CN107806824A - The detection method and device of contact net geometric parameter under a kind of lower-speed state - Google Patents
The detection method and device of contact net geometric parameter under a kind of lower-speed state Download PDFInfo
- Publication number
- CN107806824A CN107806824A CN201710906716.1A CN201710906716A CN107806824A CN 107806824 A CN107806824 A CN 107806824A CN 201710906716 A CN201710906716 A CN 201710906716A CN 107806824 A CN107806824 A CN 107806824A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- contact
- contact line
- line
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000003384 imaging method Methods 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims description 20
- 230000002146 bilateral effect Effects 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 5
- 230000003068 static effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 8
- 238000000034 method Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000002633 protecting effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G06T5/70—
-
- 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
- G06T7/13—Edge detection
-
- 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
-
- 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
- G06T2207/20024—Filtering details
Abstract
The invention discloses a kind of detection method and device of contact net geometric parameter under lower-speed state, including obtain positioned at the one-dimensional contact net image for positioned at the side of track length direction two being respectively camera lens；Gray proces are carried out to identify contact line in contact net to one-dimensional contact net image, determine the image space of contact line in the picture；Imaging angle of the contact line in corresponding camera lens is determined according to the image space of contact line；The station-keeping data for being located at track according to imaging angle and camera lens determines the geometric parameter of contact net, the one dimensional image gathered by obtaining line-scan camera carries out geometric parameter detection, because the one-dimensional image precision of line-scan camera is high, line sweep speed is fast, detected with tens sampled measurements point per second, low speed Static Detection can be carried out to contact net, the picture of shooting is not in blooming.
Description
Technical field
The present invention relates to Inspection Technology for Overhead Contact System field, more specifically, it relates to which contact net is several under a kind of lower-speed state
The detection method and device of what parameter.
Background technology
Contact net is in electric railway, is set up along rail overhead "the" shape, takes the high pressure of stream defeated for pantograph
Electric wire.Contact net is the main truss of railway electrification project, is that being powered to electric locomotive for downline overhead erection is special
The transmission line of electricity of form.With the continuous expansion of railway traffic transportation network and urban mass transit network scale and increasingly complete
Kind, the contact net maintenance task of railway operation maintenance department related to urban track traffic is also increasingly heavy.
For effectively lifting railway transport capacity and conevying efficiency, railway operation maintenance department must be in the control repair time
The quality and efficiency of upkeep operation are effectively improved simultaneously, and this requires railway operation maintenance department to use more advanced detection technique
With more scientific analysis method, the efficiency of maintenance repair is improved from detection technique, accuracy of detection etc., meets existing line day
The delivery receiving acceptance adapter requirements of one's work of normal maintenance work and newly-built circuit.Existing detection department is typically examined using vehicular
Survey device to detect contact net, the geometric parameter of contact net is measured when detection means is run at high speed with train.
Existing Contact Line Detection device is set for vehicular, and its picture that filming apparatus is discharged in high speed detection can go out
Existing a certain degree of blooming, contact line can be usually lost, and trigger the alarm of mistake.
The content of the invention
The technical problem that technical solution of the present invention solves is that existing Contact Line Detection device is set for vehicular, its
A certain degree of blooming occurs in the picture that filming apparatus is discharged in high speed detection, can usually lose contact line, and touches
Send out the alarm of mistake.
To achieve the above object, technical solution of the present invention provides a kind of detection of contact net geometric parameter under lower-speed state
Method, including：
Obtain positioned at the one-dimensional contact net image for positioned at the side of track length direction two being respectively camera lens；
Gray proces are carried out to identify contact line in contact net to the one-dimensional contact net image, determine contact line in the picture
Image space；
Imaging angle of the contact line in corresponding camera lens is determined according to the image space of contact line；
The station-keeping data for being located at the track according to the imaging angle and the camera lens determines the geometric parameter of contact net.
