CN106680285A - Infrared image-assisted method of recognizing contamination condition of insulator by visible light image - Google Patents
Infrared image-assisted method of recognizing contamination condition of insulator by visible light image Download PDFInfo
- Publication number
- CN106680285A CN106680285A CN201611027566.9A CN201611027566A CN106680285A CN 106680285 A CN106680285 A CN 106680285A CN 201611027566 A CN201611027566 A CN 201611027566A CN 106680285 A CN106680285 A CN 106680285A
- Authority
- CN
- China
- Prior art keywords
- insulator
- visible images
- infrared image
- value
- infrared
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to an infrared image-assisted method of recognizing the contamination condition of an insulator by a visible light image. The method comprises the following steps: collecting the visible light image of the insulator, and performing visible light image processing and visible light characteristic value extraction of the insulator; collecting the infrared image of the insulator, and performing infrared image processing and infrared characteristic value extraction of the insulator; establishing a contamination level recognizing mathematic model based on the visible light image and an infrared image information-assisted visible light image contamination state recognizing mathematic model; and selecting a corresponding mathematic model to solve the contamination level of the insulator according to the environmental relative humidity. Compared with the prior art, the method provided by the invention has the advantages of removing the influence of environmental lighting, considering the influence of a high relative humidity environment on a visible light method, and being concise and universal in mathematic model.
Description
Technical field
The present invention relates to the method for recognizing insulator contamination state, more particularly, to the visible ray aided in based on infrared image
Image recognition insulator contamination status method.
Background technology
Insulator occupies critical role in defeated, power distribution network, the various microgranules such as dust, saline and alkaline, industrial fumes in air
Or birds droppings can all be deposited in outer surface of insulator and form pollution layer, make insulator dielectric intensity decreases, be susceptible to pollution flashover, cause
Very big economic loss.If the degree of filth convenient, safely and accurately can be determined, and rational cleaning meter is formulated accordingly
Draw, can more effectively prevent and treat pollution flashover, strengthen power grid operation, reduce the economic loss that pollution flashover brings.
In order to accurately determine cleaning or the flushing cycle of insulator, the detection insulator for adopting both at home and abroad at present is dirty
The method of dirty value mainly has equivalent salt density method and leakage current method.Equivalent salt density method must have a power failure to transmission line of electricity first
By measure salinity density after washing, it is difficult to reflect insulator truth in operation.Leakage current method is by detection
Flow through the size variation of insulator surface pollution layer electric current to detect the pollution level of insulator under working voltage effect.Although leakage
Current method can reflect more serious insulation fault, but leave the limited time of operator's process after failure of insulation is judged for,
It is difficult to extensively apply, and it requires a set of detection means is installed on each insulator chain, high cost, the Maintenance and Repair of device are needed
Power failure is carried out.
By contrast, there is low cost, need not disassembles, need not stop based on the insulator contamination condition detection method of image
It is electricity, the advantages of complex appts need not be installed, be difficult by electromagnetic interference, remote non-cpntact measurement including visible images method, red
Outer image method and ultraviolet image method.The electric discharge facula information of the temperature information and ultraviolet image of infrared image is only relatively wet in height
Just can be obvious enough in discharge process under degree environment, and without obvious characteristic when usually, so both approaches presence is quite big
Limitation, but temperature information is more more stable than discharge information, easily catch, thermal infrared imager price also generally less than it is ultraviolet into
As instrument.Visible images method can according to insulator disk face color characteristic reflect insulator contamination amount number, and contamination letter
The acquisition of breath does not require insulator arc-over, if ambient lighting can be overcome to affect (colour temperature, illumination etc.) this difficult point, and chooses suitable
Visible Light Characteristics value, find the corresponding relation of eigenvalue and filthy accumulation, you can recognize insulator by visible images
Gradation for surface pollution.And filth is diluted after making moist under high relative humidity, filthy color characteristic is also changed, and gradation for surface pollution identification is accurate
Rate declines, therefore relative humidity is aided in visible ray method using other information when higher.
In recent years, the recognition methodss of insulator contamination grade great majority be based on artificial intelligence approach, such as artificial neural network,
Vector machine etc. is held, but thus remains a need for a large amount of insulation subsamples of collection in advance, and by cleaning the methods such as insulator card
Sample gradation for surface pollution is measured, could be by model training to degree of precision.If can be special using contaminated insulator surface color
Temperature profile of seeking peace sets up succinct, general mathematical model, you can remove a large amount of training from contamination amount difference the characteristics of gradual change
The collection of sample and measure, improve the practical of insulator contamination grade recognition methodss conscientiously.
