CN211205191U - Rail pad displacement monitoring system based on image recognition processing - Google Patents
Rail pad displacement monitoring system based on image recognition processing Download PDFInfo
- Publication number
- CN211205191U CN211205191U CN201920878188.8U CN201920878188U CN211205191U CN 211205191 U CN211205191 U CN 211205191U CN 201920878188 U CN201920878188 U CN 201920878188U CN 211205191 U CN211205191 U CN 211205191U
- Authority
- CN
- China
- Prior art keywords
- image recognition
- rail
- displacement
- monitoring
- unit
- 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.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The utility model discloses a rail underbody bolster displacement monitoring system based on image recognition handles, it includes monitoring devices, information transmission system and terminal, monitoring devices establishes in the track side, it includes the image recognition unit, the processor unit, the memory cell, power supply unit and alarm device, the image recognition unit includes optical lens and image sensor, the optical lens carries out data conversion with the image sensor with the image of shooing and transmits to the processor unit, the processing result is stored in the memory cell, send to the terminal through the information transmission system simultaneously, control alarm device and warn after the processing result exceeds the settlement threshold value; the power supply unit provides electric energy. The utility model aims at providing a rail underboarding displacement monitoring system based on image recognition handles, this monitoring system is used for carrying out analysis, early warning, report to key position data rail transit's reliability to rail underboarding displacement real-time supervision, reduces staff's work load.
Description
Technical Field
The utility model belongs to the technical field of rail transit monitoring facilities, specifically be a rail lower bolster displacement monitoring system based on image recognition handles.
Background
Rail transit refers to a type of transportation or transportation system in which operating vehicles need to travel on a specific track, and the most typical rail transit is a railway system consisting of conventional trains and standard railways. With the diversified development of train and railway technologies, rail transit is more and more types, and is not only distributed in long-distance land transportation, but also widely applied to medium-short distance urban public transportation. In recent years, the high-speed railway in China is in a rapid development period, and the country vigorously builds high-speed railway lines, so as to accelerate and promote economic development among cities, and meanwhile, the method brings a plurality of new challenges to track safety.
As is known to all, the rail is deformed and displaced due to expansion and contraction, and the rail is particularly obvious in the environment with higher temperature. However, when the displacement is large, the base plate under the rail is driven to move together, the base plate plays roles of positioning, buffering, insulating and the like on the rail, if the rail is greatly slid, the rail is loosened, the driving safety is not favorable, especially on a rail turnout (large lateral extrusion force) or a bridge and other weak zones with poor stability, the safe passing of the train is greatly threatened, therefore, a large number of workers at the railway department perform manual monitoring, the most main defect is that on one hand, the manual judgment is performed through naked eyes, the deviation exists, and the displacement condition of the base plate cannot be reflected in real time, such as: the method comprises the following steps that a patrol worker starts in the morning, observes a place without large displacement of a base plate, and observes the place when the patrol worker returns at night, wherein the displacement condition of the base plate is the same because the temperature difference between the morning and the evening is small, and the displacement is not observed when the temperature at noon is the highest, so that great potential safety hazard exists; on the other hand, as the number of railway lines increases and the driving speed increases, more manpower and material resources are required to be continuously input for corresponding monitoring and maintenance, and the operation cost is increased inevitably, so that the problem needs to be solved urgently.
Through retrieval discovery, patent document with publication number cn201010272150.x discloses an on-line track monitoring method and an on-line track testing system which are realized by a communication system, a computer system, a displacement sensor, a vibration sensor, a laser distance detector, a microprocessor and a communication module, can be used for carrying out on-line monitoring on changes of relative spacing of tracks, changes of plane height, changes of track fastening facilities and cracks and deformation generated in the tracks, and have the characteristics of good monitoring real-time performance, capability of timely discovering and alarming sudden track parameter changes, and low testing workload and cost. The online test system involves the application of a large number of sensors, microprocessors and the like, is not economical, has complex detection and is difficult to popularize.
SUMMERY OF THE UTILITY MODEL
The utility model aims at above problem, provide a rail underboarding displacement monitoring system based on image recognition handles, this monitoring system is used for rail underboarding displacement real-time supervision, still comprehensive state data such as the orbital vibration of expandable monitoring and displacement, accomplishes and carries out analysis, early warning, report to the key position data, improves track transportation's reliability, reduces railway staff's work load.
Meanwhile, the method for monitoring the displacement of the under-rail pad based on image recognition processing is also disclosed.
