CN106485701A - Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image - Google Patents
Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image Download PDFInfo
- Publication number
- CN106485701A CN106485701A CN201610848561.6A CN201610848561A CN106485701A CN 106485701 A CN106485701 A CN 106485701A CN 201610848561 A CN201610848561 A CN 201610848561A CN 106485701 A CN106485701 A CN 106485701A
- Authority
- CN
- China
- Prior art keywords
- image
- crotch
- detection
- messenger wire
- wire base
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 20
- 239000004020 conductor Substances 0.000 claims abstract description 16
- 230000004807 localization Effects 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims description 23
- 230000008878 coupling Effects 0.000 claims description 20
- 238000010168 coupling process Methods 0.000 claims description 20
- 238000005859 coupling reaction Methods 0.000 claims description 20
- 210000005069 ears Anatomy 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 5
- 230000013011 mating Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 206010041349 Somnolence Diseases 0.000 abstract description 5
- 239000011159 matrix material Substances 0.000 description 16
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000011524 similarity measure Methods 0.000 description 4
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
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
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4084—Scaling of whole images or parts thereof, e.g. expanding or contracting in the transform domain, e.g. fast Fourier transform [FFT] domain scaling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20068—Projection on vertical or horizontal image axis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image, methods described step is as follows:Step one:Input Messenger Wire base original image, is fabricated to matching template after denoising;Step 2:Shoot Messenger Wire base detection image;Step 3:The Messenger Wire base detection image shooting is selected, mates with matching template contrast after denoising, realize the coarse localization of detection image;Step 4:To the detection image that in the 3rd step, the match is successful, first carry out rotation scaling and process, then carry out the normalized of Messenger Wire base, after the completion of process, cutting obtains Messenger Wire base crotch image;Step 5:Detection crotch direction;Step 6:Detect the lateral conductor direction being connected with crotch;Step 7:According to crotch direction and lateral conductor direction, judge that whether anti-loaded Messenger Wire base is.The present invention is safe and reliable, and human cost is few, and detection speed is fast, and detection efficiency is high, and operating cost is low, and night work does not have tired drowsiness phenomenon.
Description
Technical field
The present invention relates to railway contact line detection field, the railway overhead contact system catenary seat specifically referring to based on image is anti-loaded
Whether detection method.
Background technology
At present, the detection of high ferro contact net is checked mainly by scotophase's pole-climbing operation.This method not only for
Operating personnel has higher requirement, and not safe and reliable, checks that speed is slow, efficiency is low.And Messenger Wire base is to relate on contact net
And long-term safety can realize the critical piece of its respective action to contact net, its whether anti-loaded for Messenger Wire base with lateral conductor
Whether stress equalization, and in stress, whether lateral conductor easily comes off is sufficiently reflected.If Messenger Wire base is anti-loaded,
When the factor impact such as being given a shock, lateral conductor easily landing from crotch, causes very big to the operation of High Speed Railway Trains
Potential safety hazard.At present in addition to manual inspection, also there is not correlation technique that the detection of Messenger Wire base is carried out with disclosure.
Content of the invention
The invention provides based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image, the method safety
Reliable, human cost is few, and detection speed is fast, and detection efficiency is high, and operating cost is low, and night work does not have tired drowsiness phenomenon.
The present invention is achieved through the following technical solutions:
Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image, methods described step is as follows:
Step one:Input Messenger Wire base original image, is fabricated to matching template after denoising;
Step 2:Shoot Messenger Wire base detection image;
Step 3:The Messenger Wire base detection image shooting is selected, mates with matching template contrast after denoising, realize
The coarse localization of detection image;
Step 4:To the detection image that in the 3rd step, the match is successful, first carry out rotating scaling process, then carry out Messenger Wire base
Normalized, after the completion of process, cutting obtains Messenger Wire base crotch image;
Step 5:Detection crotch direction;
Step 6:Detect the lateral conductor direction being connected with crotch;
Step 7:According to crotch direction and lateral conductor direction, judge that whether anti-loaded Messenger Wire base is.
The present invention is safe and reliable, and human cost is few, and detection speed is fast, and detection efficiency is high, and operating cost is low, and night work is not
Have tired drowsiness phenomenon.