The content of the invention
The purpose of the present invention is exactly to provide and aided in based on infrared image to overcome the defect of above-mentioned prior art presence
Visible images identification insulator contamination status method, the method can exclude the impact of ambient lighting, and consider that environment is relative
Humidity, quickly sets up succinct, general insulator contamination grade identification model, the filthy shape to a large amount of insulators in current operation
State is made and accurately and reliably being analyzed, and provides foundation to clear up insulator contamination in time, to reduce insulator contamination power outage.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of visible images identification insulator contamination status method aided in based on infrared image, the method includes following
Step:
Step S1, gathers insulator visible images;
Step S2, insulator Visual image processing and Visible Light Characteristics value are extracted;
Step S3, gathers Insulator Infrared Image;
Step S4, Insulator Infrared Image process and infrared signature value are extracted;
Step S5, is set up the gradation for surface pollution identification mathematical model based on visible images and is aided in based on Infrared Image Information
Visible images filth state recognition mathematical model;
Step S6, according to envionmental humidity, selects corresponding mathematical model in step S5, substitutes into step S2 and step S4
In data, ask for insulator contamination grade.
Insulator visible images are gathered in step S1, ambient lighting impact need to be removed in advance, concrete operations are:
Before obtaining visible images, colour temperature correction is carried out to camera with white card, reducing ambient light colour temperature affects, then with ash
Card is exposed correction to camera, and reducing ambient light illumination affects.
In step S2, insulator Visual image processing and Visible Light Characteristics value are extracted concrete operations and are included:
Insulator visible images are converted to into gray-scale maps;Insulator disk is extracted with seed region growth method to gray level image
Face region, and obtain corresponding visible images card region;Extract visible images card region U in YUV color spaces
Component average and V component average;The absolute value of the difference of relatively 0 grade and IV level contaminated insulator card color U component averages, 0 grade
With the absolute value of the difference of IV level contaminated insulator card color V component averages, absolute value the greater corresponding component is elected as most
Whole eigenvalue.
In step S4, Insulator Infrared Image is processed and infrared signature value is extracted concrete operations and included:With the temperature of each pixel
Infrared image is converted to gray level image as gray value by angle value;Insulator is extracted with maximum variance between clusters to gray level image
Card region, and obtain corresponding infrared image card region;Extract the temperature rise maximum of T in infrared image card regionmaxAs
Infrared Image Features value.
Determine that applied mathematical model method is according to envionmental humidity in step S6:Envionmental humidity RH<
When 60%, equivalent salt deposit density value is calculated using the gradation for surface pollution identification mathematical model based on visible images;Environment is relatively wet
Need Infrared Image Features value to be assisted in identifying during degree RH >=60%, visible light image information is determined with envionmental humidity RH
With the weight of Infrared Image Information, the visible images filth state recognition mathematical model aided in based on Infrared Image Information is utilized
Calculate equivalent salt deposit density value;Equivalent salt deposit density value according to obtaining judges insulator contamination grade.
Gradation for surface pollution based on visible images recognizes that mathematical model is:
Wherein, ESDD:Equivalent salt deposit density value;
V:The visible images eigenvalue V component average of contaminated insulator to be identified;
V1:The visible images eigenvalue V component average of IV level contaminated insulators;
V0:The visible images eigenvalue V component average of 0 grade of contaminated insulator;
RH:Envionmental humidity.
Based on the visible images filth state recognition mathematical model of Infrared Image Information auxiliary it is:
Wherein, ESDD:Equivalent salt deposit density value;
V:The visible images eigenvalue V component average of contaminated insulator to be identified;
V1:The visible images eigenvalue V component average of IV level contaminated insulators;
V0:The visible images eigenvalue V component average of 0 grade of contaminated insulator;
Tmax:The temperature rise maximum in the infrared image card region of contaminated insulator to be identified;
RH:Envionmental humidity.
Compared with prior art, the present invention has advantages below:
1) impact of gentle illumination of checking colors in the gatherer process of insulator visible images has carried out preliminary removal;Visible ray
Feature U component (or V component) further uses mathematics as B component in RGB color (or R component) and the difference of luminance signal Y
Method eliminates the monochrome information difference in image, is finally completed the removal affected on ambient lighting, is conducive to improving filth etc.