In order to realize the above purpose, the utility model adopts the technical scheme that: a displacement monitoring system of a pad under a rail based on image recognition processing comprises a monitoring device, an information transmission system and a terminal, wherein the monitoring device is arranged on the side of the rail and comprises an image recognition unit, a processor unit, a storage unit, a power supply unit and an alarm device which are electrically connected, the image recognition unit comprises an optical lens and an image sensor which are connected, the optical lens carries out data conversion on a shot image through the image sensor and then transmits the data to the processor unit for processing, a processing result is stored in the storage unit and is simultaneously transmitted to the terminal through the information transmission system, and the alarm device is controlled to warn when the processing result exceeds a set threshold value; the power supply unit provides electric energy for the image recognition unit, the processor unit and the alarm device.
Furthermore, an infrared light supplement lamp is arranged on the image recognition unit.
Furthermore, the power supply unit adopts a solar photovoltaic system to supply power, the solar photovoltaic system comprises a solar cell panel, a charging controller and a rechargeable battery which are electrically connected in sequence, and the rechargeable battery is electrically connected with the image recognition unit, the processor unit and the alarm device respectively.
Further, the alarm device is an alarm bell or audible and visual alarm connected with the processor unit.
Further, the information transmission system is a WiFi module, a GPRS communication module or a 3G/4G network module.
Further, the terminal is a PC or a mobile phone.
Furthermore, the monitoring device is arranged at the side of the steel rail fork, the railway bridge and the railway tunnel.
The monitoring method of the under-rail pad displacement monitoring system based on the image recognition processing comprises the following steps:
step A, field calibration: arranging a monitoring device on the steel rail side, adjusting the optimal shooting angle, shooting and calibrating the position to be monitored after starting up to obtain the characteristic value of the initial position of the test object, setting a standard threshold value of the position change of the calibration point as a calibration template, and storing the standard threshold value in a storage unit;
b, data acquisition comparison and analysis processing:
a. searching for calibration point A (x) in calibration template T (m, n) picture1,y1);
b. The calibration template T (m, n) is overlapped on the searched graph S (W, H) to be translated, and a subgraph is searchedThe search range is: i is not less than 1 and not more than W-n, j is not less than 1 and not more than H-m, T andsimilarity of (c):
normalizing the above formula to obtain a correlation coefficient matched with the template:
when the calibration template is the same as the searched graph, the correlation coefficient R (i, j) =1, and after all searches are completed in the searched graph S, the maximum value of R is foundCorresponding sub-diagram thereofI.e. matching the target, in the sub-graphFind the index point A' (x) with changed position2,y2) (ii) a Calculating template T (m, n) and subgraph by multiple multi-target detection averagingAverage Offset (x) between two points of the corresponding index point A, A2-x1,y2-y1);
In the formula:the template covers the area of the searched subgraph, i, j is the coordinate of the lower left corner of the subgraph on the searched graph S;
c. calculating the actual target displacement according to the pixel proportion of the image identification unit, wherein the actual corresponding X-direction displacement difference value is (X)2-x1) The difference in displacement in the Y direction is (Y)2-y1)*;
d. If the actual corresponding X, Y direction displacement value exceeds the threshold value set in the initial state, marking and early warning the picture information, and controlling an alarm device to warn;
step C, monitoring result distribution: the processor unit sends the analysis result in the step B to each terminal through an information transmission system;
step D, real-time monitoring: and (6) repeating the step B, C, setting the sampling frequency, carrying out image acquisition and analysis on the site at intervals, and distributing the images to the terminals in real time.
Further, the information transmission system in the step C is distributed to the terminal through one or more of a WiFi module, a GPRS communication module, and a 3G/4G network module.
The utility model has the advantages that: the monitoring device is used for monitoring displacement data of the under-rail base plate in real time, can also expand and monitor comprehensive state data of vibration, displacement and the like of the rail, completes analysis, early warning and report on position data of the relevant key, improves the reliability of rail transit and transportation, and reduces the workload of railway workers.
1. The utility model discloses well rail bottom suspension board monitoring position remote auxiliary device has simple structure, small light in weight, be convenient for constantly survey rail bottom suspension board position, convenient to use, range of application are wide, the security is good, the reliability is high, adaptation environmental protection nature is strong, characteristics such as longe-lived.
2. The utility model discloses a monitoring devices can apply to the monitoring railway track any relative displacement's that appears structural, like the relative displacement change of monitoring switch structure tongue and stock rail on the big slope, high-speed railway fastener position change etc. guarantee railway transportation's safety.