Further, it is described that contact line in contact net is identified to the one-dimensional contact net image progress gray proces, really
Determining the image space of contact line in the picture includes：
Bilateral filtering is carried out to the image after gray proces；
Soble rim detections are carried out in its dimension to each pixel in the image after gray proces, generate edge image；
The pixel region in edge image is carried out according to default gray threshold filtering determine contact line in the picture into image position
Put.
Further, in addition to：
Obtain the offset image obtained close to the camera lens of fix bar where the contact line；
Gray proces generation biasing gray-scale map is carried out to the offset image, from the fix bar in the biasing gray-scale map
The coordinate for the top of the fix bar, choosing the top and gray value are searched for as the contact line coordinates in bottom upwards
With the reference value of gray value.
Further, gray threshold weighting is set with described with the gray value on the top coordinate in the biasing gray-scale map
After update the gray threshold.
Further, if the coordinate on the top is more than setting coordinate distance with the line coordinates that contacts, mistake is pushed
Prompting.
In order to solve the above-mentioned technical problem, technical solution of the present invention additionally provides contact net geometric parameters under a kind of lower-speed state
Several detection means, including：
Image module is obtained, for obtaining positioned at the one-dimensional contact net figure for positioned at the side of track length direction two being respectively camera lens
Picture；
Identification module, for carrying out gray proces to the one-dimensional contact net image to identify contact line in contact net, it is determined that
The image space of contact line in the picture；
Position module is determined, for determining imaging angle of the contact line in corresponding camera lens according to the image space of contact line；
Parameter module is determined, the station-keeping data for being located at the track according to the imaging angle and the camera lens determines
The geometric parameter of contact net.
Further, the identification module also includes：
Filter unit, for carrying out bilateral filtering to the image after gray proces；
Detection unit, it is raw for carrying out Soble rim detections in its dimension to each pixel in the image after gray proces
Into edge image；
Determining unit, determine that contact line is being schemed for carrying out filtering to the pixel region in edge image according to default gray threshold
Image space as in.
Further, the acquisition image module also includes：
Bias unit is obtained, the offset image that the camera lens for obtaining close to fix bar where the contact line obtains；
Search unit, for carrying out gray proces generation biasing gray-scale map to the offset image, in the biasing gray-scale map
Searched for upwards to the top of the fix bar from the bottom of the fix bar, choose coordinate and the gray value conduct on the top
The reference value of the contact line coordinates and gray value.
Further, the search unit includes：
Subelement is updated, for setting gray threshold with described in the biasing gray-scale map with the gray value on the top coordinate
The gray threshold is updated after weighting.
Further, the search unit also includes：
Subelement is pushed, if for judging that the coordinate on the top is more than setting coordinate distance with the line coordinates that contacts, is pushed away
Send miscue.
The beneficial effect of technical solution of the present invention comprises at least：The one dimensional image gathered by obtaining line-scan camera enters
Row geometric parameter detects, and because the one-dimensional image precision of line-scan camera is high, line sweep speed is fast, with tens per second samplings
Measurement point is detected, and can carry out low speed Static Detection to contact net, the picture of shooting is not in blooming.
The present invention calculates the position of contact line based on binocular principle, improves the recognition accuracy of contact line, reduce due to
The false alarm lost contact line and triggered, and binocular principle is based on, it can also avoid when one camera is shot, due to image
Into aberration lamp reason, and other lines in image are identified as contact line lamp problem by mistake.
The gray-value image that the present invention carries out gray proces to shooting image and generated uses filtering and edge detection algorithm
Afterwards, even if blooming occurs in image, influence of the noise to extraction contact line in image in background can be also filtered out, improves ash
The definition of angle value image.Extraction is connect according to the offset position of the contact line in the camera lens interior biasing image of fix bar
Tactile line position is judged, simultaneously as the smooth degree on contact line surface can change its gray value in video camera, is passed through
The gray value of contact line in offset image is merged to track the contact line gray value of current detection, is connect so as to further improve identification
Touch the accuracy rate of line.
The present invention carries out whole day to contact net using optical touchless detection mode and detected in real time, and testing result is accurate, inspection
Efficiency high is surveyed, is assessed for contact net sound state geometric parameter measurement and provides a kind of reliable technological means, improved power supply and set
The operating efficiency of standby examination and maintenance.
Brief description of the drawings
Fig. 1 is the method flow schematic diagram of the embodiment of the present invention one；
Fig. 2 is the S1 of the embodiment of the present invention one method flow schematic diagram；
Fig. 3 is the S12 of the embodiment of the present invention one method flow schematic diagram；
Fig. 4 is the S2 of the embodiment of the present invention one method flow schematic diagram；
Fig. 5 is the apparatus structure block diagram of the embodiment of the present invention two；
Fig. 6 is the block diagram that the embodiment of the present invention two obtains image module；
Fig. 7 is the block diagram of the identification module of the embodiment of the present invention two and search unit；
Fig. 8 is camera coverage schematic diagram in the embodiment of the present invention one.
Reference：100th, image module is obtained；110th, bias unit is obtained；120th, search unit；121st, renewal is single
Member；122nd, subelement is pushed；200th, identification module；210th, filter unit；220th, detection unit；230th, determining unit；300th, really
Determine position module；400th, parameter module is determined.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Inventor enters to prior art and analysed in depth during the present invention is realized, it is found that it is existing prior art is present
There is the reason for false alarm occurs in the device for detecting contact net to be：Existing Contact Line Detection device is set for vehicular, its
A certain degree of blooming occurs in the picture that filming apparatus is discharged in high speed detection, can usually lose contact line
The defects of based on above-mentioned prior art, technical solution of the present invention provides resolving ideas.
Embodiment one
With reference to the foregoing invention thinking of technical solution of the present invention, the detection method of contact net geometric parameter under a kind of lower-speed state,
As shown in figure 1, comprise the following steps：
Step S1：Obtain positioned at the one-dimensional contact net image for positioned at the side of track length direction two being respectively camera lens.
As shown in figure 8, in concrete condition, high-speed linear CCD cameras can be arranged on and slide hand push in orbit
On dolly, the position of two video cameras is correspondingly arranged at the top of two one steel rails respectively, and is formed and clapped towards shooting above rail
Light curtain is taken the photograph, linear laser light source, the irradiation area of linear laser light source and the shooting area of video camera are additionally provided with by video camera
Overlap, the image that LASER Light Source can shoot video camera becomes apparent from.
As shown in Fig. 2 wherein step S1 also includes step S11 and step S12.
Step S11：Obtain the offset image obtained close to the camera lens of fix bar where contact line.
Contact net includes the contact line for being arranged in multiple fix bars of rail side and being erected in fix bar, fix bar
Erect on the ground.The video camera of close fix bar is directed away from fix bar, also contains containing contact line in its image taken
There is the fix bar with contacting linear contact lay, the now imaging of fix bar is extended to the edge of image by the lateral location of contact line.
Step S12：Gray proces generation biasing gray-scale map is carried out to offset image, from fix bar in gray-scale map is biased
The coordinate for the top of fix bar, choosing top and gray value are searched for as contact line coordinates and the ginseng of gray value in bottom upwards
Examine value.
Because the position of image border where fix bar is constant, thus from image border be the bottom of fix bar into image
Between location finding be fix bar top, and contact line is located at the top of fix bar.
As shown in figure 3, step S12 also includes step S121 and step S122.
Step S121：Gray scale threshold is updated with the gray value on the coordinate of top in biasing gray-scale map and after setting gray threshold weighting
Value.
The gray value of nearest fix bar tip contact line is obtained to update initial gray threshold value, makes gray threshold to contact
The gray value of line carries out real-time tracking, improves the accuracy of the contact line geometric parameter measured.
Step S122：If the coordinate on top is more than setting coordinate distance with contacting line coordinates, miscue is pushed.
Although biased error be present with real position in the contact line coordinate position in offset image, biased error tool
There is setting fluctuation range, if beyond setting fluctuation range, then it represents that contact line coordinates has mistake, it is necessary to alarm.
Return to Fig. 1, step S2：Gray proces are carried out to identify contact line in contact net to one-dimensional contact net image, really
Determine the image space of contact line in the picture.