The accuracy rate and efficiency of level identification;
2) impact of the high relative humidity conditions to visible ray method is considered, visible ray method is carried out using infrared information auxiliary
Help, under the different relative humiditys of realization, insulator contamination grade accurately identifies;
3) letter is set up with contamination amount is different the characteristics of gradual change using contaminated insulator surface color feature and temperature profile
Clean, general mathematical model, eliminates collection and the measure of a large amount of training samples, improves conscientiously insulator contamination grade identification side
The practical of method;
4) without the need for any equipment is installed on shaft tower, operation and maintenance cost are low, simple to operate, safe and reliable, inspection
Survey high precision.
Description of the drawings
A kind of insulator contamination state of visible images aided in based on Infrared Image Information that Fig. 1 is provided for the present invention
Recognition methodss embodiment flow chart;
Fig. 2 is the insulator visible images gathered in the present invention;
Fig. 3 is the insulator Visual image processing result figure gathered in the present invention;
Fig. 4 is the Insulator Infrared Image gathered in the present invention;
Fig. 5 is the Insulator Infrared Image result figure gathered in the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is a part of embodiment of the present invention, rather than whole embodiments.Based on this
Embodiment in bright, the every other reality obtained on the premise of creative work is not made by those of ordinary skill in the art
Example is applied, should all belong to the scope of protection of the invention.
Embodiment
The present invention proposes the visible images identification insulator contamination status method aided in based on infrared image, can exclude ring
The impact of border illumination, and consider envionmental humidity, succinct, general insulator contamination grade identification model is quickly set up, it is right
In current operation, the filthy state of a large amount of insulators is made and accurately and reliably being analyzed, and provides foundation to clear up insulator contamination in time,
To reduce insulator contamination power outage.
Referring to Fig. 1, the invention provides the visible images identification insulator contamination state side aided in based on infrared image
Method, comprises the following steps:
Step 10, gathers insulator visible images;
Insulator visible images are gathered specifically with digital camera;
In implementing, before obtaining visible images, colour temperature correction need to be carried out to camera with white card, to reduce ambient light
Colour temperature affects, then correction is exposed to camera with gray card, to reduce the impact of ambient light illumination.It is logical with gray card correct exposure value
It is often to automatically adjust shutter speed in fixed camera aperture relief camera;
Preferably, shooting distance is 0.5~4m, and the angle of depression is 15 °~45 °, and frontlighting shoots;
Except the insulator visible images of gradation for surface pollution to be measured, also need to gather 0 grade of contaminated insulator (ESDD<
0.01mg/cm2) visible images and an IV level contaminated insulator (ESDD >=0.3mg/cm2) visible images, to build
Vertical gradation for surface pollution recognizes mathematical model;If scene has no IV level contaminated insulators, the dirt of some contaminated insulator cards can be swept down
It is dirty, shot after being stacked into adequate thickness, to obtain the color characteristic close with IV level contaminated insulator card color characteristics
Value.
Step 11, insulator Visual image processing and Visible Light Characteristics value are extracted;
Insulator visible images are converted to into gray-scale maps first;
Seed region growth method is to start progressively to expand to neighborhood pixels with certain threshold value from seed point, so as to be partitioned into spy
The figure partitioning algorithm in similar region is levied, the gray-scale maps got to the conversion of insulator visible images uniformly choose several
Card seed point, and the threshold epsilon (such as ε=15) of seed growth is set, insulator card region in gray level image is extracted, then is obtained
Corresponding visible images card region.(Fig. 2 is not this to the insulator visible images of collection and processing result image such as Fig. 2
Necessary figure needed for invention), shown in Fig. 3 (Fig. 3 is not necessary figure needed for the present invention).
The difference of illumination condition, but colour temperature, aperture, shutter are reduced when step 10 gathers visible images by camera
It is have pole to regulate and control, there is certain deviation.YUV color spaces are a kind of color coding sides adopted by eurovision system
Method, including luminance component Y, chromatic component U and V, represented with R, G, B of RGB color the Y of YUV color spaces, U,
The equation of V is as follows:
Y=0.299*R+0.587*G+0.114*B
U=0.492* (B-Y)
V=0.877* (R-Y)
From equation, chromatic component U, V are that B, R deduct luminance component Y, mathematically further eliminate luminance difference
Impact.This characteristic causes U and V component in the characteristic component of various color spaces, is more suitable for as different illumination bars
Insulator visible images card color feature value under part.
As the filthy color characteristic of the insulator disk face color characteristic and Different field of different model has differences, therefore
In implementing, U components and V component need to be accepted or rejected to obtain more preferable gradation for surface pollution recognition accuracy, its essence is choosing
Go out insulator card from the bigger person of change that original color characteristic is transitioned into U components and V component after filthy color characteristic:Ask for one
Individual 0 grade of contaminated insulator (ESDD<0.01mg/cm2) visible images eigenvalue U component averages U0With V component average V0, ask
Take an IV level contaminated insulator (ESDD >=0.3mg/cm2) visible images eigenvalue U component averages U1With V component average
V1;If | U0-U1|>|V0-V1|, then U variables are taken as final visible images eigenvalue, otherwise take V variables as finally may be used
See light image eigenvalue.
Step 12, gathers Insulator Infrared Image;
Insulator Infrared Image is gathered with thermal infrared imager;
Preferably, shooting distance is recommended to be 0.5~4m, the angle of depression is 15 °~30 °, with acquisition insulation to be measured in actual photographed
Reduce complex degree of background as far as possible to be advisable while all cards.
Step 13, Insulator Infrared Image process and infrared signature value are extracted;
With the temperature value of each pixel as gray value, infrared image is converted to into gray level image;
Insulator card region is extracted with maximum variance between clusters to gray level image, and obtains corresponding infrared image card
Region;
Extract the temperature rise maximum of T in infrared image card regionmaxAs Infrared Image Features value.
Concretely comprise the following steps:
Insulator card region is extracted with maximum variance between clusters to gray level image, the equation of the method is:
σ2(T)=WA(μA-μ)2+WB(μB-μ)2
In formula, segmentation thresholds of the T for target area A and background area B, span 0~255;μAIt is averagely grey for region A
Degree;WAThe ratio of image is accounted for for region A pixel numbers;μBFor region B average gray;WBThe ratio of image is accounted for for region B pixel numbers
Example;Grand mean gray scales of the μ for image;σ2(T) it is the variance of region A and B.When the value of T causes σ2(T) when maximum, region A with
Region B difference is maximum, gray-scale maps is split as threshold value with the gray value, obtains target area A, i.e. insulator card area
Domain, finally obtains the corresponding infrared image card region of gray-scale maps.The Insulator Infrared Image and processing result image of collection is such as
Shown in Fig. 4 (Fig. 4 is not necessary figure needed for the present invention), Fig. 5 (Fig. 5 is not necessary figure needed for the present invention).
Extract the temperature rise maximum of T in infrared image card regionmaxAs Infrared Image Features value.
Step 14, is set up the gradation for surface pollution identification mathematical model based on visible images and is aided in based on Infrared Image Information
Visible images filth state recognition mathematical model;
In implementing, for the scope of application of the gradation for surface pollution identification mathematical model based on visible images is phase
To humidity RH<60%.By taking the rufous ceramic insulator of the different gradation for surface pollution that artificial kieselguhr is defiled as an example, by step 11
V component is selected as Visible Light Characteristics, 0 grade of contaminated insulator eigenvalue V is obtained0With an IV level defilement and insulation subcharacter
Value V1Afterwards, V-ESDD relational expressions can be listed:
V=V1-(V1-V0)e-10·ESDD
ESDD-V relational expressions after abbreviation are the gradation for surface pollution identification mathematical model based on visible images:
In implementing, for the visible images filth state recognition mathematical modulo aided in based on Infrared Image Information
The scope of application of type is relative humidity RH >=60%.The rufous ceramic insulation of the different gradation for surface pollution defiled with artificial kieselguhr
As a example by son, V component is selected by step 11 and is used as Visible Light Characteristics, obtain 0 grade of contaminated insulator eigenvalue V0With one
IV level contaminated insulator eigenvalue V1Afterwards, it is considered to relative humidity RH, V-ESDD relational expressions can be listed:
V=[V1-(V1-V0)e-10·ESDD-V0]·e- 0.3 (RH-60%)/10%+V0
ESDD-V relational expressions after abbreviation are the visible images filth state aided in based on Infrared Image Information
The visible light part of identification mathematical model:
By taking the rufous ceramic insulator of the different gradation for surface pollution that artificial kieselguhr is defiled as an example, selected by step 13 red
Outer feature TmaxAfterwards, and consider relative humidity RH, T can be listedmax- ESDD relational expressions:
Tmax=(12-12e-10·ESDD)·e0.3 (RH-100%)/10%
ESDD-V relational expressions after abbreviation are the visible images filth state aided in based on Infrared Image Information
Identification mathematical model infrared part:
Weighted sum is asked to visible light part and infrared part finally according to relative humidity RH, RH is higher, it is seen that light part
Weight is lower, and the weight of infrared part is higher.
To sum up, set up the gradation for surface pollution based on visible images and recognize mathematical model and based on Infrared Image Information auxiliary
Visible images filth state recognition mathematical model such as following formula:
Wherein, the value of RH need to be read from drimeter, and each variable implication is:
ESDD:Equivalent salt deposit density value;
V:The visible images eigenvalue V component average of contaminated insulator to be identified;
V1:The visible images eigenvalue V component average of IV level contaminated insulators;
V0:The visible images eigenvalue V component average of 0 grade of contaminated insulator;
Tmax:The temperature rise maximum in the infrared image card region of contaminated insulator to be identified;
RH:Envionmental humidity.
Step 15, asks for insulator contamination grade;
Wherein, the gradation for surface pollution based on visible images recognizes mathematical model and based on Infrared Image Information auxiliary
Visible images filth state recognition mathematical model, substantially with envionmental humidity RH=60% as separation:Environment phase
To humidity RH<When 60%, ESDD is the function with regard to V;Infrared Image Features value is needed to enter during envionmental humidity RH >=60%
Row assists in identifying, and ESDD is with regard to V, TmaxWith the function of RH, and visible light image information and Infrared Image Information are determined with RH
Weight.
In implementing, the mathematical model set up using step 14 substitutes into the eigenvalue V (RH of insulation subsample to be measured<
, or V, T 60%)maxWith RH (RH >=60%), you can calculate ESDD, so as to draw corresponding gradation for surface pollution.
Implement a kind of insulator contamination state of visible images aided in based on Infrared Image Information that the present invention is provided
Recognition methodss, by gathering insulator visible images, Jing image processing techniquess extract Visible Light Characteristics value, set up based on visible
The gradation for surface pollution identification mathematical model of light image, is aided in using Infrared Image Information, sets up what is aided in based on Infrared Image Information
Visible images filth state recognition mathematical model, realizes that insulator contamination grade is recognized, and then formulates cleaning plan.This method
Impact of the illumination to visible images is eliminated, and Infrared Image Information auxiliary is introduced under high relative humidity, realize complicated ring
Under the conditions of border, insulator contamination grade accurately identifies;Using contaminated insulator surface color feature and temperature profile with contamination amount
The characteristics of different and gradual change, succinct, general mathematical model is set up, collection and the measure of a large amount of training samples is eliminated, conscientiously
Improve the practical of insulator contamination grade recognition methodss;Any extras need not be installed on shaft tower, it is not necessary to
Have a power failure, save human and material resources, financial resources, safety economy reliability.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or replacement should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
The protection domain of requirement is defined.
Claims (7)
1. a kind of visible images aided in based on infrared image recognize insulator contamination status method, it is characterised in that the party
Method is comprised the following steps:
Step S1, gathers insulator visible images;
Step S2, insulator Visual image processing and Visible Light Characteristics value are extracted;
Step S3, gathers Insulator Infrared Image;
Step S4, Insulator Infrared Image process and infrared signature value are extracted;
Step S5, set up based on visible images gradation for surface pollution identification mathematical model and based on Infrared Image Information aid in can
See light image filth state recognition mathematical model;
Step S6, according to envionmental humidity, selects corresponding mathematical model in step S5, substitutes in step S2 and step S4
Data, ask for insulator contamination grade.
2. a kind of visible images aided in based on infrared image according to claim 1 recognize insulator contamination state side
Method, it is characterised in that insulator visible images are gathered in step S1, need to remove ambient lighting impact in advance, and concrete operations are:
Before obtaining visible images, colour temperature correction is carried out to camera with white card, reducing ambient light colour temperature affects, then with gray card pair
Camera is exposed correction, and reducing ambient light illumination affects.
3. a kind of visible images aided in based on infrared image according to claim 1 recognize insulator contamination state side
Method, it is characterised in that insulator Visual image processing and Visible Light Characteristics value are extracted concrete operations and included in step S2:
Insulator visible images are converted to into gray-scale maps;Insulator card area is extracted with seed region growth method to gray level image
Domain, and obtain corresponding visible images card region;Extract visible images card region U components in YUV color spaces
Average and V component average;Compare absolute value, 0 grade and the IV of 0 grade and the difference of IV level contaminated insulator card color U component averages
The absolute value of the difference of level contaminated insulator card color V component average, elects absolute value the greater corresponding component as final spy
Value indicative.
4. a kind of visible images aided in based on infrared image according to claim 1 recognize insulator contamination state side
Method, it is characterised in that Insulator Infrared Image is processed and infrared signature value is extracted concrete operations and included in step S4:Use each picture
Infrared image is converted to gray level image as gray value by the temperature value of element;Gray level image is extracted with maximum variance between clusters
Insulator card region, and obtain corresponding infrared image card region;Extract the temperature rise maximum in infrared image card region
TmaxAs Infrared Image Features value.
5. a kind of visible images aided in based on infrared image according to claim 1 recognize insulator contamination state side
Method, it is characterised in that determine that applied mathematical model method is according to envionmental humidity in step S6:Envionmental humidity
RH<When 60%, equivalent salt deposit density value is calculated using the gradation for surface pollution identification mathematical model based on visible images;Environment is relative
Need Infrared Image Features value to be assisted in identifying during humidity RH >=60%, visible images letter is determined with envionmental humidity RH
The weight of breath and Infrared Image Information, using the visible images filth state recognition mathematical modulo aided in based on Infrared Image Information
Type calculates equivalent salt deposit density value;Equivalent salt deposit density value according to obtaining judges insulator contamination grade.
6. a kind of visible images aided in based on infrared image according to claim 1 recognize insulator contamination state side
Method, it is characterised in that the gradation for surface pollution based on visible images recognizes that mathematical model is:
Wherein, ESDD:Equivalent salt deposit density value;
V:The visible images eigenvalue V component average of contaminated insulator to be identified;
V1:The visible images eigenvalue V component average of IV level contaminated insulators;
V0:The visible images eigenvalue V component average of 0 grade of contaminated insulator;
RH:Envionmental humidity.
7. the visible images aided in based on infrared image according to claim 1 recognize insulator contamination status method,
Characterized in that,
Based on the visible images filth state recognition mathematical model of Infrared Image Information auxiliary it is:
Wherein, ESDD:Equivalent salt deposit density value;
V:The visible images eigenvalue V component average of contaminated insulator to be identified;
V1:The visible images eigenvalue V component average of IV level contaminated insulators;
V0:The visible images eigenvalue V component average of 0 grade of contaminated insulator;
Tmax:The temperature rise maximum in the infrared image card region of contaminated insulator to be identified;
RH:Envionmental humidity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611027566.9A CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611027566.9A CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106680285A true CN106680285A (en) | 2017-05-17 |
CN106680285B CN106680285B (en) | 2022-04-05 |
Family
ID=58866677
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611027566.9A Active CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106680285B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107240095A (en) * | 2017-05-25 | 2017-10-10 | 武汉大学 | A kind of DC line pollution severity of insulators state recognition method based on visible images |
CN107292246A (en) * | 2017-06-05 | 2017-10-24 | 河海大学 | Infrared human body target identification method based on HOG PCA and transfer learning |
CN107464233A (en) * | 2017-07-19 | 2017-12-12 | 国家电网公司 | The image detecting method and system of composite insulator based on Lab color modes |
CN107729397A (en) * | 2017-09-21 | 2018-02-23 | 国网天津市电力公司电力科学研究院 | A kind of method that icing snow type is judged using image RGB component |
CN107767364A (en) * | 2017-09-12 | 2018-03-06 | 中国林业科学研究院林业研究所 | The method that trees canopy surface temperature is precisely extracted based on thermal-induced imagery |
CN107885921A (en) * | 2017-10-27 | 2018-04-06 | 国家电网公司 | Composite insulator rod core aging evaluation method |
CN108872819A (en) * | 2018-07-29 | 2018-11-23 | 湖南湖大华龙电气与信息技术有限公司 | Isolator detecting unmanned plane and method based on infrared thermal imagery and visible light |
CN110567964A (en) * | 2019-07-19 | 2019-12-13 | 华瑞新智科技(北京)有限公司 | method and device for detecting defects of power transformation equipment and storage medium |
CN110824311A (en) * | 2019-11-22 | 2020-02-21 | 南京信息工程大学 | Zinc oxide valve plate breakdown point detection device and method based on image recognition |
CN112966576A (en) * | 2021-02-24 | 2021-06-15 | 西南交通大学 | System and method for aiming insulator water washing robot based on multi-light source image |
CN113241228A (en) * | 2021-05-31 | 2021-08-10 | 江西尚高电瓷电气有限公司 | Antifouling self-cleaning type line column type porcelain insulator |
CN113884500A (en) * | 2021-10-12 | 2022-01-04 | 国家电网有限公司 | Porcelain insulator defect detection method based on ultraviolet imaging |
CN115047010A (en) * | 2022-04-26 | 2022-09-13 | 国网四川省电力公司电力科学研究院 | Insulator contamination degree detection method based on multi-source spectrum sensing technology |
CN116071368A (en) * | 2023-04-07 | 2023-05-05 | 国网山西省电力公司电力科学研究院 | Insulator pollution multi-angle image detection and fineness analysis method and device |
CN116679171A (en) * | 2023-05-15 | 2023-09-01 | 江苏云峰科技股份有限公司 | Insulation state judging system of insulation piece of wind power generation switch |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102809568A (en) * | 2012-08-28 | 2012-12-05 | 广东电网公司佛山供电局 | Method and system for monitoring contamination distribution of insulator |
CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Insulator detection method and device based on visible light image |
CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
-
2016
- 2016-11-17 CN CN201611027566.9A patent/CN106680285B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102809568A (en) * | 2012-08-28 | 2012-12-05 | 广东电网公司佛山供电局 | Method and system for monitoring contamination distribution of insulator |
CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Insulator detection method and device based on visible light image |
CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
Non-Patent Citations (3)
Title |
---|
LIJUN JIN 等: "Condition Evaluation of the Contaminated Insulators by Visible Light Images Assisted With Infrared Information", 《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》 * |
LIU HUI 等: "Detection and Processing for ±660 Composite Insulator Abnormal Discharge", 《2014 INTERNATIONAL CONFERENCE ON POWER SYSTEM TECHNOLOGY 》 * |
金立军等: "基于红外与可见光图像信息融合的绝缘子污秽等级识别", 《中国电机工程学报》 * |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107240095A (en) * | 2017-05-25 | 2017-10-10 | 武汉大学 | A kind of DC line pollution severity of insulators state recognition method based on visible images |
CN107292246A (en) * | 2017-06-05 | 2017-10-24 | 河海大学 | Infrared human body target identification method based on HOG PCA and transfer learning |
CN107464233A (en) * | 2017-07-19 | 2017-12-12 | 国家电网公司 | The image detecting method and system of composite insulator based on Lab color modes |
CN107464233B (en) * | 2017-07-19 | 2021-11-05 | 国家电网公司 | Composite insulator image detection method and system based on Lab color mode |
CN107767364B (en) * | 2017-09-12 | 2021-03-23 | 中国林业科学研究院林业研究所 | Method for accurately extracting temperature of tree canopy based on infrared thermal image |
CN107767364A (en) * | 2017-09-12 | 2018-03-06 | 中国林业科学研究院林业研究所 | The method that trees canopy surface temperature is precisely extracted based on thermal-induced imagery |
CN107729397A (en) * | 2017-09-21 | 2018-02-23 | 国网天津市电力公司电力科学研究院 | A kind of method that icing snow type is judged using image RGB component |
WO2019057174A1 (en) * | 2017-09-21 | 2019-03-28 | 国网天津市电力公司电力科学研究院 | Method for determining type of ice and snow cover |
US11093744B1 (en) | 2017-09-21 | 2021-08-17 | Electric Power Science & Research Institute Of State Grid Tianjin Electric Power Company | Method and device for determining types of ice-and-snow cover |
CN107729397B (en) * | 2017-09-21 | 2020-01-14 | 国网天津市电力公司电力科学研究院 | Method for judging ice and snow covering type by using RGB (red, green and blue) components of image |
CN107885921A (en) * | 2017-10-27 | 2018-04-06 | 国家电网公司 | Composite insulator rod core aging evaluation method |
CN108872819A (en) * | 2018-07-29 | 2018-11-23 | 湖南湖大华龙电气与信息技术有限公司 | Isolator detecting unmanned plane and method based on infrared thermal imagery and visible light |
CN110567964A (en) * | 2019-07-19 | 2019-12-13 | 华瑞新智科技(北京)有限公司 | method and device for detecting defects of power transformation equipment and storage medium |
CN110824311A (en) * | 2019-11-22 | 2020-02-21 | 南京信息工程大学 | Zinc oxide valve plate breakdown point detection device and method based on image recognition |
CN112966576A (en) * | 2021-02-24 | 2021-06-15 | 西南交通大学 | System and method for aiming insulator water washing robot based on multi-light source image |
CN113241228A (en) * | 2021-05-31 | 2021-08-10 | 江西尚高电瓷电气有限公司 | Antifouling self-cleaning type line column type porcelain insulator |
CN113884500A (en) * | 2021-10-12 | 2022-01-04 | 国家电网有限公司 | Porcelain insulator defect detection method based on ultraviolet imaging |
CN115047010A (en) * | 2022-04-26 | 2022-09-13 | 国网四川省电力公司电力科学研究院 | Insulator contamination degree detection method based on multi-source spectrum sensing technology |
CN116071368A (en) * | 2023-04-07 | 2023-05-05 | 国网山西省电力公司电力科学研究院 | Insulator pollution multi-angle image detection and fineness analysis method and device |
CN116071368B (en) * | 2023-04-07 | 2023-06-16 | 国网山西省电力公司电力科学研究院 | Insulator pollution multi-angle image detection and fineness analysis method and device |
CN116679171A (en) * | 2023-05-15 | 2023-09-01 | 江苏云峰科技股份有限公司 | Insulation state judging system of insulation piece of wind power generation switch |
CN116679171B (en) * | 2023-05-15 | 2023-11-10 | 江苏云峰科技股份有限公司 | Insulation state judging system of insulation piece of wind power generation switch |
Also Published As
Publication number | Publication date |
---|---|
CN106680285B (en) | 2022-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106680285A (en) | Infrared image-assisted method of recognizing contamination condition of insulator by visible light image | |
CN104483326B (en) | High-voltage line defects of insulator detection method and system based on depth belief network | |
CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
CN106780438B (en) | Insulator defect detection method and system based on image processing | |
CN110458839B (en) | Effective wire and cable monitoring system | |
CN102288884B (en) | External insulation discharging detecting method based on ultraviolet light spots | |
CN105957088B (en) | Transformer composite insulator casing monitoring method and system based on computer vision | |
CN108898085A (en) | Intelligent road disease detection method based on mobile phone video | |
CN105868722A (en) | Identification method and system of abnormal power equipment images | |
CN104408459A (en) | Image identification method applied to power equipment monitoring | |
CN107240079A (en) | A kind of road surface crack detection method based on image procossing | |
CN104331978B (en) | Recognition device and method for fold of paper currency | |
CN103442209A (en) | Video monitoring method of electric transmission line | |
CN105957081B (en) | A kind of glass insulator falls to go here and there fault detection method | |
CN106326808A (en) | Method for detecting bird nests in power transmission line poles based on unmanned plane images | |
CN103196380A (en) | Electric transmission line image acquisition device and electric transmission line icing thickness detection system | |
CN108108772A (en) | A kind of insulator contamination condition detection method based on distribution line Aerial Images | |
CN105096305A (en) | Method and device for analyzing state of insulator | |
CN109345586A (en) | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology | |
CN107833211A (en) | Zero resistance insulator automatic testing method and device based on infrared image | |
CN107179479A (en) | Transmission pressure broken lot defect inspection method based on visible images | |
CN108665468A (en) | A kind of device and method extracting tangent tower insulator chain based on dimensionality reduction gray scale texture-form matrix | |
CN109858636A (en) | Power circuit livewire work method and apparatus based on mixed reality | |
CN114445331A (en) | Cable intermediate joint construction defect detection method, system and device based on image recognition | |
CN111008967B (en) | Insulator RTV coating defect identification method |
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 |