixel values in the insulator mask between the wave peak sections, and carrying out self-explosion defect fault detection on the insulator string region obtained in the third step, wherein the self-explosion defect fault detection specifically comprises the following steps: considering from the insulator form wave structure, when the candidate area is an insulator string, after the image is vertically projected, the sudden change between two wave peak sections is found out according to a certain criterion as the position of the insulator with the self-explosion defect; as shown in fig. 5, from a sequence of peak points (x)1,x2,...xn) Let g (x) be the pixel value of 255 in the insulator mask between the peak sectionsp) The pixel proportion is used as a characteristic for searching the self-explosion defect interval, and the pixel proportion formula is as follows:
Figure BDA0002659417990000093
in the formula, g (x)p) Representing a pixel value of 255 in an insulator mask between peak segmentsPixel ratio, xpIs the p-th peak point in the sequence of peak points, row (I)k) The width of the candidate region image of the ith insulator string in the set I is taken as the width of the candidate region image of the ith insulator string in the set I;
further, based on the fact that the self-explosion defect of the insulator has a small value of g (x), constructing an algorithm for detecting the self-explosion defect position of the insulator as follows:
4.1) calculate area ═ max (g (x)p))+min(g(xp) 2, where area is the median of g (x);
4.2) if
Figure BDA0002659417990000094
Then the peak band [ x ] is indicatedp,xp+1]The self-explosion defect exists;
image mask I for insulator string in candidate regionkAnd finally, inversely mapping the positions of the insulators detected in the coordinate system to an input image according to the change relation between the image coordinates, and finishing the final positioning of the defects of the insulators of the image when the insulator string candidate region set I is traversed.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (2)