As shown in figure 4, wherein step S2 also includes step S21, step S22 and step S23.
Step S21：Bilateral filtering is carried out to the image after gray proces.
Bilateral filtering is a kind of nonlinear filtering method, is spatial neighbor degree and pixel value similarity with reference to image
A kind of compromise processing, while consider spatial information (si) and grey similarity, reach the purpose for protecting side denoising.With simple, non-iterative,
The characteristics of local.The benefit of two-sided filter is can to do Edge preservation, general Wiener filtering or gaussian filtering in the past
Remove noise reduction, all can relatively significantly fuzzy edge, for the protecting effect and unobvious of high frequency detail.Two-sided filter is filtered than Gauss
The more Gauss variances of ripple, it is the Gaussian filter function based on spatial distribution, so in adjacent edges, from picture farther out
The pixel value that element will not have influence on edge too much, so ensures that the preservation of adjacent edges pixel value.
Step S22：Soble rim detections are carried out in its dimension to each pixel in the image after gray proces, it is raw
Into edge image.
Sobel algorithms are one of most important operators in whole pixel image rim detection, machine learning, Digital Media,
The science technology information fields such as computer vision play very important effect.Sobel algorithms have two, and one is detection level edge
's；Another is detection vertical edge, only choosing can have horizontal edge or vertical edge in the present embodiment.Sobel algorithms
Another form is isotropism Sobel algorithms, also there is two, and one is detection level edge, and another is that detection is vertical
Edge.Isotropism Sobel algorithms are compared with common Sobel algorithms, and its position weight coefficient is more accurate, in detection not
The amplitude of gradient is consistent during equidirectional edge.All 2 in Sobel the algorithm matrixes are changed to radical sign 2, it is each to same with regard to that can obtain
Property Sobel matrix.Because Sobel algorithms are the forms of filter operator, for extracting edge, fast convolution letter can be utilized
Number, it is easy and effective, therefore be widely used.Only drawback is that Sobel algorithms not by the main body of image and background strictly
Make a distinction, be in other words exactly that Sobel algorithms are not based on gradation of image and handled, because Sobel algorithms are without strictly
The vision physiological feature of people is simulated, so the image outline of extraction is sometimes not satisfactory.But bilateral filtering can will not
Distinguish main body and background in the case of fuzzy edge, therefore bilateral filtering is combined with Sobel algorithms can improve extraction and contact
The accuracy rate of line.
Step S23：Filtering is carried out to the pixel region in edge image according to default gray threshold and determines that contact line is being schemed
Image space as in.
Pixel region is filtered by default gray threshold, further determines that position of the contact line in each video camera.Root
According to illumination, background gray scale and the dynamic state of parameters such as speed adjustment gray threshold is moved, line target and the back of the body will be contacted using gray threshold method
Scape is split.
Return to Fig. 1, step S3：Imaging angle of the contact line in corresponding camera lens is determined according to the image space of contact line.
Step S4：The station-keeping data for being located at track according to imaging angle and camera lens determines the geometric parameter of contact net.
Calculated according to imager coordinate of the contact line of determination in each video camera and stereoscopic model and obtain contact line
Height and lateral attitude.Stereoscopic model in the present embodiment is positioned based on principle of triangulation, samples two shootings
The contact line imager coordinate of machine is locus i.e. height and the lateral attitude that can determine that contact line.Due to the established angle of video camera
The focal length of degree and camera lens is fixed, and can calculate contact line according to image space of the contact line in video camera exists
Imaging angle in left and right video camera.Because the spacing of left and right video camera is fixed, can be counted by trigonometric function publicity
Calculate lateral attitude and the height of contact line relative orbit central point.Above-mentioned trigonometric function formula is that prior art is no longer drawn herein
With.
Technical solution of the present invention carries out geometric parameter detection by obtaining the one dimensional image that line-scan camera gathers, due to
The one-dimensional image precision of line-scan camera is high, and line sweep speed is fast, is detected with tens sampled measurements point per second, can be with
Low speed Static Detection is carried out to contact net, the picture of shooting is not in blooming.