3. The utility model discloses a monitoring system only needs to mark the point of waiting to monitor when handling data, carry out the feature localization fast, return the feature localization result that has the calling information, the system has the point after the automatic identification position change, have characteristics such as swift, simple, accurate, convenient, automatic, but remote calculation, this method is for other methods, the subgraph evaluation value of searching is higher, make the rate of accuracy of feature localization result enough good, and the complexity of method is lower, can quick search the subgraph, let the user in time obtain the feature localization result; the calculation range is wide, a plurality of calibration points can be calculated simultaneously, and the influence of the displacement of other components can be avoided.
Drawings
Fig. 1 is the utility model discloses monitoring devices and track mounting relation sketch map.
Fig. 2 is a schematic view of a part of an enlarged structure at a in fig. 1 according to the present invention.
Fig. 3 is the connection relationship diagram of the monitoring system module of the present invention.
Fig. 4 is the utility model discloses monitoring system work flow chart.
The text labels in the figures are represented as: 1. an image recognition unit; 2. a processor unit; 3. a storage unit; 4. a power supply unit; 5. an alarm device; 6. a track plate; 7. a sleeper; 8. a steel rail; 9. a backing plate.
Detailed Description
In order to make the technical solution of the present invention better understood, the present invention is described in detail below with reference to the accompanying drawings, and the description of the present invention is only exemplary and explanatory, and should not be construed as limiting the scope of the present invention.
As shown in fig. 1-4, the specific structure of the present invention is: a displacement monitoring system of a pad under a rail based on image recognition processing comprises a monitoring device, an information transmission system and a terminal, wherein the monitoring device is arranged on the side of the rail and comprises an image recognition unit 1, a processor unit 2, a storage unit 3, a power supply unit 4 and an alarm device 5 (which can adopt an acousto-optic warning device) which are electrically connected, the image recognition unit 1 comprises an optical lens and an image sensor (preferably a CCD image sensor) which are connected, the optical lens carries out data conversion on a shot image through the image sensor and then transmits the shot image to the processor unit 2 for processing, a processing result is stored in the storage unit 3 and is simultaneously transmitted to the terminal through the information transmission system, and the alarm device 5 is controlled to carry out warning when the processing result exceeds a set threshold value; the power supply unit 4 supplies electric energy to the image recognition unit 1, the processor unit 2 and the alarm device 5.
Preferably, an infrared fill light is arranged on the image recognition unit 1, a high-brightness L ED fill light is configured, and the brightness of color temperatures 6000K and L ED fill light can be adjusted through the video coding unit.
Preferably, the power supply unit 4 is powered by a solar photovoltaic system, the solar photovoltaic system comprises a solar cell panel, a charging controller and a rechargeable battery which are electrically connected in sequence, and the rechargeable battery is electrically connected with the image recognition unit 1, the processor unit 2 and the alarm device 5 respectively.
Preferably, the alarm device 5 is an alarm bell or an audible and visual alarm connected to the processor unit 2.
Preferably, the information transmission system is a WiFi module, a GPRS communication module or a 3G/4G network module. The GPRS wireless transmission system mainly aims at industrial application, provides an RS232 standard interface, is directly connected with user equipment, and realizes the functions of Chinese and English short messages, multimedia messages and GPRS data transmission, and the software interface is simple and easy to use.
Preferably, the terminal is a PC or a mobile phone. The system is convenient for operators to receive on site or remotely and can be monitored flexibly.
Preferably, the monitoring device is arranged at the side of a steel rail fork, a railway bridge or a railway tunnel. The above places are the places most prone to displacement, and therefore need to be monitored specially.