1. A projection curve analysis-based insulator spontaneous explosion defect detection method is characterized by comprising the following steps:
shooting an insulator string to be detected on an overhead tower power transmission line by an unmanned aerial vehicle to obtain an original image of the insulator string to be detected, wherein the original image of the insulator string to be detected comprises the insulator string and background information thereof, and the insulator string is an insulator assembly formed by connecting insulators with the same shape and size in series through a core rod;
graying the original image of the insulator string to be detected to obtain a grayscale image, and performing local texture feature superpixel segmentation on the grayscale imagePerforming superpixel segmentation on the gray level image, then determining an insulator string candidate region by combining an adaptive threshold method and image morphological operation, and storing the insulator string candidate region in a set I ═ I1,I2,...,InN is the number of candidate regions;
thirdly, angle correction is carried out on the insulator string candidate regions in the second step by utilizing Hough transform to obtain corrected images, vertical projection is carried out on each candidate region to obtain a projection curve graph, and the obtained curve graph is analyzed to obtain a target region of the insulator string to be detected, wherein the method specifically comprises the following steps:
3.1) fitting a main shaft straight line of the candidate region by random consistent sampling, rotating the main shaft of the candidate region to the horizontal direction, and starting traversing the insulator string candidate region set I, knowing that the insulator string candidate region image obtained in the step two is a binary image, knowing that pixel values corresponding to pixel points are only {0, 255} two values, and carrying out accumulated projection on the pixel points with the pixel point value of 255 in the mask of the insulator candidate region image according to the vertical direction to obtain a projection curve, wherein the pixel accumulation formula is as follows:
Figure FDA0002659417980000011
wherein, S (x) represents a cumulative function of non-0 pixel values of the candidate area image mask of the insulator string in each column direction, (I, x) is the pixel point coordinate on the image, I (I, x) represents the pixel value of the pixel point (I, x) of the kth candidate area image, and r is the maximum line number corresponding to the image mask two-dimensional matrix along the horizontal direction;
3.2) in order to determine that the candidate region is an insulator string, a sign determination function sgn (x) is set, and a difference quantity function Δ S (x) ═ S (x +1) -S (x) is calculated and used for searching a projection curve peak. The symbol decision function is formulated as follows:
Figure FDA0002659417980000012
when sgn (x +1) ≧ 0, sgn (x) is set to be 1, otherwise sgn (x) is set to be-1; at this time, the original value of sgn (x) is corrected to 0, so as to extract the peak value of the projection curve in the later period;
performing forward traversal on sgn (x), which means that when sgn (x +1) -sgn (x) -2, (x, s (x)) is a peak coordinate corresponding to the projection curve; storing the horizontal coordinates of the pixel points of all the wave crests to a set xpoint＝{x1,x2...xnIn the formula, n is the number of peaks; computing a set xpointAverage projected cumulative value S of all peak points in the waveX_avgsAnd finding the maximum projected cumulative value SX_max(ii) a Peak point average projected cumulative value SX_avgsAnd a maximum projected cumulative value SX_maxRespectively as follows:
Figure FDA0002659417980000021
SX_max＝max(S(xi))
setting the peak threshold th to 0.75SX_avgs+0.25*SX_maxAll the peak points of S (x) < th are dropped, and the set x is updatedpointAnd the peak mean SX_avgs(ii) a Calculating the variance D of the peak value2The formula is as follows:
Figure FDA0002659417980000022
in the formula, D2Representing the variance of the peak points, wherein n represents the number of the peak points;
setting variance threshold DthAs 5, the candidate region decision formula is:
Figure FDA0002659417980000023
if the candidate area is an insulator string area, continuing to execute the next step, and if the candidate area is a non-insulator string area, returning to the step II to add 1 to the k value for continuing to execute the step II;
fourthly, calculating the pixel proportion of pixel values in the insulator mask between the wave peak sections, and carrying out self-explosion defect fault detection on the insulator string region obtained in the third step, wherein the self-explosion defect fault detection specifically comprises the following steps: considering from the insulator form wave structure, when the candidate area is an insulator string, after the image is vertically projected, the sudden change between two wave peak sections is found out according to a certain criterion as the position of the insulator with the self-explosion defect; from a sequence of peak points (x)1,x2,...xn) Let g (x) be the pixel value of 255 in the insulator mask between the peak sectionsp) The pixel proportion is used as a characteristic for searching the self-explosion defect interval, and the pixel proportion formula is as follows:
Figure FDA0002659417980000024
in the formula, g (x)p) Represents the pixel ratio, x, of 255 in the insulator mask between the peak sectionspIs the p-th peak point in the sequence of peak points, row (I)k) The width of the candidate region image of the ith insulator string in the set I is taken as the width of the candidate region image of the ith insulator string in the set I;
further, based on the fact that the self-explosion defect of the insulator has a small value of g (x), constructing an algorithm for detecting the self-explosion defect position of the insulator as follows:
4.1) calculate area ═ max (g (x)p))+min(g(xp) 2, where area is the median of g (x);
4.2) if
Figure FDA0002659417980000031
Then the peak band [ x ] is indicatedp,xp+1]The self-explosion defect exists;
image mask I for insulator string in candidate regionkAnd finally, inversely mapping the positions of the insulators detected in the coordinate system to an input image according to the change relation between the image coordinates, and finishing the final positioning of the defects of the insulators of the image when the insulator string candidate region set I is traversed.
2. The method for detecting the self-explosion defect of the insulator based on the projection curve analysis as claimed in claim 1, wherein the super-pixel segmentation method of the local texture features comprises the following steps:
1) after converting an image from an RGB image into an LAB color space, initializing a clustering center, and calculating the similarity measurement D of two pixel points by combining texture features:
Figure FDA0002659417980000032
in the formula dcIs the color distance, d, of two pixels in Lab spacesIs a spatial distance, dwThe difference distance of the local texture features is obtained, s, m and c are constants, and the weights of the space, the color and the texture features in the similarity measurement are comprehensively represented;
wherein d isc,ds,dwComprises the following steps:
Figure FDA0002659417980000033
Figure FDA0002659417980000034
Figure FDA0002659417980000035
in the formula, (l, a, b) represents pixel color characteristics, (x, y) is pixel space coordinates, and w is pixel point texture characteristics;
2) and setting an undirected weighted graph G (V, E) according to the obtained superpixel image, wherein V is a superpixel node set, E is an edge set formed by connecting edges of adjacent superpixels, and the shortest path edge weight value accumulation and calculation formula of any two superpixels comprises the following steps:
Figure FDA0002659417980000036
in the formula dg(ri,rj) Cumulative sum of shortest path edge weights, d, representing any two superpixelsc-lab(ri,rj) Is the mean color characteristic Euclidean distance, r, between two superpixelsi、rjRepresenting a superpixel node; computing superpixel boundary connectivity Bcon(r) the calculation formula is as follows:
Figure FDA0002659417980000041
in the formula Bcon(r) the connectivity of the super-pixel boundary is strong and weak, E (r) is the area of the geodesic distance weight expansion area, b is the number of pixels connected with the boundary in the statistical r, when the super-pixel r is connected with the boundary, b is more than 0, otherwise, b is 0;
Figure FDA0002659417980000042
and E (r) in the formula is as follows:
where norm is a normalization operation, exp denotes an exponential function with a natural constant e as the base, σ is an equilibrium parameter and is set to 10;
3) different weights are distributed according to the difference of the background super pixel characteristics, and the calculation formula is as follows:
Figure FDA0002659417980000043
in the formula Bp(r) is the weight of the background superpixel, which represents the strength of the background attribute. Calculating the saliency C of the superpixel based on the background prior in combination with the weight valuet(ri)：
Figure FDA0002659417980000044
In the formula Ct(ri) Representing the saliency of a super-pixel, Dc(ri,rj) Is a background super pixel riAnd super pixel rjThe color euclidean distance in LAB space of (a); n is a radical ofBIs the number of background superpixels; dspa(ri,rj) Is a background super pixel riAnd super pixel rjThe spatial distance of (a);
4) setting the number of super pixels as K and setting K as three different scales of 150,200 and 600 respectively, so that more local details can be reserved in significance detection while integral structure information is reserved; performing multi-scale fusion on the significance of the three superpixels under different scales, determining a superpixel significance map through normalization, and finally denoising by utilizing bilateral filtering to obtain a final significance map;
5) and after obtaining the saliency map of the insulator image, performing binary segmentation on the image by using a self-adaptive threshold method, removing noise points in the image by combining morphological operation, calculating a connected domain in the map as a candidate region, marking the candidate region, and preparing for next insulator fault detection.
CN202010899222.7A 2020-08-31 2020-08-31 Insulator self-explosion defect detection method based on projection curve analysis Active CN112150412B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010899222.7A CN112150412B (en) 2020-08-31 2020-08-31 Insulator self-explosion defect detection method based on projection curve analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010899222.7A CN112150412B (en) 2020-08-31 2020-08-31 Insulator self-explosion defect detection method based on projection curve analysis

Publications (2)

Publication Number Publication Date
CN112150412A true CN112150412A (en) 2020-12-29
CN112150412B CN112150412B (en) 2022-11-22

Family

ID=73890317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010899222.7A Active CN112150412B (en) 2020-08-31 2020-08-31 Insulator self-explosion defect detection method based on projection curve analysis

Country Status (1)

Country Link
CN (1) CN112150412B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112862770A (en) * 2021-01-29 2021-05-28 珠海迪沃航空工程有限公司 Defect analysis and diagnosis system, method and device based on artificial intelligence
CN113887430A (en) * 2021-09-30 2022-01-04 国网山东省电力公司信息通信公司 Method and system for locating polling video characters
CN114937039A (en) * 2022-07-21 2022-08-23 阿法龙(山东)科技有限公司 Intelligent detection method for steel pipe defects

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103886610A (en) * 2014-04-05 2014-06-25 东北电力大学 Image type defect detecting method for insulator
CN104281857A (en) * 2013-07-08 2015-01-14 中国科学院沈阳自动化研究所 Insulator detecting method based on orthogonal direction projection
CN106683075A (en) * 2016-11-22 2017-05-17 广东工业大学 Power transmission line tower cross arm bolt defect detection method
CN106778734A (en) * 2016-11-10 2017-05-31 华北电力大学（保定） A kind of insulator based on rarefaction representation falls to go here and there defect inspection method
JP2017194425A (en) * 2016-04-22 2017-10-26 株式会社 東京ウエルズ Defect inspection method and defect inspection system
CN108010019A (en) * 2017-11-29 2018-05-08 国网电力科学研究院武汉南瑞有限责任公司 One kind is based on the defects of adaptively cutting single insulator detection method
CN110675387A (en) * 2019-09-26 2020-01-10 北京国网富达科技发展有限责任公司 Method and device for detecting structural defects of transmission line iron tower

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104281857A (en) * 2013-07-08 2015-01-14 中国科学院沈阳自动化研究所 Insulator detecting method based on orthogonal direction projection
CN103886610A (en) * 2014-04-05 2014-06-25 东北电力大学 Image type defect detecting method for insulator
JP2017194425A (en) * 2016-04-22 2017-10-26 株式会社 東京ウエルズ Defect inspection method and defect inspection system
CN106778734A (en) * 2016-11-10 2017-05-31 华北电力大学（保定） A kind of insulator based on rarefaction representation falls to go here and there defect inspection method
CN106683075A (en) * 2016-11-22 2017-05-17 广东工业大学 Power transmission line tower cross arm bolt defect detection method
CN108010019A (en) * 2017-11-29 2018-05-08 国网电力科学研究院武汉南瑞有限责任公司 One kind is based on the defects of adaptively cutting single insulator detection method
CN110675387A (en) * 2019-09-26 2020-01-10 北京国网富达科技发展有限责任公司 Method and device for detecting structural defects of transmission line iron tower

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王伟旭等: "基于曲线和点状奇异性的接触网用棒形瓷绝缘子外部缺陷的状态检测方法", 《电瓷避雷器》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112862770A (en) * 2021-01-29 2021-05-28 珠海迪沃航空工程有限公司 Defect analysis and diagnosis system, method and device based on artificial intelligence
CN113887430A (en) * 2021-09-30 2022-01-04 国网山东省电力公司信息通信公司 Method and system for locating polling video characters
CN113887430B (en) * 2021-09-30 2024-04-30 国网山东省电力公司信息通信公司 Method and system for locating polling video text
CN114937039A (en) * 2022-07-21 2022-08-23 阿法龙(山东)科技有限公司 Intelligent detection method for steel pipe defects
CN114937039B (en) * 2022-07-21 2022-10-25 阿法龙(山东)科技有限公司 Intelligent detection method for steel pipe defects

Also Published As

Publication number Publication date
CN112150412B (en) 2022-11-22

Similar Documents

Publication Publication Date Title
CN112150412B (en) Insulator self-explosion defect detection method based on projection curve analysis
CN111428748B (en) HOG feature and SVM-based infrared image insulator identification detection method
CN109118479B (en) Capsule network-based insulator defect identification and positioning device and method
Sohn et al. Automatic powerline scene classification and reconstruction using airborne lidar data
CN113313005B (en) Power transmission conductor on-line monitoring method and system based on target identification and reconstruction
Wang et al. Recognition and drop-off detection of insulator based on aerial image
CN111814686A (en) Vision-based power transmission line identification and foreign matter invasion online detection method
CN112883878B (en) Automatic point cloud classification method under transformer substation scene based on three-dimensional grid
CN109523528B (en) Power transmission line extraction method based on unmanned aerial vehicle binocular vision SGC algorithm
CN112435208B (en) Insulator region detection method for significant edge guidance
CN108537170A (en) A kind of power equipment firmware unmanned plane inspection pin missing detection method
CN114241364A (en) Method for quickly calibrating foreign object target of overhead transmission line
CN113409252B (en) Obstacle detection method for overhead transmission line inspection robot
CN113554595A (en) Unmanned aerial vehicle laser radar point cloud tower head deformation detection device and method
CN112115770A (en) Method and system for identifying autonomous inspection defects of unmanned aerial vehicle of overhead line
CN109523543A (en) A kind of wire strand breakage detection method based on Edge Distance
CN111220619B (en) Insulator self-explosion detection method
Hao et al. Detection of bird nests on power line patrol using single shot detector
Hong-Bin et al. Target tracking method of transmission line insulator based on multi feature fusion and adaptive scale filter
Zhang et al. Defect detection of anti-vibration hammer based on improved faster R-CNN
CN111931577A (en) Intelligent inspection method for specific foreign matters of power grid line
CN114061476B (en) Method for detecting deflection of insulator of power transmission line
CN110223346B (en) Shape prior-based multi-insulator positioning method
Hao et al. Based on Surf feature extraction and insulator damage identification for capsule networks
Lv et al. Research on Insulator Defect Detection and Recognition in Overhead Transmission Line Based on Convolutional Neural Network

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
TA01 Transfer of patent application right

Effective date of registration: 20221017

Address after: No. 2 Wenfeng East Road, Changshan County, Quzhou City, Zhejiang Province 324200

Applicant after: Changshan power supply company of State Grid Zhejiang Electric Power Co.,Ltd.

Applicant after: NORTHEAST DIANLI University

Address before: No. 900, Century Avenue, Quzhou City, Zhejiang Province

Applicant before: Quzhou Guangming Electric Power Investment Group Co.,Ltd. Futeng Technology Branch

Applicant before: NORTHEAST DIANLI University

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant