CN105472355A - Switch machine notch monitoring system and method based on binocular visual processing identification - Google Patents
Switch machine notch monitoring system and method based on binocular visual processing identification Download PDFInfo
- Publication number
- CN105472355A CN105472355A CN201610021854.7A CN201610021854A CN105472355A CN 105472355 A CN105472355 A CN 105472355A CN 201610021854 A CN201610021854 A CN 201610021854A CN 105472355 A CN105472355 A CN 105472355A
- Authority
- CN
- China
- Prior art keywords
- image
- notch
- subsystem
- optical fiber
- switch machine
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 title claims abstract description 21
- 230000000007 visual effect Effects 0.000 title abstract description 6
- 230000005540 biological transmission Effects 0.000 claims abstract description 33
- 239000000835 fiber Substances 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 239000013307 optical fiber Substances 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 17
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000013523 data management Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 238000012552 review Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract 1
- 241000283707 Capra Species 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 101150012579 ADSL gene Proteins 0.000 description 1
- 102100020775 Adenylosuccinate lyase Human genes 0.000 description 1
- 108700040193 Adenylosuccinate lyases Proteins 0.000 description 1
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 241001212149 Cathetus Species 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning, or like safety means along the route or between vehicles or vehicle trains
- B61L23/04—Control, warning, or like safety means along the route or between vehicles or vehicle trains for monitoring the mechanical state of the route
-
- 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
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
Abstract
The invention provides a switch machine notch monitoring system and method based on binocular visual processing identification, relating to the switch machine notch monitoring field. The detection system comprises an on-site binocular collection subsystem, a CAN bus fiber transmission subsystem and a monitoring subsystem. The binocular collection subsystem collects notch images, and transmits the images to the monitoring subsystem through the CAN bus fiber transmission subsystem; the monitoring subsystem performs visual processing, and employs a gauss filter to perform smooth filtering de-noising processing; a Canny edge detector extracts notch edge information, performs Hough transformation on edge images to detect line segments, and identifies line segment information in the images. Through a series of constraint conditions, effective line segments on the top left side of notch edges are screened, reference mark and real marking line segment coordinates are recorded, and notch offsets on the images are calculated according to image geometrical distances. According to proportions, real notch offsets are calculated. A left image and a right image are both processed according to the processing flow, thereby improving calculating accuracy.
Description
Technical field
The present invention relates to a kind of notch of switch machine monitoring system and method, belong to track switch control field in track traffic, specifically a kind of notch of switch machine monitoring system based on binocular vision processing and identification and method.
Background technology
The safety and stability monitoring of actuator's goat of switch control system plays an important role for the safe operation of train in track traffic industry.Notch state Monitoring Data (image and video) analyzes the important references of goat running status.
Traditional notch of switch machine monitoring method is divided into directly to be measured and the large class of indirect inspection two.The transducer of direct metering system is arranged on clearance gaps, and its output can directly reflect measured gap size, but installs complicated.Indirect measure is easily installed, but needs carefully to adjust reference position.There are the following problems for existing goat monitoring system: one when being the electromagnetic measurement adopted in existing system, and the impact by temperature and electromagnetism is comparatively large, and some system can only reflect notch state qualitatively, can not carry out quantitative analysis to breach; Some system also needs to provide different transducers to different goats.Two is that existing notch of switch machine monitoring system and monitoring principle are various, incompatible between various method, this provides for improved the operation of system and the difficulty of upgrading and cost.Three is that existing monitoring system many employings ADSL transmits, and brings larger delay to the real-time high-definition transmission of image and video.
Summary of the invention
In order to solve problems of the prior art, the invention provides a kind of notch of switch machine monitoring system based on binocular vision processing and identification and Optical Fiber Transmission and method, this method is less to on-the-spot goat transformation, integrated circuit control card with binocular high-definition camera only need be installed, processing and identification task be given operational capability powerful Surveillance center.This monitoring system and method can improve the compatibility of system and the accuracy rate of monitoring effectively.
The object of the invention is to, there is provided a kind of scope of application wide, system compatibility is good, the notch of switch machine monitoring system that monitoring accuracy is high and method, view data only need be transferred to by optical fiber technology gap edge and the breach side-play amount that Surveillance center can draw any moment by this system and method.This system and method can also carry out independent upgrading and maintenance, does not need the structure changing on-the-spot goat.
The object of the present invention is achieved like this: the notch of switch machine monitoring system based on binocular vision processing and identification and Optical Fiber Transmission comprises on-the-spot binocular acquisition subsystem, CAN optical fiber transmission subsystem, Monitor And Control Subsystem.
Described binocular acquisition subsystem comprises high-definition camera, integrated circuit control card, described integrated circuit control card controls high-definition camera, and described integrated circuit control card module integration has image compression encoding chip, video streaming chip, signal conversion chip, the real-time gap image collected by high-definition camera carries out preliminary treatment by integrated circuit control card, coding, compression.
Described CAN optical fiber transmission subsystem comprises: CAN and Transmission Fibers, and the fan-out of integrated circuit control card is always reportedly delivered to Transmission Fibers by described CAN, and data are sent to Monitor And Control Subsystem by Transmission Fibers.
Described Monitor And Control Subsystem comprises: application host and database server, and image and video data are stored in mass storage by Surveillance center, and original image and video is presented on monitor screen.Described application host can carry out Canny rim detection, Hough transform, constraints algorithm data analysis and treament, and database server carries out data management.To comprise the left figure of video camera of jagged information and right figure carry out gray processing process, smoothed image, remove noisy operation.Then use Canny edge detector to carry out rim detection to image, subsequently Hough transform is carried out to image and carry out Line segment detection, identify the segment data extracted in image.Then, identifying processing line segment is out screened, adjudicates, sort operation, finally identify the line segment representing breach left hand edge accurately.Finally, according to breach calculations of offset principle, passing ratio calculates notch of switch machine side-play amount in reality.
Above-mentioned monitoring implementation procedure is suitable for left image and right image simultaneously, and according to the breach side-play amount that left and right image calculates respectively, the value that is averaged processes, and obtains the statistic of breach side-play amount.
Preferably, described high-definition camera is specially binocular high-definition camera, gathers left figure and right figure respectively.
Preferably, it is characterized in that, described integrated circuit control card is specially ARM chip integrated circuit control card.
Preferably, integrated memory cell in described integrated circuit control card.By the data buffer storage that collects in memory cell, finally data can be transferred to Monitor And Control Subsystem to store.
Preferably, described Transmission Fibers comprises optical fiber controller, optical fiber group, and described optical fiber group comprises 100,000,000 optical fiber, optical fiber switch, kilomega optic fiber., described optical fiber controller is used for pilot signal in the transmission of fiber segment, comprises fiber optic switching module and transceiver for digitized signal being converted to light signal and logical in optical fiber controller.
Described Canny edge detector carries out rim detection principle to image: it is level and smooth that image uses the Gaussian filter with specified value deviations, thus can reduce noise.Calculate partial gradient and edge direction at each pixel place, formula is as follows:
Marginal point is defined as the point that on gradient direction, its intensity local is maximum.The marginal point determined can cause occurring ridge in gradient amplitude image.Then, algorithm follows the trail of the top of all ridges, is not allly set to 0 in the pixel at the top of ridge, to provide one day fine rule in the output.Ridge pixel uses two threshold value T1 and T2 to do threshold process, wherein T1 < T2.The ridge pixel that value is greater than T2 is called strong edge pixel, and the ridge pixel between T1 and T2 is called weak edge pixel.Finally, algorithm is integrated into strong pixel by the weak pixel connected 8, performs edge link.
The principle that described Hough transform carries out line detection is: the edge breaks that image pixel causes due to noise, non-uniform illumination and spuious brightness discontinuous and be difficult to obtain local edge completely.Hough transform is used to find and the method for concatenated image middle conductor.In plane right-angle coordinate xy, straight line can use equation
y=kx+b
Represent.For the point (x that on straight line, is determined
0, y
0), have
y
0=kx
0+b
This represents the straight line in parameter plane (k-b).Therefore, the straight line in the corresponding parameter plane of a point in image, a point in the corresponding parameter plane of the straight line in image.Hough transformation is done to points all on image, the line correspondences that finally will detect must be that parameter plane cathetus intersects that maximum points.So just detected straight line in the picture.In actual applications, straight line adopts parametric equation to be usually:
ρ=xcosθ+ysinθ
Method of attachment based on Hough transform is:
The gradient of computed image also arranges thresholding to it, obtains a width bianry image.Determine to segment again in ρ θ plane.The number of its accumulator element is checked in the place of concentrating pixels tall.Relation in the unit that inspection is selected between pixel.
Described breach calculations of offset principle and ratio formula principle are:
Wherein, M is the developed width of benchmark image, and L is breach real offset, and M ' is the width of reference mark on image, and L ' is the side-play amount of breach on image.
Based on the notch of switch machine monitoring system of binocular vision processing and identification and Optical Fiber Transmission, described goat supervisory control system comprises data acquisition module, signal conversion module, fiber optic switching module and transceiver, and Surveillance center.Wherein data acquisition module comprises binocular high-definition camera head unit, image compression unit, video streaming unit etc.; The task that data acquisition unit completes comprises the collecting work of data, and the compression coding work of data, the terminal transmission of data is to signal conversion unit.Signal conversion unit is used for the Digitization of data.Fiber optic switching module and transceiver is comprised, for digitized signal being converted to light signal and being transmitted through the fiber to Surveillance center in Transmission Fibers.Surveillance center is used for the work such as image display, image procossing, image recognition, data modeling, the evaluation of notch of switch machine health status.
Another object of the present invention, provides a kind of monitoring method of the notch of switch machine monitoring system based on binocular vision process and Optical Fiber Transmission, comprises the steps:
S1. integrated circuit control card control high-definition camera carries out data acquisition, and the real-time gap image collected by high-definition camera carries out preliminary treatment, coding, compression by integrated circuit control card;
S2. data-signal is transferred data to Monitor And Control Subsystem by CAN and Transmission Fibers;
S3. image and video data are stored in mass storage by Monitor And Control Subsystem, and are presented on monitor screen by original image and video;
S4. to comprise the camera review of jagged information carry out gray processing process, smoothed image, remove noisy operation;
S5. use Canny edge detector to carry out rim detection to image, subsequently Hough transform is carried out to image and carry out Line segment detection, identify the segment data extracted in image;
S6. identifying processing line segment out screened, adjudicate, sort operation, finally identify the line segment representing breach left hand edge accurately.
S7. according to breach calculations of offset principle, passing ratio calculates notch of switch machine side-play amount in reality.
Preferably, described monitoring implementation procedure is suitable for left image and right image simultaneously, and according to the breach side-play amount that left and right image calculates respectively, the value that is averaged processes, and obtains the statistic of breach side-play amount.
Beneficial effect of the present invention comprises:
(1) the notch of switch machine image measured data adopting binocular high-definition camera to collect, solves the complexity problem that traditional monitoring system needs to install various types of transducer.
(2) adopt the method for binocular camera and visual processes, can fully analyze breach information, solve the inaccurate problem of sensor measurement, improve compatibility and the retractility of whole system, simplify the engineering construction difficulty of goat part.
(3) technical difficulty is placed on the powerful Surveillance center of computing ability, alleviates resource anxiety and the development difficulty of embedded end.Utilize the technology such as image vision, enhance technology gold content, reduce maintenance cost.
(4) adopt CANoverFiber technical transmission data, can real-time Transmission high-definition image and video flowing, there is built-in industrial and control the reliable and stable advantage of CAN, have again optical fiber with a large bandwidth and at a high rate, jamproof advantage.
Accompanying drawing explanation
Fig. 1 is system architecture diagram of the present invention;
Fig. 2 is visual processes identification workflow diagram of the present invention;
Fig. 3 is the image after image of the present invention display, process, identification; Figure a is gray level image; Figure b is the postrun image of Canny edge detector; Figure c is the image after Hough transform; Figure d is the image that finally obtains after judgement, classification.
Embodiment
Below in conjunction with accompanying drawing and instantiation, the present invention is elaborated.
Shown in composition graphs 1, the overall architecture of notch of switch machine monitoring system is divided into the large subsystem of on-the-spot goat part, CAN fibre transmission portions, Surveillance center's part 3.At the scene in goat part, system needs to install binocular high-definition camera, by the gap position of the alignment lens track of video camera, two the camera symmetries in left and right are put, camera is connected to integrated circuit control card by USB interface, integrated circuit control card based on ARM and Linux platform, to camera collection to data encode, store, the operation such as compression.In Surveillance center, run the system of image vision processing and identification, this system process images video data, through a series of computing, notch of switch machine image and identifying information are shown on monitor.Being in the middle of two subsystems is above CAN fibre transmission portions, mainly adopts CANoverFiber transmission technology, and optical fiber is symmetric bandwidth transmission medium, and lateral fiber 100Mbps rises, and trunk fiber 1Gbps rises.Optical fiber is good economy performance (25km rises) in medium and long distance transmission.Can real-time video transmission and various data, control signal capacity is large, antijamming capability is strong.Widely use in new industrial system, also can the original CAN system of compatible upgrading.
Shown in composition graphs 2, the display of this visual processes identification workflow diagram be the core technology flow process of Surveillance center.First to comprise the left figure of video camera of jagged information and right figure carry out gray processing process, smoothed image, remove noisy operation.Then use Canny edge detector to carry out rim detection to image, subsequently Hough transform is carried out to image and carry out Line segment detection, identify the segment data extracted in image.Then, identifying processing line segment is out screened, adjudicates, sort operation, finally identify the line segment representing breach left hand edge accurately.Finally, according to breach calculations of offset principle, passing ratio calculates notch of switch machine side-play amount in reality.Above-mentioned monitoring implementation procedure is suitable for left image and right image simultaneously, and according to the breach side-play amount that left and right image calculates respectively, the value that is averaged processes, and obtains the statistic of breach side-play amount.
Shown in composition graphs 3, first width figure a is original gap image, two rectangular color lumps up and down in image are reference mark and actual breach respectively, through gray processing process, filtering, remove noise, the second width image b is obtained after using the operations such as Canny edge detector, line detection is carried out through Hough transform, and obtain the 3rd width image c with marking line segment effectively, preferably mark with colored line segment, such as red line marks, finally, through a series of screening, judgement, the operations such as classification, final line segment marks the sideline, left and right of two rectangular-shaped color lumps, as shown in the 4th width image d, preferably mark with colored line segment, such as blue line marks, these four lines are four line segments most effectively, accurately can be gone out both horizontal offsets by mathematical computations by these four line segments.
Claims (10)
1., based on a notch of switch machine monitoring system for binocular vision identification and Optical Fiber Transmission, it is characterized in that, described detection system comprises on-the-spot binocular acquisition subsystem, CAN optical fiber transmission subsystem, Monitor And Control Subsystem,
Described binocular acquisition subsystem comprises high-definition camera, integrated circuit control card, described integrated circuit control card controls high-definition camera, and described integrated circuit control card module integration has image compression encoding chip, video streaming chip, signal conversion chip;
Described CAN optical fiber transmission subsystem comprises: CAN and Transmission Fibers, and the fan-out of integrated circuit control card is always reportedly delivered to Transmission Fibers by described CAN, and data are sent to Monitor And Control Subsystem by Transmission Fibers;
Described Monitor And Control Subsystem comprises: application host and database server, and described application host can carry out Canny rim detection, Hough transform, constraints algorithm data analysis and treament, and database server carries out data management.
2. monitoring system according to claim 1, it is characterized in that, described high-definition camera is specially binocular high-definition camera.
3. monitoring system according to claim 1, it is characterized in that, described integrated circuit control card is specially ARM chip integrated circuit control card.
4. monitoring system according to claim 1, is characterized in that, integrated memory cell in described integrated circuit control card.
5. monitoring system according to claim 1, it is characterized in that, described Transmission Fibers comprises optical fiber controller, optical fiber group, and described optical fiber group comprises 100,000,000 optical fiber, optical fiber switch, kilomega optic fiber.
6. monitoring system according to claim 5, it is characterized in that, described optical fiber controller comprises fiber optic switching module and transceiver.
7. described in any one of claim 1-6 based on the monitoring method of the notch of switch machine monitoring system of binocular vision process, it is characterized in that, comprise the steps:
S1. integrated circuit control card control high-definition camera carries out data acquisition, and the real-time gap image collected by high-definition camera carries out preliminary treatment, coding, compression by integrated circuit control card;
S2. data-signal is transferred data to Monitor And Control Subsystem by CAN and Transmission Fibers;
S3. image and video data are stored in mass storage by Monitor And Control Subsystem, and are presented on monitor screen by original image and video;
S4. to comprise the camera review of jagged information carry out gray processing process, smoothed image, remove noisy operation;
S5. use Canny edge detector to carry out rim detection to image, subsequently Hough transform is carried out to image and carry out Line segment detection, identify the segment data extracted in image;
S6. identifying processing line segment out screened, adjudicate, sort operation, finally identify the line segment representing breach left hand edge accurately.
S7. according to breach calculations of offset principle, passing ratio calculates notch of switch machine side-play amount in reality.
8. notch of switch machine monitoring method according to claim 7, is characterized in that, the principle of image being carried out to Hough transform is as follows:
In polar coordinate system, linear equation is: ρ=xcos θ+ysin θ, the gradient of computed image also arranges thresholding to it, obtain a width bianry image, determine to segment again with in ρ θ plane, the number of its accumulator element is checked in the place of concentrating pixels tall, the relation in the unit that inspection is selected between pixel.
9. notch of switch machine monitoring method according to claim 7, is characterized in that, breach calculations of offset principle and ratio formulae discovery side-play amount, and principle is as follows:
M is the developed width of benchmark image
L is breach real offset
M ' is the width of reference mark on image
L ' is breach side-play amount about on image.
10. the notch of switch machine monitoring method according to claim 7-9, it is characterized in that, described monitoring implementation procedure is suitable for left image and right image simultaneously, according to the breach side-play amount that left and right image calculates respectively, the value that is averaged processes, and obtains the statistic of breach side-play amount.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610021854.7A CN105472355A (en) | 2016-01-13 | 2016-01-13 | Switch machine notch monitoring system and method based on binocular visual processing identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610021854.7A CN105472355A (en) | 2016-01-13 | 2016-01-13 | Switch machine notch monitoring system and method based on binocular visual processing identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105472355A true CN105472355A (en) | 2016-04-06 |
Family
ID=55609578
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610021854.7A Pending CN105472355A (en) | 2016-01-13 | 2016-01-13 | Switch machine notch monitoring system and method based on binocular visual processing identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105472355A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107907287A (en) * | 2016-12-27 | 2018-04-13 | 西安铁路信号有限责任公司 | A kind of goat compound mechanics environmental reliability experimental provision and method |
CN108917599A (en) * | 2018-07-03 | 2018-11-30 | 深圳市迈进科技有限公司 | A kind of notch of switch machine image monitoring device |
CN109708696A (en) * | 2018-12-28 | 2019-05-03 | 宁波思高信通科技有限公司 | A kind of goat thrust monitoring system |
CN111145197A (en) * | 2019-12-10 | 2020-05-12 | 电子科技大学 | Accurate turnout switch machine notch edge positioning method based on histogram and local gradient |
CN111144235A (en) * | 2019-12-10 | 2020-05-12 | 通控研究院(安徽)有限公司 | Video-based switch blade crawling monitoring method |
CN111862229A (en) * | 2020-06-05 | 2020-10-30 | 北京中科慧眼科技有限公司 | Binocular camera adjusting method and device |
CN112623269A (en) * | 2020-12-04 | 2021-04-09 | 中国航空工业集团公司成都飞机设计研究所 | Embedded control surface clearance and skewness automatic detection method and equipment |
CN112817840A (en) * | 2020-12-30 | 2021-05-18 | 交控科技股份有限公司 | Turnout inspection column and inspection block gap measuring method and device based on camera |
CN113251970A (en) * | 2021-04-30 | 2021-08-13 | 西安铁路信号有限责任公司 | On-line detection method for abrasion loss of switch machine locking surface |
CN115107834A (en) * | 2022-07-18 | 2022-09-27 | 西南交通大学 | Vehicle-mounted monitoring system for running track of wheel set of railway vehicle |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5311600A (en) * | 1992-09-29 | 1994-05-10 | The Board Of Trustees Of The Leland Stanford Junior University | Method of edge detection in optical images using neural network classifier |
CN1600611A (en) * | 2004-10-10 | 2005-03-30 | 北京交通大学 | Method for monitoring operating state of switch machine for switches and crossings of wheel track |
CN102490764A (en) * | 2011-12-13 | 2012-06-13 | 天津卓朗科技发展有限公司 | Automatic detection method of track turnout notch |
CN102556119A (en) * | 2011-12-19 | 2012-07-11 | 济南铁路天龙高新技术开发有限公司 | Method for directly collecting gap data measured by indication lever gap image of railway point switch |
CN202353668U (en) * | 2011-12-19 | 2012-07-25 | 济南铁路天龙高新技术开发有限公司 | Gap image acquisition processor of S700K electric switch machine |
CN102673611A (en) * | 2011-12-19 | 2012-09-19 | 济南铁路天龙高新技术开发有限公司 | Video monitoring method and video monitoring system of indication rod gaps of railway point switch |
CN202508119U (en) * | 2012-03-23 | 2012-10-31 | 上海天沐自动化仪表有限公司 | Turnout gap monitoring system |
CN102951183A (en) * | 2012-10-31 | 2013-03-06 | 同济大学 | Switch machine indication gap displacement monitoring device based on linear array image sensor |
CN202879528U (en) * | 2012-08-29 | 2013-04-17 | 北京中铁通电务技术开发有限公司 | Universal notch detecting equipment for switch machine |
CN203434750U (en) * | 2013-08-15 | 2014-02-12 | 李德臣 | Coal mine override trip-preventing intelligent monitoring system based on synchronous measurement information system |
CN104330041A (en) * | 2014-09-30 | 2015-02-04 | 中铁山桥集团有限公司 | Measuring method for track switch steel rail member drill hole dimension |
CN204775299U (en) * | 2015-08-13 | 2015-11-18 | 宁波思高信通科技有限公司 | Breach video monitoring system is showed to goat |
CN206353824U (en) * | 2016-01-13 | 2017-07-25 | 江苏金晓电子信息股份有限公司 | A kind of notch of switch machine monitoring system based on binocular vision processing identification |
-
2016
- 2016-01-13 CN CN201610021854.7A patent/CN105472355A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5311600A (en) * | 1992-09-29 | 1994-05-10 | The Board Of Trustees Of The Leland Stanford Junior University | Method of edge detection in optical images using neural network classifier |
CN1600611A (en) * | 2004-10-10 | 2005-03-30 | 北京交通大学 | Method for monitoring operating state of switch machine for switches and crossings of wheel track |
CN102490764A (en) * | 2011-12-13 | 2012-06-13 | 天津卓朗科技发展有限公司 | Automatic detection method of track turnout notch |
CN102556119A (en) * | 2011-12-19 | 2012-07-11 | 济南铁路天龙高新技术开发有限公司 | Method for directly collecting gap data measured by indication lever gap image of railway point switch |
CN202353668U (en) * | 2011-12-19 | 2012-07-25 | 济南铁路天龙高新技术开发有限公司 | Gap image acquisition processor of S700K electric switch machine |
CN102673611A (en) * | 2011-12-19 | 2012-09-19 | 济南铁路天龙高新技术开发有限公司 | Video monitoring method and video monitoring system of indication rod gaps of railway point switch |
CN202508119U (en) * | 2012-03-23 | 2012-10-31 | 上海天沐自动化仪表有限公司 | Turnout gap monitoring system |
CN202879528U (en) * | 2012-08-29 | 2013-04-17 | 北京中铁通电务技术开发有限公司 | Universal notch detecting equipment for switch machine |
CN102951183A (en) * | 2012-10-31 | 2013-03-06 | 同济大学 | Switch machine indication gap displacement monitoring device based on linear array image sensor |
CN203434750U (en) * | 2013-08-15 | 2014-02-12 | 李德臣 | Coal mine override trip-preventing intelligent monitoring system based on synchronous measurement information system |
CN104330041A (en) * | 2014-09-30 | 2015-02-04 | 中铁山桥集团有限公司 | Measuring method for track switch steel rail member drill hole dimension |
CN204775299U (en) * | 2015-08-13 | 2015-11-18 | 宁波思高信通科技有限公司 | Breach video monitoring system is showed to goat |
CN206353824U (en) * | 2016-01-13 | 2017-07-25 | 江苏金晓电子信息股份有限公司 | A kind of notch of switch machine monitoring system based on binocular vision processing identification |
Non-Patent Citations (1)
Title |
---|
张宇宁;谢琦;: "一种基于机器视觉的铁路道岔检测方法" * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107907287A (en) * | 2016-12-27 | 2018-04-13 | 西安铁路信号有限责任公司 | A kind of goat compound mechanics environmental reliability experimental provision and method |
CN107907287B (en) * | 2016-12-27 | 2023-11-24 | 西安铁路信号有限责任公司 | Device and method for testing reliability of composite mechanical environment of railway point machine |
CN108917599A (en) * | 2018-07-03 | 2018-11-30 | 深圳市迈进科技有限公司 | A kind of notch of switch machine image monitoring device |
CN109708696A (en) * | 2018-12-28 | 2019-05-03 | 宁波思高信通科技有限公司 | A kind of goat thrust monitoring system |
CN111145197B (en) * | 2019-12-10 | 2022-05-03 | 电子科技大学 | Accurate turnout switch machine notch edge positioning method based on histogram and local gradient |
CN111144235A (en) * | 2019-12-10 | 2020-05-12 | 通控研究院(安徽)有限公司 | Video-based switch blade crawling monitoring method |
CN111144235B (en) * | 2019-12-10 | 2023-06-02 | 通控研究院(安徽)有限公司 | Switch tongue track crawling monitoring method based on video |
CN111145197A (en) * | 2019-12-10 | 2020-05-12 | 电子科技大学 | Accurate turnout switch machine notch edge positioning method based on histogram and local gradient |
CN111862229A (en) * | 2020-06-05 | 2020-10-30 | 北京中科慧眼科技有限公司 | Binocular camera adjusting method and device |
CN112623269A (en) * | 2020-12-04 | 2021-04-09 | 中国航空工业集团公司成都飞机设计研究所 | Embedded control surface clearance and skewness automatic detection method and equipment |
CN112817840A (en) * | 2020-12-30 | 2021-05-18 | 交控科技股份有限公司 | Turnout inspection column and inspection block gap measuring method and device based on camera |
CN112817840B (en) * | 2020-12-30 | 2024-01-26 | 交控科技股份有限公司 | Switch checking column and checking block gap measuring method and device based on camera |
CN113251970A (en) * | 2021-04-30 | 2021-08-13 | 西安铁路信号有限责任公司 | On-line detection method for abrasion loss of switch machine locking surface |
CN113251970B (en) * | 2021-04-30 | 2023-09-12 | 西安铁路信号有限责任公司 | Online detection method for wear amount of locking surface of switch machine |
CN115107834A (en) * | 2022-07-18 | 2022-09-27 | 西南交通大学 | Vehicle-mounted monitoring system for running track of wheel set of railway vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105472355A (en) | Switch machine notch monitoring system and method based on binocular visual processing identification | |
Karakose et al. | A new computer vision based method for rail track detection and fault diagnosis in railways | |
CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
CN102323070B (en) | Method and system for detecting abnormality of train | |
CN104006834B (en) | Transformer station's mechanical type table counts collection and diagnostic system | |
CN109489584B (en) | Tunnel clearance detection system and tunnel clearance identification method based on 3D technology | |
CN103837087B (en) | Pantograph automatic testing method based on active shape model | |
CN104504388A (en) | Pavement crack identification and feature extraction algorithm and system | |
CN103927507A (en) | Improved multi-instrument reading identification method of transformer station inspection robot | |
CN102490764B (en) | Automatic detection method of track turnout notch | |
CN102628814A (en) | Automatic detection method of steel rail light band abnormity based on digital image processing | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
KR20150012384A (en) | Pothole Recognition System and Its Implementation Method | |
CN202444572U (en) | Non-reference video monitoring image blurring quality detection device | |
CN101510295B (en) | Design method for machine vision system based on PCIe and Vision Assistan | |
CN108981565A (en) | A kind of municipal rail train pantograph disalignment monitoring device and method | |
CN206353824U (en) | A kind of notch of switch machine monitoring system based on binocular vision processing identification | |
CN203083532U (en) | A system used for detecting the safe operation of a power transmission line | |
CN103996266B (en) | Tailing reservoir safety monitoring device based on video analysis | |
Liu et al. | A binocular reconstruction method fused with Laplacian image information for pavement texture evaluation | |
CN102980536A (en) | Brake pad steel backing planeness detecting system and method thereof | |
CN110110889A (en) | A kind of measuring method and system of hydroelectric project rated consumption amount | |
CN102620048B (en) | Image monitoring method for monitoring safety of valves in industrial boiler field | |
CN102928093A (en) | Infrared-based billet surface temperature measurement 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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160406 |
|
WD01 | Invention patent application deemed withdrawn after publication |