The present invention calculates the position of contact line based on binocular principle, improves the recognition accuracy of contact line, reduce due to
The false alarm lost contact line and triggered, and binocular principle is based on, it can also avoid when one camera is shot, due to image
Into aberration lamp reason, and other lines in image are identified as contact line lamp problem by mistake.
The gray-value image that the present invention carries out gray proces to shooting image and generated uses filtering and edge detection algorithm
Afterwards, even if blooming occurs in image, influence of the noise to extraction contact line in image in background can be also filtered out, improves ash
The definition of angle value image.Extraction is connect according to the offset position of the contact line in the camera lens interior biasing image of fix bar
Tactile line position is judged, simultaneously as the smooth degree on contact line surface can change its gray value in video camera, is passed through
The gray value of contact line in offset image is merged to track the contact line gray value of current detection, is connect so as to further improve identification
Touch the accuracy rate of line.
The present invention carries out whole day to contact net using optical touchless detection mode and detected in real time, and testing result is accurate, inspection
Efficiency high is surveyed, is assessed for contact net sound state geometric parameter measurement and provides a kind of reliable technological means, improved power supply and set
The operating efficiency of standby examination and maintenance.
Embodiment two
With reference to the foregoing invention thinking of technical solution of the present invention, the detection means of contact net geometric parameter under a kind of lower-speed state,
As shown in figure 5, including：
Image module 100 is obtained, for obtaining positioned at the one-dimensional contact net for positioned at the side of track length direction two being respectively camera lens
Image；
As shown in fig. 6, obtaining image module 100 also includes：
Bias unit 110 is obtained, the offset image that the camera lens for obtaining close to fix bar where contact line obtains；
Search unit 120, for carrying out gray proces generation biasing gray-scale map to offset image, from fixation in gray-scale map is biased
To the top of fix bar, the coordinate and gray value for choosing top are used as contact line coordinates and gray value for search upwards for the bottom of bar
Reference value.
As shown in fig. 7, search unit 120 includes：
Update subelement 121, in bias gray-scale map with the gray value on the coordinate of top and set gray threshold weight after more
New gray threshold.
Identification module 200, for carrying out gray proces to one-dimensional contact net image to identify contact line in contact net, really
Determine the image space of contact line in the picture；
Identification module 200 also includes：
Filter unit 210, for carrying out bilateral filtering to the image after gray proces；
Detection unit 220, for carrying out the inspection of Soble edges in its dimension to each pixel in the image after gray proces
Survey, generate edge image；
Determining unit 230, contact line is determined for carrying out filtering to the pixel region in edge image according to default gray threshold
Image space in the picture.
Search unit 120 also includes push subelement 122, if the coordinate that push subelement 122 is used to judge top is with connecing
Touch line coordinates and be more than setting coordinate distance, then push miscue.
Position module 300 is determined, for determining angle of image of the contact line in corresponding camera lens according to the image space of contact line
Degree；
Parameter module 400 is determined, the station-keeping data for being located at track according to imaging angle and camera lens determines contact net
Geometric parameter.
Described above is only the preferred embodiment of the present invention, and protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical schemes belonged under thinking of the present invention belong to protection scope of the present invention.It should be pointed out that for the art
Those of ordinary skill for, some improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (10)
- A kind of 1. detection method of contact net geometric parameter under lower-speed state, it is characterised in that including：Obtain positioned at the one-dimensional contact net image for positioned at the side of track length direction two being respectively camera lens；Gray proces are carried out to identify contact line in contact net to the one-dimensional contact net image, determine contact line in the picture Image space；Imaging angle of the contact line in corresponding camera lens is determined according to the image space of contact line；The station-keeping data for being located at the track according to the imaging angle and the camera lens determines the geometric parameter of contact net.
- 2. detection method according to claim 1, it is characterised in that described that gray scale is carried out to the one-dimensional contact net image Processing identifies contact line in contact net, determines that the image space of contact line in the picture includes：Bilateral filtering is carried out to the image after gray proces；Soble rim detections are carried out in its dimension to each pixel in the image after gray proces, generate edge image；The pixel region in edge image is carried out according to default gray threshold filtering determine contact line in the picture into image position Put.
- 3. detection method according to claim 2, it is characterised in that also include：Obtain the offset image obtained close to the camera lens of fix bar where the contact line；Gray proces generation biasing gray-scale map is carried out to the offset image, from the fix bar in the biasing gray-scale map The coordinate for the top of the fix bar, choosing the top and gray value are searched for as the contact line coordinates in bottom upwards With the reference value of gray value.
- 4. detection method according to claim 3, it is characterised in that also include：The ash is updated with the gray value on the top coordinate and described set after gray threshold weights in the biasing gray-scale map Spend threshold value.
- 5. detection method according to claim 4, it is characterised in that also include：If the coordinate on the top is more than setting coordinate distance with the line coordinates that contacts, miscue is pushed.
- 6. the detection means of contact net geometric parameter under a kind of lower-speed state, including：Obtain image module（100）, for obtaining positioned at the one-dimensional contact for positioned at the side of track length direction two being respectively camera lens Net image；Identification module（200）, for carrying out gray proces to the one-dimensional contact net image to identify contact line in contact net, Determine the image space of contact line in the picture；Determine position module（300）, for determining imaging angle of the contact line in corresponding camera lens according to the image space of contact line；Determine parameter module（400）, for being located at the relative position number of the track according to the imaging angle and the camera lens According to the geometric parameter for determining contact net.
- 7. detection means according to claim 6, it is characterised in that the identification module（200）Also include：Filter unit（210）, for carrying out bilateral filtering to the image after gray proces；Detection unit（220）, for carrying out the inspection of Soble edges in its dimension to each pixel in the image after gray proces Survey, generate edge image；Determining unit（230）, for being carried out filtering determination contact to the pixel region in edge image according to default gray threshold The image space of line in the picture.
- 8. detection means according to claim 7, it is characterised in that the acquisition image module（100）Also include：Obtain bias unit（110）, for obtaining the offset image of the camera lens acquisition close to fix bar where the contact line；Search unit（120）, for carrying out gray proces generation biasing gray-scale map to the offset image, in the biasing gray scale Search for the coordinate and gray value for the top of the fix bar, choosing the top in figure upwards from the bottom of the fix bar As the contact line coordinates and the reference value of gray value.
- 9. detection means according to claim 8, it is characterised in that the search unit（120）Including：Update subelement（121）, for setting ash with described in the biasing gray-scale map with the gray value on the top coordinate The gray threshold is updated after degree threshold value weighting.
- 10. detection means according to claim 9, it is characterised in that the search unit（120）Also include：Push subelement（122）If for judging that the coordinate on the top is more than setting coordinate distance with the line coordinates that contacts, Then push miscue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710906716.1A CN107806824A (en) | 2017-09-29 | 2017-09-29 | The detection method and device of contact net geometric parameter under a kind of lower-speed state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710906716.1A CN107806824A (en) | 2017-09-29 | 2017-09-29 | The detection method and device of contact net geometric parameter under a kind of lower-speed state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107806824A true CN107806824A (en) | 2018-03-16 |
Family
ID=61592039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710906716.1A Pending CN107806824A (en) | 2017-09-29 | 2017-09-29 | The detection method and device of contact net geometric parameter under a kind of lower-speed state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107806824A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636812A (en) * | 2018-12-13 | 2019-04-16 | 银河水滴科技（北京）有限公司 | A kind of Rail Surface and contact net surface image dividing method and device |
| CN112747722A (en) * | 2020-12-30 | 2021-05-04 | 苏州大晚成智能科技有限公司 | Method and device for synchronously shooting and measuring contact lines by four cameras |
| CN115314401A (en) * | 2022-06-30 | 2022-11-08 | 中铁第四勘察设计院集团有限公司 | Contact network state monitoring method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217111A (en) * | 2012-11-28 | 2013-07-24 | 西南交通大学 | Non-contact contact line geometrical parameter detecting method |
| CN104567684A (en) * | 2015-01-20 | 2015-04-29 | 中国铁道科学研究院 | Contact network geometrical parameter detection method and device |
| CN104748685A (en) * | 2015-04-17 | 2015-07-01 | 上海铁路局科学技术研究所 | Dynamic measurement method of geometric parameters of overhead contact system |
| CN105674880A (en) * | 2016-01-25 | 2016-06-15 | 成都国铁电气设备有限公司 | Geometric parameter measuring method and system for overhead lines based on binocular principle |
-
2017
- 2017-09-29 CN CN201710906716.1A patent/CN107806824A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217111A (en) * | 2012-11-28 | 2013-07-24 | 西南交通大学 | Non-contact contact line geometrical parameter detecting method |
| CN104567684A (en) * | 2015-01-20 | 2015-04-29 | 中国铁道科学研究院 | Contact network geometrical parameter detection method and device |
| CN104748685A (en) * | 2015-04-17 | 2015-07-01 | 上海铁路局科学技术研究所 | Dynamic measurement method of geometric parameters of overhead contact system |
| CN105674880A (en) * | 2016-01-25 | 2016-06-15 | 成都国铁电气设备有限公司 | Geometric parameter measuring method and system for overhead lines based on binocular principle |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636812A (en) * | 2018-12-13 | 2019-04-16 | 银河水滴科技（北京）有限公司 | A kind of Rail Surface and contact net surface image dividing method and device |
| CN112747722A (en) * | 2020-12-30 | 2021-05-04 | 苏州大晚成智能科技有限公司 | Method and device for synchronously shooting and measuring contact lines by four cameras |
| CN115314401A (en) * | 2022-06-30 | 2022-11-08 | 中铁第四勘察设计院集团有限公司 | Contact network state monitoring method and device, electronic equipment and storage medium |
| CN115314401B (en) * | 2022-06-30 | 2024-03-15 | 中铁第四勘察设计院集团有限公司 | Contact net state monitoring method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11891261B2 (en) | Device and method for detecting flatness of sheet material | |
| US9251586B2 (en) | Optical overhead wire measurement | |
| CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
| CN106679567A (en) | Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision | |
| CN103808723A (en) | Exhaust gas blackness automatic detection device for diesel vehicles | |
| CN107678036A (en) | A kind of vehicle-mounted contactless contact net geometric parameter dynamic detection system and method | |
| EP2861802B1 (en) | Rolling wheel deflectometer | |
| CN106996748A (en) | A kind of wheel footpath measuring method based on binocular vision | |
| CN108921164B (en) | Contact net locator gradient detection method based on three-dimensional point cloud segmentation | |
| CN104574393A (en) | Three-dimensional pavement crack image generation system and method | |
| CN107806824A (en) | The detection method and device of contact net geometric parameter under a kind of lower-speed state | |
| CN104183133A (en) | Method for acquiring and transmitting road traffic flow dynamic information | |
| CN105426894B (en) | Railway plug pin image detecting method and device | |
| JP2017083245A (en) | Clearance limit determination device | |
| CN103810676A (en) | Method for monitoring running speed of steel pipe | |
| CN206583440U (en) | A kind of projected image sighting distance detecting system | |
| CN110230985A (en) | A kind of sleeper bolt detection device | |
| CN108871226B (en) | Method, device and system for measuring snow depth | |
| CN103646390A (en) | Image processing system and method based on multi-level image positioning | |
| Li et al. | Histogram-Based Road Markings Extraction by Using 3D Laser Imaging | |
| CN206223458U (en) | Vibration detecting system of the rail vehicle based on video analysis in tunnel | |
| CN107449373B (en) | High-speed structured light scanning method and system based on stereoscopic vision | |
| CN113963053A (en) | Method for detecting height of contact net | |
| CN116626706B (en) | Rail transit tunnel intrusion detection method and system | |
| RU2772643C2 (en) | Method for location of points or lines of interest on a railway |
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: 20180316 |
|
| RJ01 | Rejection of invention patent application after publication |