Further, in described step 5, the concrete detection mode in crotch direction is:Crotch image is carried out gray scale vertical
Projection, obtains the gray value of this image vertical direction, if the vertical gray-level projection superposition value on the left of crotch picture centre is more than the right side
The vertical gray-level projection superposition value of side, then explanation crotch opening direction is on right side;If vertical on the left of contrary crotch picture centre
Gray Projection superposition value is less than the vertical gray-level projection superposition value on right side, then explanation crotch opening direction is in left side.
Further, in described step 6, the concrete detection mode in crotch direction is:By the Line segment detection based on Gauss
Method, detects the edge of above-mentioned Messenger Wire base place crotch image, extracts straight-line segment the longest, and calculates the slope of this line segment
Direction, i.e. the incline direction of lateral conductor.
Further, in described step 7, if crotch direction is identical with lateral conductor direction, Messenger Wire base is anti-loaded, if curved
Hook direction is different from lateral conductor direction, then Messenger Wire base is not anti-loaded.
Further, in described step 3, the feature that coupling is chosen is the rotation ears of Messenger Wire base, can obtain after coupling
To anglec of rotation ModelAngle of this detection image, zoom factor ModelScale, coupling fraction ModelScore and rotation
The center ranks coordinate of ears, when coupling fraction ModelScore is more than the coupling fraction threshold values thresholdScore setting
When, represent that the match is successful and realizes coarse positioning, on the contrary unsuccessful.Mating concrete mode is:
Off-line phase:Choose the shooting quality preferably image containing Messenger Wire base, select rotation ears region, use
Canny filter process two image, and calculate the direction vector of region inner margin point;Meanwhile, calculate in an identical manner
The direction vector of the ears region inner margin point of matching template.
On-line stage:Using image pyramid hierarchical search strategy.Enter in image pyramid top traversal search first
Row similarity measurements are flux matched, if To Template pixel is pi=(ri,ci)T, corresponding direction vector is di=(ti,ui)T, i=
1,2 ..., n, direction vector is calculated after being filtered by Canny, and search image also calculates each using after Canny filtering
The direction vector e of point (r, c)r,c=(vr,c,wr,c)T, template is carried out affine transformation, and the translating sections of affine change is divided
From the template point after conversion is p 'i=Api, corresponding direction vector is d 'i=Adi, A is second order standard spin matrix.Searching
Rope image certain specified point q=(r, c)TPlace, template is mated with search image, calculate convert in rear pattern plate returning a little
The summation of one dot product of normalization direction vector changing direction vector and search image corresponding position, and in this, as coupling score value,
I.e. in the similarity measure of q point, the computing formula of similarity measure is the template after conversion:
And return potential match point center ranks coordinate, coupling score value ModelScore and running parameter ModelScale,
ModelAngle.
It is characterized in that, described coupling score threshold ThresholdScore=smin=0.5.
Described support positioner image is carried out by the way of transformation matrix by space field transformation according to template image;Institute
Stating transformation matrix HomMat2DGlobal is:
HomMat2DGlobal=HomMat2DScale*HomMat2DRotat
Wherein, HomMat2DScale represents scale transformation matrix, and HomMat2DRotate represents rotational transformation matrix;
Described translation transformation matrix calculation is:
Described scale transformation matrix H omMat2DScale is:
Wherein, ModelScale represents the zoom factor supporting positioner image with respect to template image;
Described rotational transformation matrix HomMat2DRotate is:
Wherein, when phi represents image normalization to be matched, support the anglec of rotation that positioner image is with respect to template image
Degree, i.e. phi=ModelAngle.
Further, the cutting in described step 4 includes two steps, first cuts out fixed ruler using fixing rectangular area
Very little Messenger Wire base image, after being specifically normalized detection image, centered on the ranks coordinate of center, left and right is each
Extend 160 pixels, extend 400 pixels up and down, obtain the Messenger Wire base image that size is 320*800;Further according to coordinate points
Carry out the cutting of Messenger Wire base image, obtain crotch image, after being specifically normalized Messenger Wire base image, along a left side
Upper coordinate points are (82,469), and lower right coordinate point carries out cutting for (219,587).
Further, in described step 3, after the Messenger Wire base detection image shooting is selected, this image is carried out
Enhancement process, enhancement method is linear transformation.It is implemented as:
G '=g × Mult+Add
Mult=255/ (GMax-GMin)
Add=Mult × GMin
Wherein, g is the gray value of pixel in image before enhancement process, and g ' is result images gray value after enhancement process;
Mult is linear transform coefficient, and Add is linear transformation increment, GMax and GMin represents the maximum in image before enhancement process respectively
Gray value and minimum gradation value.
Further, the detection image in described step 2 adopts noncontact camera imaging.Can by camera be contained in for
Shot on the train of detection, it would however also be possible to employ additive method is shot, with imaging clearly, shooting speed is fast, saves into
This is selected for standard.
The present invention compared with prior art, have the advantage that for:
(1) present invention is safe and reliable, and human cost is few, and detection speed is fast, and detection efficiency is high, and operating cost is low, and night is made
Industry does not have tired drowsiness phenomenon.
(2) image processing process of the present invention can use computer disposal, and intelligence degree is high.
Specific embodiment
With reference to embodiment, the present invention is described in further detail, but embodiments of the present invention not limited to this.
Embodiment 1:
Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image it is characterised in that:Methods described walks
Suddenly as follows:
Step one:Input Messenger Wire base original image, is fabricated to matching template after denoising;
Step 2:Shoot Messenger Wire base detection image;
Step 3:The Messenger Wire base detection image shooting is selected, mates with matching template contrast after denoising, realize
The coarse localization of detection image;
Step 4:To the detection image that in the 3rd step, the match is successful, first carry out rotating scaling process, then carry out Messenger Wire base
Normalized, after the completion of process, cutting obtains Messenger Wire base crotch image;
Step 5:Detection crotch direction;
Step 6:Detect the lateral conductor direction being connected with crotch;
Step 7:According to crotch direction and lateral conductor direction, judge that whether anti-loaded Messenger Wire base is.
The present invention is safe and reliable, and human cost is few, and detection speed is fast, and detection efficiency is high, and operating cost is low, and night work is not
Have tired drowsiness phenomenon.
Embodiment 2:
The present embodiment is further improved on the basis of embodiment 1, the concrete detection in crotch direction in described step 5
Mode is:Crotch image is carried out gray scale vertical projection, obtains the gray value of this image vertical direction, if crotch picture centre is left
The superposition value of the vertical gray-level projection of side is more than the projection superposition value of the vertical gray scale on right side, then explanation crotch opening direction is on the right side
Side;If the vertical gray-level projection superposition value on the left of contrary crotch picture centre is less than the vertical gray-level projection superposition value on right side,
Illustrate crotch opening direction in left side.
In described step 6, the concrete detection mode in crotch direction is:By the line segment detecting method based on Gauss, detect
The edge of above-mentioned Messenger Wire base place crotch image, extraction straight-line segment the longest, and calculate the slope direction of this line segment, that is, tiltedly
The incline direction of bracing wire.
In described step 7, if crotch direction is identical with lateral conductor direction, Messenger Wire base is anti-loaded, if crotch direction with tiltedly
Stayguy direction is different, then Messenger Wire base is not anti-loaded.
In described step 3, the feature that coupling is chosen is the rotation ears of Messenger Wire base, can obtain this detection after coupling
In anglec of rotation ModelAngle of image, zoom factor ModelScale, coupling fraction ModelScore and rotation ears
Heart ranks coordinate, when mating the coupling fraction threshold values thresholdScore that fraction ModelScore is more than setting, expression
It is made into work(and realize coarse positioning, on the contrary unsuccessful.Mating concrete mode is:
Off-line phase:Choose the shooting quality preferably image containing Messenger Wire base, select rotation ears region, use
Canny filter process two image, and calculate the direction vector of region inner margin point;Meanwhile, calculate in an identical manner
The direction vector of the ears region inner margin point of matching template.
On-line stage:Using image pyramid hierarchical search strategy.Enter in image pyramid top traversal search first
Row similarity measurements are flux matched, if To Template pixel is pi=(ri,ci)T, corresponding direction vector is di=(ti,ui)T, i=
1,2 ..., n, direction vector is calculated after being filtered by Canny, and search image also calculates each using after Canny filtering
The direction vector e of point (r, c)r,c=(vr,c,wr,c)T, template is carried out affine transformation, and the translating sections of affine change is divided
From the template point after conversion is p 'i=Api, corresponding direction vector is d 'i=Adi, A is second order standard spin matrix.Searching
Rope image certain specified point q=(r, c)TPlace, template is mated with search image, calculate convert in rear pattern plate returning a little
The summation of one dot product of normalization direction vector changing direction vector and search image corresponding position, and in this, as coupling score value,
I.e. in the similarity measure of q point, the computing formula of similarity measure is the template after conversion:
And return potential match point center ranks coordinate, coupling score value ModelScore and running parameter ModelScale,
ModelAngle.
It is characterized in that, described coupling score threshold ThresholdScore=smin=0.5.
Described support positioner image is carried out by the way of transformation matrix by space field transformation according to template image;Institute
Stating transformation matrix HomMat2DGlobal is:
HomMat2DGlobal=HomMat2DScale*HomMat2DRotat
Wherein, HomMat2DScale represents scale transformation matrix, and HomMat2DRotate represents rotational transformation matrix;
Described translation transformation matrix calculation is:
Described scale transformation matrix H omMat2DScale is:
Wherein, ModelScale represents the zoom factor supporting positioner image with respect to template image;
Described rotational transformation matrix HomMat2DRotate is:
Wherein, when phi represents image normalization to be matched, support the anglec of rotation that positioner image is with respect to template image
Degree, i.e. phi=ModelAngle.
Cutting in described step 4 includes two steps, first cuts out the carrier cable of fixed dimension using fixing rectangular area
Seat image, after being specifically normalized detection image, centered on the ranks coordinate of center, left and right respectively extends 160
Pixel, extends 400 pixels up and down, obtains the Messenger Wire base image that size is 320*800;Carry out carrier cable further according to coordinate points
The cutting of seat image, obtains crotch image, after being specifically normalized Messenger Wire base image, along top-left coordinates point is
(82,469), lower right coordinate point carries out cutting for (219,587).
In described step 3, after the Messenger Wire base detection image shooting is selected, enhancement process is carried out to this image,
Enhancement method is linear transformation.It is implemented as:
G '=g × Mult+Add
Mult=255/ (GMax-GMin)
Add=Mult × GMin
Wherein, g is the gray value of pixel in image before enhancement process, and g ' is result images gray value after enhancement process;
Mult is linear transform coefficient, and Add is linear transformation increment, GMax and GMin represents the maximum in image before enhancement process respectively
Gray value and minimum gradation value.
Detection image in described step 2 adopts noncontact camera imaging.Camera can be contained in the train for detection
On shot, it would however also be possible to employ additive method is shot, and with imaging clearly, shooting speed is fast, cost-effective enters for standard
Row selects.
The other parts of the present embodiment are same as Example 1, repeat no more.
The above, be only presently preferred embodiments of the present invention, and not the present invention is done with any pro forma restriction, every according to
Any simple modification above example made according to the technical spirit of the present invention, equivalent variations, each fall within the protection of the present invention
Within the scope of.
Claims (8)
1. based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image it is characterised in that:Methods described step
As follows:
Step one:Input Messenger Wire base original image, is fabricated to matching template after denoising;
Step 2:Shoot Messenger Wire base detection image;
Step 3:The Messenger Wire base detection image shooting is selected, mates with matching template contrast after denoising, realize detection
The coarse localization of image;
Step 4:To the detection image that in the 3rd step, the match is successful, first carry out rotating scaling process, then carry out returning of Messenger Wire base
One change is processed, and after the completion of process, cutting obtains Messenger Wire base crotch image;
Step 5:Detection crotch direction;
Step 6:Detect the lateral conductor direction being connected with crotch;
Step 7:According to crotch direction and lateral conductor direction, judge that whether anti-loaded Messenger Wire base is.
2. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 1, it is special
Levy and be:In described step 5, the concrete detection mode in crotch direction is:Crotch image is carried out gray scale vertical projection, is somebody's turn to do
The gray value of image vertical direction, if the vertical gray-level projection superposition value on the left of crotch picture centre is more than the vertical gray scale on right side
Projection superposition value, then explanation crotch opening direction is on right side;If the vertical gray-level projection superposition on the left of contrary crotch picture centre
Less than the vertical gray-level projection superposition value on right side, then explanation crotch opening direction is in left side for value.
3. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 1 and 2, its
It is characterised by:In described step 6, the concrete detection mode in crotch direction is:By the line segment detecting method based on Gauss, detect
The edge of above-mentioned Messenger Wire base place crotch image, extraction straight-line segment the longest, and calculate the slope direction of this line segment, that is, tiltedly
The incline direction of bracing wire.
4. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 3, it is special
Levy and be:In described step 7, if crotch direction is identical with lateral conductor direction, Messenger Wire base is anti-loaded, if crotch direction with tiltedly
Stayguy direction is different, then Messenger Wire base is not anti-loaded.
5. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 1, it is special
Levy and be:In described step 3, the feature that coupling is chosen is the rotation ears of Messenger Wire base, can obtain this detection figure after coupling
The center of anglec of rotation ModelAngle of picture, zoom factor ModelScale, coupling fraction ModelScore and rotation ears
Ranks coordinate, when mating the coupling fraction threshold values thresholdScore that fraction ModelScore is more than setting, represents coupling
Success simultaneously realizes coarse positioning, otherwise unsuccessful.
6. according to claim 1 or 5 based on the detection method that whether anti-loaded the railway overhead contact system catenary seat of image is, its
It is characterised by:Cutting in described step 4 includes two steps, first cuts out the load of fixed dimension using fixing rectangular area
Rope seat image, carries out the cutting of Messenger Wire base image further according to coordinate points, obtains crotch image.
7. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 1, it is special
Levy and be:In described step 3, after the Messenger Wire base detection image shooting is selected, enhancement process is carried out to this image,
Enhancement method is linear transformation.
8. the detection method whether anti-loaded based on the railway overhead contact system catenary seat of image according to claim 1, it is special
Levy and be:Detection image in described step 2 adopts noncontact camera imaging.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610848561.6A CN106485701B (en) | 2016-09-26 | 2016-09-26 | Detection method whether railway overhead contact system catenary seat based on image is anti-loaded |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610848561.6A CN106485701B (en) | 2016-09-26 | 2016-09-26 | Detection method whether railway overhead contact system catenary seat based on image is anti-loaded |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106485701A true CN106485701A (en) | 2017-03-08 |
CN106485701B CN106485701B (en) | 2019-03-22 |
Family
ID=58267509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610848561.6A Active CN106485701B (en) | 2016-09-26 | 2016-09-26 | Detection method whether railway overhead contact system catenary seat based on image is anti-loaded |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106485701B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109101982A (en) * | 2018-07-26 | 2018-12-28 | 珠海格力智能装备有限公司 | Target object identification method and device |
CN111462045A (en) * | 2020-03-06 | 2020-07-28 | 西南交通大学 | Method for detecting defects of catenary support assembly |
CN112733831A (en) * | 2021-01-08 | 2021-04-30 | 南昌航空大学 | Trademark detection method and system |
CN112907596A (en) * | 2021-05-06 | 2021-06-04 | 荣旗工业科技(苏州)股份有限公司 | Coil turn number online measurement method based on image processing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102980896A (en) * | 2012-11-28 | 2013-03-20 | 西南交通大学 | Method for detecting breakage of lugs of high-speed rail contact net suspension device |
CN103310438A (en) * | 2013-04-16 | 2013-09-18 | 西南交通大学 | Overhead contact system rod insulator fault detection method based on Harris corners and image difference |
CN104318582A (en) * | 2014-11-14 | 2015-01-28 | 西南交通大学 | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning |
CN104794720A (en) * | 2015-05-04 | 2015-07-22 | 成都唐源电气有限责任公司 | Method and system for positioning steady ears in catenary images |
-
2016
- 2016-09-26 CN CN201610848561.6A patent/CN106485701B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102980896A (en) * | 2012-11-28 | 2013-03-20 | 西南交通大学 | Method for detecting breakage of lugs of high-speed rail contact net suspension device |
CN103310438A (en) * | 2013-04-16 | 2013-09-18 | 西南交通大学 | Overhead contact system rod insulator fault detection method based on Harris corners and image difference |
CN104318582A (en) * | 2014-11-14 | 2015-01-28 | 西南交通大学 | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning |
CN104794720A (en) * | 2015-05-04 | 2015-07-22 | 成都唐源电气有限责任公司 | Method and system for positioning steady ears in catenary images |
Non-Patent Citations (2)
Title |
---|
ZHANG G 等: "Automatic recognition for catenary insulators of high-speed railway based on contourlet transform and Chan–Vese model", 《OPTIK - INTERNATIONAL JOURNAL FOR LIGHT AND ELECTRON OPTICS》 * |
杨红梅: "基于图像处理的接触网支持及悬挂装置不良状态检测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109101982A (en) * | 2018-07-26 | 2018-12-28 | 珠海格力智能装备有限公司 | Target object identification method and device |
CN109101982B (en) * | 2018-07-26 | 2022-02-25 | 珠海格力智能装备有限公司 | Target object identification method and device |
CN111462045A (en) * | 2020-03-06 | 2020-07-28 | 西南交通大学 | Method for detecting defects of catenary support assembly |
CN111462045B (en) * | 2020-03-06 | 2022-07-01 | 西南交通大学 | Method for detecting defects of catenary support assembly |
CN112733831A (en) * | 2021-01-08 | 2021-04-30 | 南昌航空大学 | Trademark detection method and system |
CN112733831B (en) * | 2021-01-08 | 2022-04-15 | 南昌航空大学 | Trademark detection method and system |
CN112907596A (en) * | 2021-05-06 | 2021-06-04 | 荣旗工业科技(苏州)股份有限公司 | Coil turn number online measurement method based on image processing |
Also Published As
Publication number | Publication date |
---|---|
CN106485701B (en) | 2019-03-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | High speed automatic power line detection and tracking for a UAV-based inspection | |
CN106504238A (en) | Railway contact line defect inspection method based on image procossing and convolutional neural networks | |
CN106485701A (en) | Based on the whether anti-loaded detection method of the railway overhead contact system catenary seat of image | |
US8300949B2 (en) | Edge detection technique having improved feature visibility | |
CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
Dreschler et al. | On the selection of critical points and local curvature extrema of region boundaries for interframe matching | |
CN109493313B (en) | Vision-based steel coil positioning method and equipment | |
CN104794720A (en) | Method and system for positioning steady ears in catenary images | |
CN106682641A (en) | Pedestrian identification method based on image with FHOG- LBPH feature | |
CN106934353B (en) | Face recognition and active tracking method for endowment robot | |
CN108275530A (en) | A kind of elevator safety method for early warning based on machine learning | |
CN104778710A (en) | Morphological image edge detecting method based on quantum theory | |
Zhang et al. | Edge detection based on improved sobel operator | |
Kortli et al. | Efficient implementation of a real-time lane departure warning system | |
CN111652953B (en) | Security image artifact removing method utilizing region search and pixel value suppression | |
CN107133600A (en) | A kind of real-time lane line detection method based on intra-frame trunk | |
Premachandra et al. | Image based automatic road surface crack detection for achieving smooth driving on deformed roads | |
CN104156946B (en) | Obstacle detection method for space tether robot in capturing area | |
CN107392127B (en) | Transmission line of electricity extracting method based on Chebyshev polynomials description | |
Ma et al. | A real time detection method of track fasteners missing of railway based on machine vision | |
CN103632378B (en) | A kind of multi thresholds edge detection method of game thought of drawing based on even point | |
CN110598521A (en) | Behavior and physiological state identification method based on intelligent analysis of face image | |
Jiang et al. | Fusion of texture features and color information of the license plate location algorithm | |
CN114596307A (en) | Method for measuring length of hanger of railway contact net based on unmanned aerial vehicle and machine vision | |
CN113537015A (en) | Method for identifying rail scratches, method for routing inspection and related device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |