CN109785285A - A kind of insulator damage testing method based on oval feature fitting - Google Patents
A kind of insulator damage testing method based on oval feature fitting Download PDFInfo
- Publication number
- CN109785285A CN109785285A CN201811511230.9A CN201811511230A CN109785285A CN 109785285 A CN109785285 A CN 109785285A CN 201811511230 A CN201811511230 A CN 201811511230A CN 109785285 A CN109785285 A CN 109785285A
- Authority
- CN
- China
- Prior art keywords
- insulator
- image
- fitting
- oval
- formula
- 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
Links
Abstract
The invention discloses a kind of insulator damage testing methods based on oval feature fitting, insulator original image is acquired first, then image gray processing, image filtering processing are carried out, remove the interference noise of image, then two dimension OTSU Threshold segmentation is carried out to image, global threshold is obtained, obtains insulation subregion, and combining form filtering and connected component labeling carry out " hole " filling and pseudo- object removal to the image after two-dimentional OTSU Threshold segmentation；The edge contour that edge detection obtains insulator is carried out to treated image, centre coordinate point and long Shaft angle are solved by optimal ellipse fitting, the fitted ellipse in sub-pieces per a piece of insulator is obtained, the optimal ellipse fitting of entire insulator chain is acquired by the top and lower section sub-pieces of analyzing insulator chain；Finally damage testing is carried out using slope model.It is big that the present invention solves the problems, such as that shade in existing insulator segmentation low efficiency and insulation subgraph, illumination influence image segmentation.
Description
Technical field
The invention belongs to technical field of image processing, and in particular to a kind of insulator breakage inspection based on oval feature fitting
Survey method.
Background technique
Important component of the insulator as transmission line of electricity has the mechanical support of conducting wire, electric insulation important
Effect, performance quality directly affect the safe operation of power grid.Since insulator is chronically exposed to field and long-term work strong
Electric field, in the adverse circumstances such as suddenly cold and hot, insulator surface can generate breakage with being difficult to avoid that.Porcelain body generates breakage and can reduce absolutely
The dielectric strength of edge, or even cause insulator to burn, puncture and be broken, lead to serious electric power accident.For fault diagnosis
Key be how to be accurately partitioned into insulator, common image partition method has edge detection, Threshold segmentation and extracted region
Deng, but since collected insulation subgraph generally includes other nonisulated sub- backgrounds, the present invention is based on existing methods to mention
A kind of oval feature approximating method realizes that the segmentation of insulator is extracted out, and the damaged inspection of insulator is realized in conjunction with slope model
It surveys.
Summary of the invention
The object of the present invention is to provide a kind of insulator damage testing methods based on oval feature fitting, solve existing
Insulator, which divides shade, illumination in low efficiency and insulation subgraph, influences big problem to image segmentation.
The technical scheme adopted by the invention is that a kind of insulator damage testing method based on oval feature fitting, tool
Body follows the steps below to implement:
Then step 1, acquisition insulator original image carry out image gray processing, image filtering processing, remove the dry of image
Disturb noise；
Step 2 carries out two dimension OTSU Threshold segmentation to the image that step 1 obtains, and obtains global threshold, obtains insulation sub-district
Domain, and combining form filtering and connected component labeling carry out " hole " filling to the image after two-dimentional OTSU Threshold segmentation
With pseudo- object removal；
Step 3 carries out the edge contour that edge detection obtains insulator to step 2 treated image, by optimal ellipse
Circle fitting solves centre coordinate point and long Shaft angle；
Step 4: the fitted ellipse in sub-pieces per a piece of insulator is obtained by step 3, by analyzing insulator chain
Top and lower section sub-pieces acquire the optimal ellipse fitting of entire insulator chain；
Step 5: the insulation subregion obtained for step 4 carries out damage testing using slope model.
The features of the present invention also characterized in that
Step 1 is specifically implemented according to the following steps:
Step 1.1, image gray processing processing, gray processing formula are as follows:
Y=0.299R+0.587G+0.114B (1)
Wherein, Y is calculated according to the relationship in R, G, B color component and colour coding method YUV between luminance signal Y
Brightness, R, G, B respectively indicate red, green, blue component；
Step 1.2, mean filter processing:
If the grey scale pixel value before image denoising processing is f (x, y), g (x, y) is the gray value after noise-removed filtering, then:
Wherein, x=0,1,2 ... ... N-1, y=0,1, what 2 ... ... N-1, m indicated selection is m row, and n indicates selection
It is the n-th column, M is indicated in Filtering Template comprising the total number of pixels including current pixel.
Step 2 is specifically implemented according to the following steps:
Step 2.1 sets image size to be split as M*N, and gray value is taken as { 0, M-1 }, if P (a, b) is figure to be split
Pixel as in, neighborhood averaging gray value S (a, b) at P (a, b) ∈ M, pixel P (a, b) are as follows:
In formula (3), k indicates P (a, b) neighborhood search window size,
What m indicated selection is m row, and what n indicated selection is the n-th column；
Step 2.2 uses cabThe gray value of indicates coordinate (a, b), the probability occurred in entire intensity value ranges with P (a,
B) it indicates are as follows:
Step 2.3, set in two-dimensional gray histogram have A and two kinds of B set, wherein A represents image object domain to be split, B
Image impurity to be split and its background field are represented, A and B include that the respective probability about dispersion with same grayscale is public
Formula, A and B have shown in relevant dispersion new probability formula such as formula (5) and (6):
Destination probability:
Background probability:
Wherein, l1Indicate background area.
Step 2.4 is assumed: S axis represents the gray value of each pixel in corresponding two-dimensional gray histogram；T axis generation
The average gray of each neighborhood of pixel points in table image, then (S, T) plane is divided into 4 parts by two-dimentional segmentation threshold (s, t),
Assuming that region I represents target, region II represents background, and region III represents boundary, and region IV represents noise；
Step 2.5, the corresponding average value bivector of two class set are as follows:
The terminating point of L-1 expression abscissa；PijRefer to the frequency that binary group (i, j) occurs, μ0Indicate the mean value of background
Vector, μ1Indicate the mean value vector of target, w0(s, t) indicates destination probability, w1(s, t) indicates background probability；
The average value of the bivector after merging is calculated by formula (7) and (8) are as follows:
Wherein, μtThe total mean value vector of two-dimensional histogram；
The tr (σ B) derived by scatter matrix is as the background parts and target part in image to be split, two classes
The distance between metric function:
Tr (σ B) indicates that the dispersion between class is estimated；
It can show that a bivector, the bivector are exactly that image carries out two dimension when tr (σ B) acquires maximum value
The Two Dimensional Thresholding (s, t) of segmentation:
tr(μB(S, T))=max { tr (μB(S, T)) } (11).
Step 3 is specifically implemented according to the following steps:
Step 3.1 extracts insulator edge by prewitt edge detection algorithm；
Step 3.2, search extract continuous boundary point and are used as edge point set to be fitted, and judge whether it meets boundary Control item
Part；According to insulator chain feature, oval perimeters are set as boundary Control condition, wherein oval maximum perimeter Lmax, oval minimum
Perimeter Lmin, qualified continuous boundary point set is subjected to ellipse fitting；
Step 3.3 is fitted obtained all ellipses to step 3.2, and setting degree of fitting is used as is fitted optimal ellipse again
Control condition, carry out deleting choosing, wherein by the square distance and minimal definition of oval boundary point to match point point be optimal quasi-
It closes；
Step 3.4 establishes two-dimensional coordinate system, optimal elliptical geometrical characteristic parameter is solved, to obtain elliptical center coordinate o
(x0,y0) and long axis rotational angle theta, the expression formula of elliptic curve it is as follows:
Ax2+Bxy+Cy2+ Dx+Ey+F=0 (12)
Equation coefficient (A, B, C, D, E, F) can be acquired by fitted ellipse, to reversely acquire centre coordinate and long axis turn
Angle is specifically calculated according to following formula:
Obtained fitted ellipse region is added in original image, so that insulator position be accurately positioned.
Step 4 is specifically implemented according to the following steps:
Step 4.1 calculates bunch of insulator the top to the distance of bottom, is expanded 1.5 times and gone here and there absolutely as whole
The long axis of edge fitting；
If step 4.2, insulator the piece number are odd number, the most intermediate a piece of insulator diameter of bunch of insulator is calculated；If
Insulator the piece number is even number, acquires intermediate two panels insulator diameter and obtains diameter of the average value as intermediate a piece of insulator, by it
Amplify 1.5 times of short axles as bunch of insulator fitting；
The centre coordinate that is fitted as bunch of insulator of centre coordinate of step 4.3, intermediate a piece of insulator；
The corner that step 4.4, bunch of insulator are fitted is centre coordinate and the bottom insulation of the top sub-pieces
Angle formed by the centre coordinate of sub-pieces.