The monitoring method of the under-rail pad displacement monitoring system based on the image recognition processing comprises the following steps:
step A, field calibration: arranging a monitoring device at the side of a steel rail, aligning to a rail lower base plate (a base plate 9 comprises a rubber base plate, an iron base plate and an elastic base plate, the base plate 9 is arranged between a sleeper 7 and the steel rail 8 and is fastened through an elastic strip), adjusting the optimal shooting angle, enabling a region to be monitored to be located in the maximum shooting range of an image recognition unit, shooting and calibrating a position to be monitored after starting up, obtaining an initial position characteristic value of a test object, setting a calibration point position change standard threshold value for a calibration template, and storing the calibration point change standard threshold value in a storage unit;
b, data acquisition comparison and analysis processing:
a. searching for calibration point A (x) in calibration template T (m, n) picture1,y1);
b. The calibration templates T (m, n) are stacked onIs translated on the searched graph S (W, H) to search subgraphThe search range is: i is not less than 1 and not more than W-n, j is not less than 1 and not more than H-m, T andsimilarity of (c):
normalizing the above formula to obtain a correlation coefficient matched with the template:
when the calibration template is the same as the searched graph, the correlation coefficient R (i, j) =1, and after all searches are completed in the searched graph S, the maximum value of R is foundCorresponding sub-diagram thereofI.e. matching the target, in the sub-graphFind the index point A' (x) with changed position2,y2) (ii) a Calculating template T (m, n) and subgraph by multiple multi-target detection averagingAverage Offset (x) between two points of the corresponding index point A, A2-x1,y2-y1);
In the formula:the template covers the area of the searched subgraph, i, j is the coordinate of the lower left corner of the subgraph on the searched graph S;
c. calculating the actual target displacement according to the pixel proportion of the image identification unit, wherein the actual corresponding X-direction displacement difference value is (X)2-x1) The difference in displacement in the Y direction is (Y)2-y1)*;
d. If the actual corresponding X, Y direction displacement value exceeds the threshold value set in the initial state, marking and early warning are carried out on the picture information, and an alarm device is controlled to work for warning;
step C, monitoring result distribution: the processor unit sends the analysis result in the step B to each terminal through an information transmission system;
step D, real-time monitoring: and (6) repeating the step B, C, setting the sampling frequency, carrying out image acquisition and analysis on the site at intervals, and distributing the images to the terminals in real time.
Preferably, the information transmission system in the step C distributes the information to the terminal through one or more of the WiFi module, the GPRS communication module and the 3G/4G network module, so as to realize real-time monitoring of the pad under the rail and complete analysis, reporting and early warning of the position data of the key.
The utility model discloses the theory of operation does: saving the target object as a template image, searching for the target in a large image captured by a camera at the later stage by using the template image, and calculating the Offset difference of the two targets to be Offset (x2-x1, y2-y1) by assuming that the position coordinate of the target point searched for at the first time is A (x1, y2) and the position coordinate of the target point searched for at the second time is A' (x2, y2) along with the time; at this time, the difference is only the difference between the pixels, and the difference is multiplied by the pixel proportion (pixel/mm), so that the actual corresponding X-direction displacement difference is (X2-X1), and the Y-direction displacement difference is (Y2-Y1).
The specific work flow is (as shown in fig. 4):
initializing a system, setting a picture pixel proportion parameter value to be 1.0002 pixels/mm, snapshotting a template picture, selecting an area to be monitored for calibration, starting monitoring by a monitoring system, comparing and analyzing the rephotoped picture with the calibrated area in the template picture after a certain time (the pad plate does not move or the movement distance is small after the time is too short), and calculating the displacement of a calibration point, wherein the horizontal coordinate displacement is-2.000 mm, the vertical coordinate displacement is 3.001mm, and in the parameter setting, the pixel proportion is set to be 1.0002 pixels/mm, so that the pad plate under the rail moves as follows: the horizontal coordinate displacement is 2.0004mm, the vertical coordinate displacement is 3.0016002mm, and when the displacement of the base plate (calculated by using the pythagorean theorem) exceeds a set threshold value, the monitoring device automatically alarms.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The principles and embodiments of the present invention have been explained herein using specific examples, which are presented only to assist in understanding the methods and their core concepts. The foregoing is only a preferred embodiment of the present invention, and it should be noted that there are objectively infinite specific structures due to the limited character expressions, and it will be apparent to those skilled in the art that a plurality of modifications, decorations or changes can be made without departing from the principle of the present invention, and the above technical features can be combined in a proper manner; the application of these modifications, variations or combinations, or the application of the concepts and solutions of the present invention in other contexts without modification, is not intended to be considered as a limitation of the present invention.
Claims (7)
1. The monitoring device is arranged on the side of a track and comprises an image recognition unit (1), a processor unit (2), a storage unit (3), a power supply unit (4) and an alarm device (5) which are electrically connected, wherein the image recognition unit (1) comprises an optical lens and an image sensor which are connected, the optical lens carries out data conversion on a shot image through the image sensor and then transmits the shot image to the processor unit (2) for processing, a processing result is stored in the storage unit (3) and is simultaneously transmitted to the terminal through the information transmission system, and the alarm device (5) is controlled to warn when the processing result exceeds a set threshold value; the power supply unit (4) provides electric energy for the image recognition unit (1), the processor unit (2) and the alarm device (5).
2. The system for monitoring the displacement of the under-rail pad based on the image recognition processing as claimed in claim 1, wherein an infrared light supplement lamp is arranged on the image recognition unit (1).
3. The image recognition processing-based rail pad displacement monitoring system according to claim 1, wherein the power supply unit (4) is powered by a solar photovoltaic system, the solar photovoltaic system comprises a solar panel, a charging controller and a rechargeable battery, which are electrically connected in sequence, and the rechargeable battery is electrically connected with the image recognition unit (1), the processor unit (2) and the alarm device (5) respectively.
4. An image recognition processing based trackpad displacement monitoring system according to claim 1, characterized in that the alarm device (5) is an alarm bell or an audible and visual alarm connected to the processor unit (2).
5. The system for monitoring displacement of the under-rail pad based on image recognition processing as claimed in claim 1, wherein the information transmission system is a WiFi module, a GPRS communication module or a 3G/4G network module.
6. The system for monitoring displacement of the under-rail pad based on image recognition processing as claimed in claim 1, wherein the terminal is a PC or a mobile phone.
7. The system for monitoring displacement of the pad plate under the rail based on the image recognition processing as claimed in claim 1, wherein the monitoring device is arranged at the side of a steel rail fork, a railway bridge or a railway tunnel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920878188.8U CN211205191U (en) | 2019-06-12 | 2019-06-12 | Rail pad displacement monitoring system based on image recognition processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920878188.8U CN211205191U (en) | 2019-06-12 | 2019-06-12 | Rail pad displacement monitoring system based on image recognition processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN211205191U true CN211205191U (en) | 2020-08-07 |
Family
ID=71856446
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201920878188.8U Active CN211205191U (en) | 2019-06-12 | 2019-06-12 | Rail pad displacement monitoring system based on image recognition processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN211205191U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110296659A (en) * | 2019-06-12 | 2019-10-01 | 中南大学 | A kind of railway rail pad system for monitoring displacement and method based on image recognition processing |
-
2019
- 2019-06-12 CN CN201920878188.8U patent/CN211205191U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110296659A (en) * | 2019-06-12 | 2019-10-01 | 中南大学 | A kind of railway rail pad system for monitoring displacement and method based on image recognition processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107037318B (en) | A kind of power cable fault locating platform | |
CN110542898A (en) | Radar group-based vehicle behavior continuous tracking detection system and method | |
CN110296659A (en) | A kind of railway rail pad system for monitoring displacement and method based on image recognition processing | |
CN103235562A (en) | Patrol-robot-based comprehensive parameter detection system and method for substations | |
CN206559654U (en) | A kind of transformer station management system positioned based on UWB | |
CN105353266A (en) | Underground cable fault monitoring system and underground cable fault monitoring method | |
CN103723161A (en) | Real-time automatic detection equipment for train loading safety | |
WO2022242759A1 (en) | Unmanned intelligent inspection system and method applied to offshore booster station | |
CN110824497A (en) | Intelligent detection device and detection method for contact network | |
CN113027530A (en) | Coal mine safety monitoring system and monitoring method based on internet data interaction | |
CN114113118B (en) | Rapid detection device and detection method for subway tunnel lining crack leakage water disease | |
CN112197218B (en) | Comprehensive energy wisdom street lamp | |
CN111385540A (en) | Wisdom municipal infrastructure management system based on video stream analysis technique | |
CN103593883A (en) | On-line GPS (Global Positioning System) night-patrol positioning system | |
CN207155816U (en) | A kind of robot inspection system based on intelligent power generation station | |
CN110217264A (en) | Vehicle wheel is to detection device, method and system | |
CN211205191U (en) | Rail pad displacement monitoring system based on image recognition processing | |
CN211263774U (en) | Be used for contact net intellectual detection system device | |
CN105811578A (en) | Power transmission line monitoring platform, power source monitoring algorithm thereof and image early warning algorithm of power transmission line monitoring platform | |
CN210005038U (en) | municipal facilities intelligent management system | |
CN201741280U (en) | High-definition interval speed measuring system | |
CN204331844U (en) | All-around intelligentization communication inspection device | |
CN116119385A (en) | Digital coal yard unmanned control system and control method thereof | |
CN114267182B (en) | Violation reminding robot system and violation reminding method | |
CN212887622U (en) | Indoor positioning navigation inspection robot system based on UWB |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |