CN107240094A - A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking - Google Patents
A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking Download PDFInfo
- Publication number
- CN107240094A CN107240094A CN201710355723.7A CN201710355723A CN107240094A CN 107240094 A CN107240094 A CN 107240094A CN 201710355723 A CN201710355723 A CN 201710355723A CN 107240094 A CN107240094 A CN 107240094A
- Authority
- CN
- China
- Prior art keywords
- mrow
- image
- msub
- infrared image
- electrical equipment
- 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.)
- Pending
Links
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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking, this method comprises the following steps:Validity feature analysis is carried out respectively to infrared image and visible images;Carry out the image registration based on profile information;Using image registration results, validity feature extraction is carried out to the infrared image after image registration and visible images according to validity feature analysis result, and carries out imaging importing, visible images is completed and is reconstructed with infrared image.Compared with prior art, the present invention have the advantages that very intuitively reaction electrical equipment defect characteristic, be conducive to comprehensive accurate judgement, algorithmic stability, information reservation degree height and strong applicability to electrical equipment defect.
Description
Technical field
The present invention relates to electrical equipment malfunction detection and diagnosis, more particularly, to a kind of for electrical equipment on-line checking
Visible ray and infrared image reconstructing method.
Background technology
As China's power network scale constantly expands, also more and more higher is required to the safety and reliability of operation of power networks, and
Defect caused by abrasion, oxidation, burn into aging, filthy and external force occurs in power network electrical equipment longtime running, so to electricity
Gas equipment carries out repair based on condition of component, potential faults is investigated in time, to safeguarding that power network safety operation is particularly important.
In electrical equipment malfunction detection and diagnostic field, it is seen that the contactless inspection such as light image detection, infrared image detection
Survey method is by feat of cost is low, speed fast, service without power-off the features such as, obtained applying more and more widely.With visible ray
The features such as profile, texture, the color of image can recognize that the mechanical breakdown of electrical equipment, such as power line foreign matter, wire strand breakage, insulation
Son falls piece, stockbridge damper displacement, conductor spacer fracture etc.;Electrical equipment overheating failure, such as gold utensil are can detect with infrared image
Loose contact, terminals overheat, external insulation surface-discharge heating etc..Though grid equipment species is various, most of electrical equipments
All have that profile texture is complete, color change substantially, the defect characteristic such as temperature rise is higher, these defects during line walking respectively by
Visible ray and infrared imaging device are caught, but because single detecting system draws an inference according only to unilateral parameter information, are usually made
Into electrical equipment malfunction mistaken diagnosis and fail to pinpoint a disease in diagnosis.Therefore, the visible ray and infrared image that carry out electrical equipment carry out merging reconstruct, by
The validity feature of two class images is integrated in an image, can not only reduce information redundance, be also beneficial to electrical equipment malfunction
It is comprehensive it is accurate judge.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind is used for electrical equipment
The visible ray and infrared image reconstructing method of on-line checking.Entered by visible images and infrared image to same electrical equipment
Image registration of the row based on profile information, the validity feature of two kinds of images is combined, be reconstructed into one comprising visible ray and
The two dimensional image of infrared two aspects image information.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking, this method includes following step
Suddenly:
S1, validity feature analysis is carried out respectively to infrared image and visible images;
S2, image registration of the progress based on profile information;
S3, using image registration results, according to validity feature analysis result to the infrared image after image registration and visible
Light image carries out validity feature extraction, and carries out imaging importing, completes visible images and is reconstructed with infrared image.
Image registrations of the step S2 based on profile information comprises the following steps:
S201, infrared image and visible images are carried out obtaining infrared image profile diagram after image preprocessing respectively and can
See light image profile diagram;
S202, Best Affine transformation search is carried out to infrared image profile diagram and visible images profile diagram, and carried out most
Good affine transformation;
S203, to infrared image artwork carry out Best Affine conversion, complete image registration.
Described validity feature analysis is chosen specifically by image procossing, characteristic processing and feature selection step embodies electricity
The feature of gas equipment deficiency or failure.
Described Best Affine transformation search is using the average nearest of infrared image profile diagram and visible images profile diagram
Distance carries out image registration degree measurement, and average minimum distance D (A, B) calculation formula function is:
D (A, B)=min (d (A, B), d (B, A))
Wherein, A, B are respectively the visible ray contour images and infrared profile image of electrical equipment, ai、biRespectively image A
In j-th of profile point, a in i-th profile point, Bj、biI-th of profile point, n in j-th profile point, B in respectively image AA、
nBProfile point number in respectively image A, B, d (A, B), d (B, A) are respectively that the point on image A is nearest to being averaged for image B
The average minimum distance of distance, the point on image B to image A.
Visible images and infrared image restructuring procedure in S3 are as follows:
Wherein, IinfAnd IvisRespectively the rgb pixel value of infrared image and visible images, I1After (x, y) is reconstruct
Rgb pixel value, T (x, y) is the pixel temperature value that coordinate is (x, y) on infrared image, TthreshFor the temperature threshold of infrared image
Value.
Described Best Affine transformation search is specially to find the best parameter group for carrying out affine transformation.
Compared with prior art, the present invention has advantages below:
1. the visible ray of electrical equipment and infrared image are carried out merging reconstruct by the present invention, by the validity feature of two class images
An image is integrated in, information redundance is greatly reduced, comprehensive accurate judgement to electrical equipment defect is also beneficial to;
2. the present invention reflects in the overheating region of electrical equipment infrared image onto visible images, very intuitively
Electrical equipment defect characteristic is reacted, while also accurately being positioned to electrical equipment defective locations;
3. inventive algorithm is stable, information reservation degree is high, highly reliable, is more or less the same for shooting angle and image size
Visible ray and infrared image can accurately be reconstructed;
4. strong applicability of the present invention, is applicable not only to the detection of the electrical equipment malfunctions such as insulator, shaft tower, gold utensil, moreover it is possible to transport
Need to combine the field of infrared image and visible light image information for remote sensing, safety check, mechanical wear detection etc..
Brief description of the drawings
Fig. 1 reconstructs flow chart for the visible ray and infrared image of the inventive method;
Fig. 2 is the particle cluster algorithm flow chart of the inventive method;
The visible images for the electric force pole tower that Fig. 3 illustrates for the present invention;
The infrared image for the electric force pole tower that Fig. 4 illustrates for the present invention;
The visible ray profile diagram for the electric force pole tower that Fig. 5 illustrates for the present invention;
The infrared image profile diagram for the electric force pole tower that Fig. 6 illustrates for the present invention;
Effect after visible ray and infrared image the profile diagram registration for the electric force pole tower that Fig. 7 illustrates for the present invention;
The visible ray and infrared image quality reconstruction figure for the electric force pole tower that Fig. 8 illustrates for the present invention.
In figure:1st, visible images, 2, infrared image, 3, validity feature analysis, 4, the image registration based on profile information,
5th, gray processing, Threshold segmentation, edge extracting, 6, visible ray and infrared image profile diagram, 7, Best Affine transformation search, 8, infrared
Image artwork carries out Best Affine conversion, 9, validity feature extraction and imaging importing, 10, visible ray and infrared image reconstruct.
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 hair
Embodiment in bright, the every other reality that those of ordinary skill in the art are obtained on the premise of creative work is not made
Example is applied, should all belong to the scope of protection of the invention.
Embodiment
As shown in Figure 1, it is adaptable to the visible ray and infrared image reconstructing method of electrical equipment on-line checking, by same
The visible images 1 and infrared image 2 of electrical equipment carry out the image registration 4 based on profile information, by the effective of two kinds of images
Feature is combined, and is reconstructed into a two dimensional image comprising visible ray and infrared two aspects image information.
Described validity feature is selected after being analyzed by validity feature, validity feature analysis refer to by image procossing,
The feature of the best performance electrical equipment defect of energy or failure is chosen after feature extraction and feature selecting, by relatively a variety of more normal
With the visible ray and infrared image of the electrical equipment of existing defects, the validity feature of the infrared image of selection is high temperature rise region,
The validity feature of visible images is profile, color and the texture of electrical equipment, in addition, the background of visible images is for electric
The fault location of equipment is also particularly significant.
The described image registration based on profile information to infrared image and visible images by carrying out gray processing, threshold value
The threshold value in visible ray and infrared image profile diagram, described Threshold segmentation is obtained after the image preprocessings such as segmentation, edge extracting
Refer to adaptive gray threshold, general to determine gray threshold using maximum variance between clusters, described edge extracting uses canny
Edge detection operator is carried out.The visible ray and infrared image profile diagram for making destination object by Best Affine transformation search are overlapped,
Best Affine conversion is carried out finally by infrared image artwork and realizes process of image registration, and described Best Affine transformation search can
Realized by population searching algorithm.
Described affine transformation includes translation transformation, stretching and rotation transformation, and translation transformation matrix is:
tx、tyRespectively image transverse translation amount and longitudinal translation amount, the matrix of stretching is:
Cx、CyRespectively image transversal stretching amount and longitudinal extension amount, the matrix of rotation transformation is:
θ is image rotation angle.Described Best Affine transformation search process is to find optimal affine transformation parameter group
Close (tx0, ty0, Cx0, Cy0, θ0), make infrared profile figure after this affine change, infrared image profile and visible images wheel
Exterior feature overlaps best results.
In the particle cluster algorithm, if i-th of particle position is Xi=(xi1,xi2,...,xi5), it is best that it is lived through
Position is designated as Pi=(pi1,pi2,...,pi5).Particle i speed Vi=(vi1,vi2,...,vi5) represent.To every generation particle,
Particle updates speed and the position of oneself using following formula:
vk+1 id=vk id+c1*rand1*(pk id-xk id)+c2*rand2*(pk gd-xk id) (1)
xk+1 id=xk id+vk+1 id (2)
K is iterations, xk idIt is the position of current particle, c1, c2It is Studying factors, rand1And rand2For [0,1] area
Interior random number.PgFor the optimum position in all particles, P is designated asg=(pg1,pg2,...,pg5)。
It is described carry out Best Affine transformation search with particle cluster algorithm during image registration degree (fitness) from
The average minimum distance of light and infrared profile image is weighed, and average minimum distance D (A, B) calculation formula is fitness function
For:
D (A, B)=min (d (A, B), d (B, A)) (3)
Wherein, A, B are respectively the visible ray contour images and infrared profile image of electrical equipment, ai、biRespectively image A
In j-th of profile point, a in i-th profile point, Bj、biI-th of profile point, n in j-th profile point, B in respectively image AA、
nBProfile point number in respectively image A, B, d (A, B), d (B, A) are respectively that the point on image A is nearest to being averaged for image B
The average minimum distance of distance, the point on image B to image A.
Described visible ray is after infrared image artwork carries out Best Affine conversion, according to effective with infrared image reconstruct
The result of signature analysis carries out validity feature to visible images and infrared image and extracted and imaging importing realization, described image
Superposition is by the high temperature rise region overlay of infrared image on visible images.Restructuring procedure is as follows:
IinfAnd IvisThe respectively rgb pixel value of infrared image and visible images, I is the rgb pixel value after reconstruct.
TthreshThe temperature threshold of infrared image, for distinguishing high temperature rise region, can equally be counted using maximum variance between clusters
Calculate.
Visible images such as Fig. 3 electrical equipments are shot by Visible Light Camera, and such as Fig. 4 infrared images pass through infrared thermal imagery
Instrument is shot.When carrying out the visible ray of electrical equipment and infrared image shooting, should try one's best holding visible ray and infrared shooting angle
Degree is consistent, and shooting distance can difference, but target size difference in both images is unsuitable excessive.
Validity feature analysis 3 is carried out to the visible images 1 and infrared image 2 shot, passes through relatively more a variety of normal works
Make the visible ray and infrared image with the electrical equipment of failure, and the image preprocessings such as gray processing, Threshold segmentation are carried out to it, count
Calculate its characteristic quantity and its validity feature is selected using Fisher criterions, the validity feature retained the need for obtaining is visible images
In electrical equipment profile, texture, color character and infrared image in high temperature rise region area and be most worth.
Visible images and infrared image to the electric force pole tower of the shooting shown in Fig. 3 and Fig. 4 carry out being based on profile
The image registration 4 of information, obtains visible ray and infrared image profile diagram 6 by gray processing, Threshold segmentation, edge extracting 5, uses
Fig. 3 and the gray threshold of Fig. 4 visible images that maximum variance between clusters are determined are 100, and the gray threshold of infrared image is
25, susceptibility threshold is 0.2 during with canny operators to visible ray and infrared image progress edge extracting, after image procossing
Electric power tower visible ray and infrared profile figure as shown in Figure 5 and Figure 6.
The visible ray and infrared profile figure of the electric power tower shown in Fig. 5 and Fig. 6 are carried out using particle cluster algorithm most preferably to imitate
Transformation search 7 is penetrated, is needed first true by the bianry image center of gravity and area that calculate the visible ray after Threshold segmentation and infrared image
Determine optimizing hunting zone.If the bianry image barycentric coodinates difference of visible ray and infrared image is (x0, y0), area ratio is r0, then it is red
Outer image transverse translation amount and longitudinal translation amount tx、tyThe region of search be respectively [x0-100,x0+ 100] and [y0-100,y0+
100], infrared image transversal stretching amount and longitudinal extension amount Cx、CyThe region of search be [r0-0.5,r0+ 0.5], infrared image
The region of search of the θ anglecs of rotation is defaulted as [- 0.5,0.5].The visible ray of electric power tower and the bianry image center of gravity of infrared image
Coordinate difference is (73,22), and area ratio is 0.7439.Then particle cluster algorithm search Best Affine conversion is carried out, search routine is such as
Shown in Fig. 2.The affine transformation parameter region of search is normalized to [0,1] entirely, the maximal rate of particle search is limited as 0.1, enters
Row particle group velocity and the initialization of position, calculate images match degree, i.e. fitness, the minimum particle position of record fitness.
Renewal is constantly iterated to population and calculates fitness, until reach that maximum iteration or fitness reach requirement, this
Parameter representated by the minimum particle position of Shi Jilu fitness is Best Affine transformation parameter.Maximum iteration is general
It is set as 50 times, specified fitness is typically set to 0.1.
As shown in fig. 7, infrared image profile diagram is carried out after Best Affine conversion, infrared image profile and visible images wheel
Wide substantially overlapping, fitness now is 1.3.Infrared image artwork is subjected to Best Affine conversion 8, the RGB tri- of infrared image
The image of individual component enters line translation according to Best Affine transformation parameter, completes the process of image registration 4 based on profile information.
The visible ray and infrared image after image registration are completed, validity feature is carried out and extracts and imaging importing 9.By infrared figure
The temperature rise of picture is extracted higher than the region of temperature threshold from infrared original image, and is superimposed upon visible ray figure in a covered manner
As upper, i.e., the pixel value of the correspondence position of visible images RGB component is replaced by infrared image RGB component, complete visible ray
With infrared image reconstruct 10.The infrared image temperature threshold of electric power tower is 28 in the Fig. 4 determined through maximum between-cluster variance algorithm
DEG C, the effect after imaging importing reconstruct is as shown in Figure 8.
The foregoing is only a specific embodiment of the 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 substitutions should be all included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (6)
1. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking, it is characterised in that this method bag
Include following steps:
S1, validity feature analysis is carried out respectively to infrared image and visible images;
S2, image registration of the progress based on profile information;
S3, using image registration results, according to validity feature analysis result to the infrared image after image registration and visible ray figure
As carrying out validity feature extraction, and imaging importing is carried out, complete visible images and reconstructed with infrared image.
2. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking according to claim 1,
Characterized in that, image registrations of the step S2 based on profile information comprises the following steps:
S201, infrared image and visible images are carried out obtaining infrared image profile diagram and visible ray after image preprocessing respectively
Image outline figure;
S202, Best Affine transformation search is carried out to infrared image profile diagram and visible images profile diagram, and most preferably imitate
Penetrate conversion;
S203, to infrared image artwork carry out Best Affine conversion, complete image registration.
3. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking according to claim 1,
Characterized in that, described validity feature analysis chooses body specifically by image procossing, characteristic processing and feature selection step
The feature of existing electrical equipment defect or failure.
4. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking according to claim 2,
Characterized in that, described Best Affine transformation search using infrared image profile diagram and visible images profile diagram it is average most
Image registration degree measurement is closely carried out, average minimum distance D (A, B) calculation formula function is:
D (A, B)=min (d (A, B), d (B, A))
<mrow>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>A</mi>
<mo>,</mo>
<mi>B</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<msub>
<mi>n</mi>
<mi>A</mi>
</msub>
</mfrac>
<munder>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>&Element;</mo>
<mi>A</mi>
</mrow>
</munder>
<munder>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
<mrow>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mo>&Element;</mo>
<mi>B</mi>
</mrow>
</munder>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<mo>|</mo>
</mrow>
<mrow>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>B</mi>
<mo>,</mo>
<mi>A</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<msub>
<mi>n</mi>
<mi>B</mi>
</msub>
</mfrac>
<munder>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>b</mi>
<mi>i</mi>
</msub>
<mo>&Element;</mo>
<mi>B</mi>
</mrow>
</munder>
<munder>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
<mrow>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
<mo>&Element;</mo>
<mi>A</mi>
</mrow>
</munder>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>b</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<mo>|</mo>
</mrow>
Wherein, A, B are respectively the visible ray contour images and infrared profile image of electrical equipment, ai、biI-th in respectively image A
J-th of profile point, a in individual profile point, Bj、biI-th of profile point, n in j-th profile point, B in respectively image AA、nBRespectively
For the profile point number in image A, B, d (A, B), d (B, A) be respectively the point on image A to image B average minimum distance,
The average minimum distance of point on image B to image A.
5. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking according to claim 1,
Characterized in that, the visible images and infrared image restructuring procedure in S3 are as follows:
<mrow>
<msub>
<mi>I</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mi>n</mi>
<mi>f</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>&GreaterEqual;</mo>
<msub>
<mi>T</mi>
<mrow>
<mi>t</mi>
<mi>h</mi>
<mi>r</mi>
<mi>e</mi>
<mi>s</mi>
<mi>h</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>v</mi>
<mi>i</mi>
<mi>s</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>T</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo><</mo>
<msub>
<mi>T</mi>
<mrow>
<mi>t</mi>
<mi>h</mi>
<mi>r</mi>
<mi>e</mi>
<mi>s</mi>
<mi>h</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, IinfAnd IvisRespectively the rgb pixel value of infrared image and visible images, I1(x, y) is the RGB pictures after reconstruct
Element value, T (x, y) is the pixel temperature value that coordinate is (x, y) on infrared image, TthreshFor the temperature threshold of infrared image.
6. a kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking according to claim 2,
Characterized in that, described Best Affine transformation search is specially to find the best parameter group for carrying out affine transformation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710355723.7A CN107240094A (en) | 2017-05-19 | 2017-05-19 | A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710355723.7A CN107240094A (en) | 2017-05-19 | 2017-05-19 | A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107240094A true CN107240094A (en) | 2017-10-10 |
Family
ID=59985877
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710355723.7A Pending CN107240094A (en) | 2017-05-19 | 2017-05-19 | A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107240094A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108061847A (en) * | 2017-12-23 | 2018-05-22 | 华北电力大学(保定) | A kind of dry reactor epoxy resins insulation medium cracking detection method |
CN108230237A (en) * | 2017-12-15 | 2018-06-29 | 同济大学 | A kind of multispectral image reconstructing method for electrical equipment on-line checking |
CN108932721A (en) * | 2018-06-28 | 2018-12-04 | 上海电力学院 | A kind of infrared Image Segmentation and fusion method for crusing robot |
CN109196551A (en) * | 2017-10-31 | 2019-01-11 | 深圳市大疆创新科技有限公司 | Image processing method, equipment and unmanned plane |
CN109978821A (en) * | 2019-02-03 | 2019-07-05 | 湖南工业大学 | A kind of wheel wear monitoring method based on image recognition |
CN111464800A (en) * | 2019-01-21 | 2020-07-28 | 佳能株式会社 | Image processing apparatus, system, method, and computer-readable storage medium |
CN113589117A (en) * | 2021-08-16 | 2021-11-02 | 国网江苏省电力有限公司泰州供电分公司 | Power equipment defect detection system and detection method |
CN115147468A (en) * | 2022-04-02 | 2022-10-04 | 杭州汇萃智能科技有限公司 | Dual-light image registration method and system and readable storage medium |
CN116563283A (en) * | 2023-07-10 | 2023-08-08 | 山东联兴能源集团有限公司 | Steam boiler gas leakage detection method and detection device based on image processing |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1546960A (en) * | 2003-12-05 | 2004-11-17 | 广州科易光电技术有限公司 | Real time display control device for composite video of infrared thermal imaging image and visible light image |
US20090238432A1 (en) * | 2008-03-21 | 2009-09-24 | General Electric Company | Method and system for identifying defects in radiographic image data corresponding to a scanned object |
CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
CN103714548A (en) * | 2013-12-27 | 2014-04-09 | 西安电子科技大学 | Infrared image and visible image registration method based on visual attention |
CN104253482A (en) * | 2014-08-08 | 2014-12-31 | 济南大学 | Image data base and inspection robot-based equipment trouble detection method |
CN104268853A (en) * | 2014-03-06 | 2015-01-07 | 上海大学 | Infrared image and visible image registering method |
CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学(保定) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
CN105205818A (en) * | 2015-09-18 | 2015-12-30 | 国网上海市电力公司 | Method for registering infrared image and visible light image of electrical equipment |
CN105354851A (en) * | 2015-11-20 | 2016-02-24 | 中国安全生产科学研究院 | Infrared and visible light video fusion method and fusion system adaptive to distance |
CN105488562A (en) * | 2015-11-27 | 2016-04-13 | 浙江工业大学义乌科学技术研究院有限公司 | Irregular part stock layout method based on multi-factor particle swarm algorithm |
-
2017
- 2017-05-19 CN CN201710355723.7A patent/CN107240094A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1546960A (en) * | 2003-12-05 | 2004-11-17 | 广州科易光电技术有限公司 | Real time display control device for composite video of infrared thermal imaging image and visible light image |
US20090238432A1 (en) * | 2008-03-21 | 2009-09-24 | General Electric Company | Method and system for identifying defects in radiographic image data corresponding to a scanned object |
CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
CN103714548A (en) * | 2013-12-27 | 2014-04-09 | 西安电子科技大学 | Infrared image and visible image registration method based on visual attention |
CN104268853A (en) * | 2014-03-06 | 2015-01-07 | 上海大学 | Infrared image and visible image registering method |
CN104253482A (en) * | 2014-08-08 | 2014-12-31 | 济南大学 | Image data base and inspection robot-based equipment trouble detection method |
CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学(保定) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
CN105205818A (en) * | 2015-09-18 | 2015-12-30 | 国网上海市电力公司 | Method for registering infrared image and visible light image of electrical equipment |
CN105354851A (en) * | 2015-11-20 | 2016-02-24 | 中国安全生产科学研究院 | Infrared and visible light video fusion method and fusion system adaptive to distance |
CN105488562A (en) * | 2015-11-27 | 2016-04-13 | 浙江工业大学义乌科学技术研究院有限公司 | Irregular part stock layout method based on multi-factor particle swarm algorithm |
Non-Patent Citations (8)
Title |
---|
ENRIQUE COIRAS 等: "A Segment-based Registration Technique for Visual-IR Images", 《CORLOS MIRAVET》 * |
丁明跃 等编著: "《物联网识别技术》", 31 July 2012, 中国铁道出版社 * |
刘波 等: "基于射线轮廓点匹配的生猪红外与可见光图像自动配准", 《农业工程学报》 * |
孔韦韦 等编著: "《图像融合技术:基于多分辨率非下采样理论与方法》", 31 July 2015, 西安电子科技大学出版社 * |
郝松傲 等: "热红外图像与可见光图像的配准与融合", 《四川测绘》 * |
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》 * |
陈家斌 编著: "《高压电器》", 31 January 2003, 中国电力出版社 * |
陶冰洁 等: "采用仿射变换的红外与可见光图像配准方法", 《光电工程》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109196551B (en) * | 2017-10-31 | 2021-08-27 | 深圳市大疆创新科技有限公司 | Image processing method and device and unmanned aerial vehicle |
CN109196551A (en) * | 2017-10-31 | 2019-01-11 | 深圳市大疆创新科技有限公司 | Image processing method, equipment and unmanned plane |
WO2019084825A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳市大疆创新科技有限公司 | Image processing method and device, and unmanned aerial vehicle |
CN108230237B (en) * | 2017-12-15 | 2021-06-04 | 同济大学 | Multispectral image reconstruction method for electrical equipment online detection |
CN108230237A (en) * | 2017-12-15 | 2018-06-29 | 同济大学 | A kind of multispectral image reconstructing method for electrical equipment on-line checking |
CN108061847A (en) * | 2017-12-23 | 2018-05-22 | 华北电力大学(保定) | A kind of dry reactor epoxy resins insulation medium cracking detection method |
CN108932721A (en) * | 2018-06-28 | 2018-12-04 | 上海电力学院 | A kind of infrared Image Segmentation and fusion method for crusing robot |
CN111464800A (en) * | 2019-01-21 | 2020-07-28 | 佳能株式会社 | Image processing apparatus, system, method, and computer-readable storage medium |
CN111464800B (en) * | 2019-01-21 | 2022-05-03 | 佳能株式会社 | Image processing apparatus, system, method, and computer-readable storage medium |
US11361408B2 (en) | 2019-01-21 | 2022-06-14 | Canon Kabushiki Kaisha | Image processing apparatus, system, image processing method, and non-transitory computer-readable storage medium |
CN109978821A (en) * | 2019-02-03 | 2019-07-05 | 湖南工业大学 | A kind of wheel wear monitoring method based on image recognition |
CN113589117A (en) * | 2021-08-16 | 2021-11-02 | 国网江苏省电力有限公司泰州供电分公司 | Power equipment defect detection system and detection method |
CN113589117B (en) * | 2021-08-16 | 2024-05-07 | 国网江苏省电力有限公司泰州供电分公司 | Power equipment defect detection system and detection method |
CN115147468A (en) * | 2022-04-02 | 2022-10-04 | 杭州汇萃智能科技有限公司 | Dual-light image registration method and system and readable storage medium |
CN116563283A (en) * | 2023-07-10 | 2023-08-08 | 山东联兴能源集团有限公司 | Steam boiler gas leakage detection method and detection device based on image processing |
CN116563283B (en) * | 2023-07-10 | 2023-09-08 | 山东联兴能源集团有限公司 | Steam boiler gas leakage detection method and detection device based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107240094A (en) | A kind of visible ray and infrared image reconstructing method for electrical equipment on-line checking | |
CN108230237A (en) | A kind of multispectral image reconstructing method for electrical equipment on-line checking | |
CN108765373A (en) | A kind of insulator exception automatic testing method based on integrated classifier on-line study | |
CN102565625B (en) | Method for intelligently diagnosing thermal defects of high-voltage transmission line based on infrared image | |
CN102508110B (en) | Texture-based insulator fault diagnostic method | |
CN112131936B (en) | Inspection robot image recognition method and inspection robot | |
CN108254077B (en) | GIS thermal fault diagnosis method based on local and global feature information fusion | |
CN107358259B (en) | Covering ice for insulator detection method based on GLOH description son and GVF-Snake model | |
Jiménez-Guarneros et al. | Diagnostic of combined mechanical and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN | |
TW201118804A (en) | Method and system for object detection | |
CN112001327B (en) | Valve hall equipment fault identification method and system | |
CN106950472B (en) | insulator detection method based on infrared and ultraviolet imaging | |
CN102519846B (en) | Hyperspectrum-based composite insulator hydrophobicity detection method | |
CN112200178A (en) | Transformer substation insulator infrared image detection method based on artificial intelligence | |
CN107843818B (en) | High-voltage insulation fault diagnosis method based on heterogeneous image temperature rise and partial discharge characteristics | |
CN109034272A (en) | A kind of transmission line of electricity heat generating components automatic identifying method | |
CN108664997A (en) | High iron catenary equipotential line defective mode detection method based on cascade Faster R-CNN | |
CN112734698A (en) | Cable terminal abnormity diagnosis method and device based on infrared image | |
CN108181560A (en) | A kind of high voltage cable insulation defect Partial Discharge Detection diagnostic method | |
CN109345586A (en) | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology | |
Zhang et al. | Detection and condition assessment of icicle bridging for suspension glass insulator by image analysis | |
CN115239646A (en) | Defect detection method and device for power transmission line, electronic equipment and storage medium | |
CN113221805B (en) | Method and device for acquiring image position of power equipment | |
CN109738452A (en) | A kind of wheel tyre defect intelligent checking system | |
Niu et al. | Electrical equipment identification method with synthetic data using edge-oriented generative adversarial 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171010 |
|
RJ01 | Rejection of invention patent application after publication |