Step 5 is specifically implemented according to the following steps:
The function model of insulator appearance are as follows:
ε is a normal number in formula；
Insulate each scale of subgraph edge can the characterization of the slope model as shown in formula (16), therefore use ramp function
Intact insulator edge is characterized, selected parameter is that the slope model of ε=1.4 characterizes the external appearance characteristic of most of insulators, will
If the insulator oriented respectively scans by column different ranks and is recorded as a result, being unsatisfactory for slope mould after scanning
It is damaged then to illustrate that insulator occurs for type.
The beneficial effects of the invention are as follows the insulator split using two-dimentional OTSU Threshold segmentation and Morphological scale-space is not
It only reflects the intensity profile of image and can reflect the spatial information between image pixel, imitated with common threshold Image Segmentation
Fruit, which is compared, to work well.The fitted ellipse in insulator chain per a piece of insulator is obtained by optimal ellipse fitting and is analyzed exhausted
The top of edge substring and lower section sub-pieces acquire the optimal ellipse fitting of entire insulator chain, and the major part of insulator all exists
Inside elliptic region, the processing for subsequent image insulator provides good basis.Finally carried out brokenly using slope model
Damage detection, the edge of the intact each scale of insulation subgraph can be characterized with slope model, after being scanned, if not
Meet slope model, then insulator occurs damaged.Compared with other damage testing methods, the method for the present invention is simple and easy, accurately
Degree is higher, and accurate positioning and the damage testing of insulator may be implemented, and lays the foundation for the safe and stable operation of transmission line of electricity.
Detailed description of the invention
Fig. 1 is a kind of insulator damage testing method flow diagram based on oval feature fitting of the present invention；
Fig. 2 is insulator original image in a kind of insulator damage testing method based on oval feature fitting of the present invention；
Fig. 3 is that insulator two dimensional gray is straight in a kind of insulator damage testing method based on oval feature fitting of the present invention
Fang Tu.
Specific embodiment
The following describes the present invention in detail with reference to the accompanying drawings and specific embodiments.
Need to carry out insulator fault diagnosis after insulator Accurate Segmentation, it is frequency occur that insulator surface, which generates breakage,
The highest failure of rate, insulator, which generates breakage, can reduce the dielectric strength of insulator porcelain body, or even will cause insulator and burn, hit
It wears and is broken, cause electric power accident.Therefore, the damage testing of insulator is a very crucial step, the breakage for insulator
Detection, common damage testing method have direct observational method, electric field measurement method, image detection etc., wherein image detection
Have accuracy high relative to other detection methods, securely and reliably, realizes the advantages that simple.The present invention is carried out using slope model
Damaged detection, the edge of the intact each scale of insulation subgraph can be characterized with slope model, exhausted by what is oriented
Edge different ranks are scanned by column respectively and recorded as a result, the various pretreatments that image is carried out by early period
Interference information in rejection image, so, if being unsatisfactory for slope model, it is damaged to prove that insulator occurs after being scanned.
A kind of insulator damage testing method based on oval feature fitting of the present invention, flow chart is as shown in Figure 1, specifically press
Implement according to following steps:
Step 1 carries high-definition camera acquisition insulation subgraph using crusing robot, and the width if Fig. 2 is acquisition is exhausted
Then edge original image carries out image gray processing, image filtering processing, the interference noise of image is removed, specifically according to following
Step is implemented:
Step 1.1, image gray processing processing, gray processing formula are as follows:
Y=0.299R+0.587G+0.114B (1)
Wherein, Y is calculated according to the relationship in R, G, B color component and colour coding method YUV between luminance signal Y
Brightness, R, G, B respectively indicate red, green, blue component；
Step 1.2, mean filter processing:
If the grey scale pixel value before image denoising processing is f (x, y), g (x, y) is the gray value after noise-removed filtering, then:
Wherein, x=0,1,2 ... ... N-1, y=0,1, what 2 ... ... N-1, m indicated selection is m row, and n indicates selection
It is the n-th column, M is indicated in Filtering Template comprising the total number of pixels including current pixel；
Step 2 carries out two dimension OTSU Threshold segmentation to the image that step 1 obtains, and obtains global threshold, obtains insulation sub-district
Domain, and combining form filtering and connected component labeling carry out " hole " filling to the image after two-dimentional OTSU Threshold segmentation
With pseudo- object removal, it is specifically implemented according to the following steps:
Step 2.1 sets image size to be split as M*N, and gray value is taken as { 0, M-1 }, if P (a, b) is figure to be split
Pixel as in, neighborhood averaging gray value S (a, b) at P (a, b) ∈ M, pixel P (a, b) are as follows:
In formula (3), k indicates P (a, b) neighborhood search window size, and what m indicated selection is m row, and what n indicated selection is
N-th column；
Step 2.2 uses cabThe probability that the gray value of indicates coordinate (a, b) occurs in entire intensity value ranges is with P (a, b)
It indicates are as follows:
Step 2.3, set in two-dimensional gray histogram have A and two kinds of B set, wherein A represents image object domain to be split, B
Image impurity to be split and its background field are represented, A and B include that the respective probability about dispersion with same grayscale is public
Formula, A and B have shown in relevant dispersion new probability formula such as formula (5) and (6):
Destination probability:
Background probability:
Wherein, l1Indicate background area；
Step 2.4, Fig. 3 are corresponding two-dimensional gray histogram schematic diagrames, it is assumed that it is straight that S axis represents corresponding two dimensional gray
The gray value of each pixel in square figure；The average gray of each neighborhood of pixel points in T axis representative image, then two dimension is divided
It cuts threshold value (s, t) and (S, T) plane is divided into 4 parts, it is assumed that region I represents target, and region II represents background, and region III is represented
Boundary, region IV represent noise；
Step 2.5, the corresponding average value bivector of two class set are as follows:
L-1 indicates the terminating point of abscissa, PijRefer to the i-th row, the destination probability of jth column, PijRefer to binary group
The frequency that (i, j) occurs, μ0Indicate the mean value vector of background, μ1Indicate the mean value vector of target, w0(s, t) indicates destination probability,
w1(s, t) indicates background probability；
The average value of the bivector after merging is calculated by formula (7) and (8) are as follows:
Wherein, μtThe total mean value vector of two-dimensional histogram；
The tr (σ B) derived by scatter matrix is as the background parts and target part in image to be split, two classes
The distance between metric function:
Wherein, tr (σ B) indicates that the dispersion between class is estimated；
It can show that a bivector, the bivector are exactly that image carries out two dimension when tr (σ B) acquires maximum value
The Two Dimensional Thresholding (s, t) of segmentation:
tr(μB(S, T))=max (tr (μB(S, T)) } (11)；
Step 3 carries out the edge contour that edge detection obtains insulator to step 2 treated image, by optimal ellipse
Circle fitting solves centre coordinate point and long Shaft angle, is specifically implemented according to the following steps:
Step 3.1 extracts insulator edge by prewitt edge detection algorithm；
Step 3.2, search extract continuous boundary point and are used as edge point set to be fitted, and judge whether it meets boundary Control item
Part；According to insulator chain feature, oval perimeters are set as boundary Control condition, wherein oval maximum perimeter Lmax, oval minimum
Perimeter Lmin, qualified continuous boundary point set is subjected to ellipse fitting；
Step 3.3 is fitted obtained all ellipses to step 3.2, and setting degree of fitting is used as is fitted optimal ellipse again
Control condition, carry out deleting choosing, wherein by the square distance and minimal definition of oval boundary point to match point point be optimal quasi-
It closes；
Step 3.4 establishes two-dimensional coordinate system, optimal elliptical geometrical characteristic parameter is solved, to obtain elliptical center coordinate o
(x0,y0) and long axis rotational angle theta, the expression formula of elliptic curve it is as follows:
Ax2+Bxy+Cy2+ Dx+Ey+F=0 (12)
Equation coefficient (A, B, C, D, E, F) can be acquired by fitted ellipse, to reversely acquire centre coordinate and long axis turn
Angle is specifically calculated according to following formula:
Obtained fitted ellipse region is added in original image, so that insulator position be accurately positioned；
Step 4: the fitted ellipse in sub-pieces per a piece of insulator is obtained by step 3, by analyzing insulator chain
Top and lower section sub-pieces acquire the optimal ellipse fitting of entire insulator chain, be specifically implemented according to the following steps:
Step 4.1 calculates bunch of insulator the top to the distance of bottom, is expanded 1.5 times and gone here and there absolutely as whole
The long axis of edge fitting；
If step 4.2, insulator the piece number are odd number, the most intermediate a piece of insulator diameter of bunch of insulator is calculated；If
Insulator the piece number is even number, acquires intermediate two panels insulator diameter and obtains diameter of the average value as intermediate a piece of insulator, by it
Amplify 1.5 times of short axles as bunch of insulator fitting；
The centre coordinate that is fitted as bunch of insulator of centre coordinate of step 4.3, intermediate a piece of insulator；
The corner that step 4.4, bunch of insulator are fitted is centre coordinate and the bottom insulation of the top sub-pieces
Angle formed by the centre coordinate of sub-pieces；
Step 5: the insulation subregion obtained for step 4 carries out damage testing using slope model, specifically according to following
Step is implemented:
The function model of insulator appearance are as follows:
ε is a normal number in formula；
Insulate each scale of subgraph edge can the characterization of the slope model as shown in formula (16), therefore use ramp function
Intact insulator edge is characterized, selected parameter is that the slope model of ε=1.4 characterizes the external appearance characteristic of most of insulators, will
If the insulator oriented respectively scans by column different ranks and is recorded as a result, being unsatisfactory for slope mould after scanning
It is damaged then to illustrate that insulator occurs for type.
The present invention is based on the basis of one-dimensional threshold segmentation method, propose the side of two-dimentional OTSU segmentation and morphology combination
Method carries out the segmentation of insulator, is suitable for various image problems, not only effectively raises the segmentation efficiency of insulator in this way, and
And reduce the shade in insulation subgraph, illumination influence caused by image segmentation.Exhausted by the primary segmentation of first time
After edge, due to insulator general shape present be ellipse, to primary segmentation go out insulation subgraph carry out edge
Detection carries out oval feature fitting for the insulator edge detected, and then completes the segmentation to bunch of insulator.
It is a kind of based on oval feature fitting insulator damage testing method compared with the method for other damage testings, simply
Easy, accuracy is higher., insulator appearance standard good for shooting effect, this model can be detected and be managed well
The result thought.Filthy existing, when rain and snow weather etc. influences, this model inspection effect is general.Improve the accuracy of this model
Method is to avoid and reduce the generation of above-mentioned non-ideality.
Claims (6)
1. a kind of insulator damage testing method based on oval feature fitting, which is characterized in that specifically real according to the following steps
It applies:
Step 1, acquisition insulator original image, then carry out image gray processing, image filtering processing, and the interference for removing image is made an uproar
Sound；
Step 2 carries out two dimension OTSU Threshold segmentation to the image that step 1 obtains, and obtains global threshold, obtains insulation subregion,
And combining form filtering and connected component labeling to after two-dimentional OTSU Threshold segmentation image carry out " hole " filling and
Pseudo- object removal；
Step 3 carries out the edge contour that edge detection obtains insulator to step 2 treated image, by optimal oval quasi-
It closes and solves centre coordinate point and long Shaft angle；
Step 4: obtaining the fitted ellipse in sub-pieces per a piece of insulator by step 3, pass through the upper of analysis insulator chain
Side and lower section sub-pieces acquire the optimal ellipse fitting of entire insulator chain；
Step 5: the insulation subregion obtained for step 4 carries out damage testing using slope model.
2. a kind of insulator damage testing method based on oval feature fitting according to claim 1, which is characterized in that
The step 1 is specifically implemented according to the following steps:
Step 1.1, image gray processing processing, gray processing formula are as follows:
Y=0.299R+0.587G+0.114B (1)
Wherein, Y is according to the bright of the relationship calculating in R, G, B color component and colour coding method YUV between luminance signal Y
Degree, R, G, B respectively indicate red, green, blue component；
Step 1.2, mean filter processing:
If the grey scale pixel value before image denoising processing is f (x, y), g (x, y) is the gray value after noise-removed filtering, then:
Wherein, x=0,1,2 ... ... N-1, y=0,1,2 ... ... N-1；What m indicated selection is m row, and what n indicated selection is
N column, M are indicated in Filtering Template comprising the total number of pixels including current pixel.
3. a kind of insulator damage testing method based on oval feature fitting according to claim 1, which is characterized in that
The step 2 is specifically implemented according to the following steps:
Step 2.1 sets image size to be split as M*N, and gray value is taken as { 0, M-1 }, if P (a, b) is in image to be split
Pixel, neighborhood averaging gray value S (a, b) at P (a, b) ∈ M, pixel P (a, b) are as follows:
In formula (3), k indicates P (a, b) neighborhood search window size, and what m indicated selection is m row, and what n indicated selection is n-th
Column；
Step 2.2 uses cabThe probability that the gray value of indicates coordinate (a, b) occurs in entire intensity value ranges is indicated with P (a, b)
Are as follows:
Step 2.3 sets in two-dimensional gray histogram and has A and two kinds of B set, and wherein A represents image object domain to be split, and B is represented
Image impurity to be split and its background field, A and B include the respective new probability formula about dispersion with same grayscale, A
Have shown in relevant dispersion new probability formula such as formula (5) and (6) with B:
Destination probability:
Background probability:
Wherein, l1Indicate background area；
Step 2.4 is assumed: S axis represents the gray value of each pixel in corresponding two-dimensional gray histogram；T axis represents figure
The average gray of each neighborhood of pixel points as in, then (S, T) plane is divided into 4 parts by two-dimentional segmentation threshold (s, t), it is assumed that
Region I represents target, and region II represents background, and region III represents boundary, and region IV represents noise；
Step 2.5, the corresponding average value bivector of two class set are as follows:
L-1 indicates the terminating point of abscissa, PijRefer to the i-th row, the destination probability of jth column, PijRefer to that binary group (i, j) goes out
Existing frequency, μ0Indicate the mean value vector of background, μ1Indicate the mean value vector of target, w0(s, t) indicates destination probability, w1(s,t)
Indicate background probability；
The average value of the bivector after merging is calculated by formula (7) and (8) are as follows:
Wherein, μtThe total mean value vector of two-dimensional histogram；
The tr (σ B) derived by scatter matrix is as the background parts and target part in image to be split, between two classes
Distance metric function:
Wherein, tr (σ B) indicates that the dispersion between class is estimated；
It can show that a bivector, the bivector are exactly that image carries out two-dimentional segmentation when tr (σ B) acquires maximum value
Two Dimensional Thresholding (s, t):
tr(μB(S, T))=max (tr (μB(S, T)) } (11).
4. a kind of insulator damage testing method based on oval feature fitting according to claim 1, which is characterized in that
The step 3 is specifically implemented according to the following steps:
Step 3.1 extracts insulator edge by prewitt edge detection algorithm；
Step 3.2, search extract continuous boundary point and are used as edge point set to be fitted, and judge whether it meets boundary Control condition；
According to insulator chain feature, oval perimeters are set as boundary Control condition, wherein oval maximum perimeter Lmax, oval minimum perimeter polygon
Lmin, qualified continuous boundary point set is subjected to ellipse fitting；
Step 3.3 is fitted obtained all ellipses to step 3.2, and setting degree of fitting is used as is fitted optimal elliptical control again
Condition processed carries out deleting choosing, wherein by the square distance and minimal definition of oval boundary point to match point point be optimal fitting；
Step 3.4 establishes two-dimensional coordinate system, optimal elliptical geometrical characteristic parameter is solved, to obtain elliptical center coordinate o (x0,
y0) and long axis rotational angle theta, the expression formula of elliptic curve it is as follows:
Ax2+Bxy+Cy2+ Dx+Ey+F=0 (12)
Equation coefficient (A, B, C, D, E, F) can be acquired by fitted ellipse, to reversely acquire centre coordinate and long Shaft angle, is had
Body is calculated according to following formula:
Obtained fitted ellipse region is added in original image, so that insulator position be accurately positioned.
5. a kind of insulator damage testing method based on oval feature fitting according to claim 1, which is characterized in that
The step 4 is specifically implemented according to the following steps:
Step 4.1 calculates bunch of insulator the top to the distance of bottom, is expanded 1.5 times as bunch of insulator
The long axis of fitting；
If step 4.2, insulator the piece number are odd number, the most intermediate a piece of insulator diameter of bunch of insulator is calculated；If insulation
Sub-pieces number is even number, acquires intermediate two panels insulator diameter and obtains diameter of the average value as intermediate a piece of insulator, is amplified
1.5 times of short axles as bunch of insulator fitting；
The centre coordinate that is fitted as bunch of insulator of centre coordinate of step 4.3, intermediate a piece of insulator；
The corner that step 4.4, bunch of insulator are fitted is the centre coordinate and bottom sub-pieces of the top sub-pieces
Centre coordinate formed by angle.
6. a kind of insulator damage testing method based on oval feature fitting according to claim 5, which is characterized in that
The step 5 is specifically implemented according to the following steps:
The function model of insulator appearance are as follows:
ε is a normal number in formula；
Insulate each scale of subgraph edge can the characterization of the slope model as shown in formula (16), therefore characterized with ramp function
Intact insulator edge, selected parameter are that the slope model of ε=1.4 characterizes the external appearance characteristic of most of insulators, will be positioned
If insulator out respectively scans by column different ranks and is recorded as a result, be unsatisfactory for slope model after scanning,
It is damaged to illustrate that insulator occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811511230.9A CN109785285B (en) | 2018-12-11 | 2018-12-11 | Insulator damage detection method based on ellipse characteristic fitting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811511230.9A CN109785285B (en) | 2018-12-11 | 2018-12-11 | Insulator damage detection method based on ellipse characteristic fitting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109785285A true CN109785285A (en) | 2019-05-21 |
| CN109785285B CN109785285B (en) | 2023-08-08 |
Family
ID=66496726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811511230.9A Active CN109785285B (en) | 2018-12-11 | 2018-12-11 | Insulator damage detection method based on ellipse characteristic fitting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785285B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517265A (en) * | 2019-09-04 | 2019-11-29 | 北京理工大学 | A kind of detection method of surface defects of products, device and storage medium |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN110909751A (en) * | 2019-11-26 | 2020-03-24 | 长沙理工大学 | Visual identification method, system and medium for transformer substation insulator cleaning robot |
| CN110956641A (en) * | 2019-11-20 | 2020-04-03 | 南京拓控信息科技股份有限公司 | Train wheel tread image segmentation method based on chemical reaction optimization |
| CN111028239A (en) * | 2019-08-10 | 2020-04-17 | 杭州屏行视界信息科技有限公司 | Ellipse accurate identification method for special body measuring clothes |
| CN111260616A (en) * | 2020-01-13 | 2020-06-09 | 三峡大学 | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization |
| CN111612761A (en) * | 2020-05-20 | 2020-09-01 | 中南大学 | Breakage detection method based on insulating porcelain insulator |
| CN111964549A (en) * | 2020-07-08 | 2020-11-20 | 航天科工防御技术研究试验中心 | Detection method for judging defect of large-volume monolithic capacitor |
| CN112116550A (en) * | 2019-06-20 | 2020-12-22 | 上海电机学院 | Insulator defect detection method based on multi-corner registration |
| CN112698380A (en) * | 2020-12-16 | 2021-04-23 | 南京大学 | Beam section processing method suitable for low-energy proton beam under strong background noise |
| CN113643234A (en) * | 2021-07-05 | 2021-11-12 | 华北电力大学 | Composite insulator damage detection method, terminal equipment and readable storage medium |
| CN114037724A (en) * | 2021-10-18 | 2022-02-11 | 哈尔滨工业大学 | Heterogeneous parallel computing system and method for threshold method image segmentation and electronic equipment |
| CN114814991A (en) * | 2022-06-28 | 2022-07-29 | 成都信息工程大学 | Method and device for identifying spatial distribution area of meteorological element field |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105160669A (en) * | 2015-08-21 | 2015-12-16 | 马鞍山市安工大工业技术研究院有限公司 | Method for detecting and locating insulator defects in power transmission line image via a drone |
| CN106060466A (en) * | 2016-06-20 | 2016-10-26 | 西安工程大学 | Video image sequence-based insulator tracking monitor method |
| CN106595593A (en) * | 2016-11-10 | 2017-04-26 | 西安工程大学 | Method for monitoring windage deviation of suspension insulator strings based on ellipse fitting |
| JP2017103936A (en) * | 2015-12-02 | 2017-06-08 | 中国電力株式会社 | Insulator chain lifting device |
| CN108257138A (en) * | 2018-01-26 | 2018-07-06 | 西安工程大学 | A kind of porcelain insulator FRACTURE CHARACTERISTICS detection method based on edge detection |
-
2018
- 2018-12-11 CN CN201811511230.9A patent/CN109785285B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105160669A (en) * | 2015-08-21 | 2015-12-16 | 马鞍山市安工大工业技术研究院有限公司 | Method for detecting and locating insulator defects in power transmission line image via a drone |
| JP2017103936A (en) * | 2015-12-02 | 2017-06-08 | 中国電力株式会社 | Insulator chain lifting device |
| CN106060466A (en) * | 2016-06-20 | 2016-10-26 | 西安工程大学 | Video image sequence-based insulator tracking monitor method |
| CN106595593A (en) * | 2016-11-10 | 2017-04-26 | 西安工程大学 | Method for monitoring windage deviation of suspension insulator strings based on ellipse fitting |
| CN108257138A (en) * | 2018-01-26 | 2018-07-06 | 西安工程大学 | A kind of porcelain insulator FRACTURE CHARACTERISTICS detection method based on edge detection |
Non-Patent Citations (4)
| Title |
|---|
| 廖圣龙 等: "输电线路对绝缘子破损航拍图像检测仿真", 《计算机仿真》 * |
| 翟永杰 等: "基于目标建议与结构搜索的绝缘子识别方法", 《华北电力大学学报(自然科学版)》 * |
| 苑利等: "基于红外成像技术的零值绝缘子检测", 《高压电器》 * |
| 黄新波 等: "基于改进色差法的复合绝缘子图像分割技术", 《高电压技术》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116550A (en) * | 2019-06-20 | 2020-12-22 | 上海电机学院 | Insulator defect detection method based on multi-corner registration |
| CN111028239A (en) * | 2019-08-10 | 2020-04-17 | 杭州屏行视界信息科技有限公司 | Ellipse accurate identification method for special body measuring clothes |
| CN110517265A (en) * | 2019-09-04 | 2019-11-29 | 北京理工大学 | A kind of detection method of surface defects of products, device and storage medium |
| CN110956641A (en) * | 2019-11-20 | 2020-04-03 | 南京拓控信息科技股份有限公司 | Train wheel tread image segmentation method based on chemical reaction optimization |
| CN110909751A (en) * | 2019-11-26 | 2020-03-24 | 长沙理工大学 | Visual identification method, system and medium for transformer substation insulator cleaning robot |
| CN110909751B (en) * | 2019-11-26 | 2022-09-02 | 长沙理工大学 | Visual identification method, system and medium for transformer substation insulator cleaning robot |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN111260616A (en) * | 2020-01-13 | 2020-06-09 | 三峡大学 | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization |
| CN111612761A (en) * | 2020-05-20 | 2020-09-01 | 中南大学 | Breakage detection method based on insulating porcelain insulator |
| CN111964549B (en) * | 2020-07-08 | 2022-06-17 | 航天科工防御技术研究试验中心 | Detection method for judging defect of large-volume monolithic capacitor |
| CN111964549A (en) * | 2020-07-08 | 2020-11-20 | 航天科工防御技术研究试验中心 | Detection method for judging defect of large-volume monolithic capacitor |
| CN112698380A (en) * | 2020-12-16 | 2021-04-23 | 南京大学 | Beam section processing method suitable for low-energy proton beam under strong background noise |
| CN113643234A (en) * | 2021-07-05 | 2021-11-12 | 华北电力大学 | Composite insulator damage detection method, terminal equipment and readable storage medium |
| CN114037724A (en) * | 2021-10-18 | 2022-02-11 | 哈尔滨工业大学 | Heterogeneous parallel computing system and method for threshold method image segmentation and electronic equipment |
| CN114037724B (en) * | 2021-10-18 | 2024-04-09 | 哈尔滨工业大学 | Heterogeneous parallel computing system and method for threshold image segmentation and electronic equipment |
| CN114814991A (en) * | 2022-06-28 | 2022-07-29 | 成都信息工程大学 | Method and device for identifying spatial distribution area of meteorological element field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109785285B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785285A (en) | A kind of insulator damage testing method based on oval feature fitting | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| EP3783374A1 (en) | Method for detecting corona discharge employing image processing | |
| CN107727662B (en) | Battery piece EL black spot defect detection method based on region growing algorithm | |
| CN103364410B (en) | Crack detection method of hydraulic concrete structure underwater surface based on template search | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN105158258A (en) | Computer vision-based bamboo strip surface defect detection method | |
| CN111428748A (en) | Infrared image insulator recognition and detection method based on HOG characteristics and SVM | |
| CN111753577A (en) | Apple identification and positioning method in automatic picking robot | |
| CN106096491B (en) | Automatic identification method for microaneurysms in fundus color photographic image | |
| CN109559324A (en) | A kind of objective contour detection method in linear array images | |
| CN110288571B (en) | High-speed rail contact net insulator abnormity detection method based on image processing | |
| CN112561899A (en) | Electric power inspection image identification method | |
| CN106651831B (en) | Bamboo block defect detection method and system | |
| CN105913425B (en) | A kind of more pig contour extraction methods based on adaptive oval piecemeal and wavelet transformation | |
| CN110728668A (en) | Airspace high-pass filter for maintaining small target form | |
| CN110866916A (en) | Machine vision-based photovoltaic cell black-core black-corner detection method, device and equipment | |
| CN111583193A (en) | Pistachio nut framework extraction device based on geometric contour template matching and algorithm thereof | |
| CN114677336B (en) | Curtain wall panel damage identification method based on infrared image | |
| CN111008967B (en) | Insulator RTV coating defect identification method | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN114972397A (en) | Infrared image defect contour detection method for wind power blade composite material | |
| CN110276787B (en) | Conductor galloping monitoring method based on marker image detection | |
| CN110427979B (en) | Road water pit identification method based on K-Means clustering algorithm |
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 |