CN206223458U - Vibration detecting system of the rail vehicle based on video analysis in tunnel - Google Patents
Vibration detecting system of the rail vehicle based on video analysis in tunnel Download PDFInfo
- Publication number
- CN206223458U CN206223458U CN201621310475.1U CN201621310475U CN206223458U CN 206223458 U CN206223458 U CN 206223458U CN 201621310475 U CN201621310475 U CN 201621310475U CN 206223458 U CN206223458 U CN 206223458U
- Authority
- CN
- China
- Prior art keywords
- train
- video camera
- detecting system
- vibration detecting
- vision sensor
- 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.)
- Expired - Fee Related
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 2
- 238000000465 moulding Methods 0.000 claims 1
- 230000002123 temporal effect Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 4
- 230000005641 tunneling Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
A kind of vibration detecting system of rail vehicle based on video analysis in tunnel is disclosed, including：At least one vision sensor, it is arranged at least one surface of the periphery of train for gathering the view data in tunnel in train process of passing through tunnel, and each vision sensor includes the first video camera and the second video camera arranged along current of traffic；Data processing unit, for the vibration data for processing the vision sensor view data for being collected and determine train, wherein the distance between the first video camera and the second video camera are equal to train operating rate and the product of video camera inter frame temporal, thus image of the first video camera being located behind at current time has overlapping region with image of second video camera in front at the former frame moment is located at, data processing unit carries out feature extraction and matching to overlapping region, so as to determine the coordinate difference between the image at current time and the image at former frame moment, it is derived from the current vibration parameters of train.
Description
Technical field
The invention provides a kind of train in the operating method for detecting vibration in tunnel and device, belong to railway tunnel detection
Technical field and oscillation sensor field.
Background technology
In recent years, with the fast development of city underground and high ferro, to the operation management of subway tunnel and railway tunnel and
Maintenance proposes requirement higher, therefore the various technical schemes that tunnel surface fault of construction is detected also are arisen at the historic moment.Wherein,
It is especially prominent to the scheme that tunnel carries out full section scanning with the tomography scan such as camera, laser e measurement technology.Full section scanning
Scheme be commonly divided into hand-held testing equipment and vehicle-mounted testing equipment.Hand-held testing equipment has many deficiencies, such as
Detection speed is slow, efficiency is low, thus be increasingly not suitable with modern times Tunnel testing window time it is short the characteristics of.And vehicle-mounted tunneling boring
Detection scheme can carry out the detection in tunnel under the speed of service higher, therefore with efficiency and convenience higher.
But, in vehicle-mounted tunneling boring detection scheme, the most important influence factor that various kinds of sensors faces is
The vibration of train.At present, a kind of effective scheme be measured using gyroscope its vibration, but gyroscope in the application itself
There is null offset, therefore have to go to correct it using the equipment for installing additional on the ground.This is caused to be detected with gyroscope and vibrated
Method application on limited by a lot.
On the other hand, current high speed camera and Video Analysis Technology reach its maturity so that with video analysis be technology hand
Section completes to be possibly realized the detection of rigid objects vibration.
The content of the invention
To overcome above mentioned problem and other technical problems to be resolved, the present invention is made that.
It is an object of the present invention to provide a kind of effectively detected based on Video Analysis Technology in full section of tunnel detection
The method and apparatus of the vibration of train, its measurement data that can accurately, reliable correct sensor completes the tunneling boring in tunnel
Detection.
According to an aspect of this disclosure, there is provided a kind of vibration inspection of rail vehicle based on video analysis in tunnel
Examining system, including：
At least one vision sensor, the vision sensor be installed at least one surface of the periphery of train with
For gathering the view data in tunnel in train process of passing through tunnel, each vision sensor is included along current of traffic
First video camera and the second video camera of arrangement；
Data processing unit, for processing the view data that vision sensor is collected, and determines current time train
Vibration data,
Wherein, the distance between first video camera and described second video camera are equal to train operating rate and video camera
The product of inter frame temporal, thus, positioned at train rear first video camera current time acquired image be located at
Second video camera in front of train has overlapping region in former frame moment acquired image, and
Wherein, the data processing unit carries out feature extraction and matching to the overlapping region such that it is able to it is determined that working as
Coordinate difference between the image and the image at former frame moment at preceding moment, is derived from the current vibration parameters of train.
Preferably, the first video camera and the second video camera are rigidly attached.
Preferably, the parameter of video camera is demarcated in advance, or carries out self-calibration.The method of wherein self-calibration refers in image
In the case that the three-dimensional coordinate of point is unknown, demarcated by the relation of image corresponding points in the scene of different angle shots
Method.
Preferably, vibration detecting system further includes control module, for making the vision sensor simultaneously or selecting
Selecting property image is acquired.
Preferably, vision sensor further includes temperature compensation means, and temperature is carried out for the parameter to the video camera
Degree compensation.
Preferably, vision sensor further includes the light source being arranged between the first video camera and the second video camera.
It is further preferred that the light source is ordinary light source or structure light source.Structure light source is to be thrown in a solid plate form
The light source being shot out, such as striated, point-like, the projection source of ring-type or the light source being made up of the laser of particular form.
Preferably, vibration detecting system includes four vision sensors, and four vision sensors are arranged in row
Four outer surfaces of car.
Preferably, between the image that synchronization is obtained there is overlapping region in the first video camera and the second video camera, and
And data processing unit can determine vision described in current time by carrying out feature extraction and matching to the overlapping region
Absolute distance between sensor and tunnel.
Preferably, train is detection vehicle or the common train for vibration detection.
Preferably, train work at present speed is transferred to the data processing unit, with based on train work at present speed
Degree determines the overlapping region of vision sensor with the deviation of setting operating rate, so that it is determined that the vibration of train.
Brief description of the drawings
Accompanying drawing shows preferred embodiment of the present disclosure, and is used to provide the technology of the disclosure together with foregoing disclose
Spirit further understands.However, the disclosure should not be construed as being limited to the embodiment shown in accompanying drawing.
Fig. 1 is the schematic diagram of vibration detecting system of the invention.
Fig. 2 shows the concrete structure of vision sensor of the invention.
Fig. 3 shows that t1 moment vision sensors gather the overlapping region of image.
Fig. 4 is the plan of the overlapping region shown in Fig. 3.
Fig. 5 shows that t1 gathers the overlapping region of image with t2 moment vision sensors.
Fig. 6 shows the plan of the overlapping region shown in Fig. 5.
Specific embodiment
Hereinafter, preferred embodiment of the present disclosure will be described in detail with reference to the attached drawings.Before described, it should be appreciated that
It is that the term used in this description and in the appended claims should not be construed as being limited to general and dictionary
Implication, but explained based on implication corresponding with the technical elements of the disclosure and concept, the implication and concept are allowing
Inventor suitably defines based on the principle of term for best explanation.
Additionally, description presented herein is only for the preferred example of illustration purpose, without being intended to limit this public affairs
The scope opened, it will thus be appreciated that can be right in the case where spirit and scope of the present disclosure when submitting the application are not departed from
It carries out other equivalent and changes.
Fig. 1 is the schematic diagram of vibration detecting system of the invention.In Fig. 1, vibration detecting system of the invention is employed
In track train 19, wherein track train 19 passes through tunnel 18.But, vibration detecting system of the invention can also be employed
Other land vehicles, are not limited solely to this.
Anticipate as shown in fig. 1, the vibration detecting system of the application includes at least one vision sensor 100, control mould
Block 20 and data processing unit 17.In the cross section of train 19, vision sensor 100 can be attached to train 19 at least
One outer surface, it is preferable that be attached to four outer surfaces of train 19.Control module 20 is configured to make vision sensor 100
Simultaneously or selectively image is acquired, and the view data that vision sensor 100 is collected is transferred at data
Reason unit 17.Data processing unit 17 can be that the view data to receiving carries out feature extraction, matching and three-dimensional position meter
The server of calculation.
Fig. 2 shows the concrete structure of a vision sensor of the invention.Vision sensor 100 is included along train
Spaced apart two or more video cameras of traffic direction A.In fig. 2, vision sensor 100 includes two video cameras 1,2,
They can use any appropriate video camera well known in the prior art, and the intrinsic parameter of video camera is determined by demarcating
With outer parameter.Alternatively, it is disposed with light source 9 between two video cameras 1,2, it is also possible to projected in tunnel surface using structure light
Related characteristic point or line.
Video camera 1,2 is arranged along current of traffic A, and is rigidly connected to each other.Video camera 1, the distance between 2 with
Train operating rate is relevant with video camera inter frame temporal.Especially, video camera 1, the distance between 2 is train operating rate and take the photograph
The product of camera inter frame temporal.That is, in train travelling process, when unit video camera inter frame temporal passes through, being located at
Video camera 1 on rear side of train is placed exactly in the position of current camera 2.
Further, vision sensor 100 is provided with temperature compensation means 13 and carries out temperature-compensating with to video camera 1,2.
Fig. 3 shows that t1 moment vision sensors gather the overlapping region of image.Fig. 4 is the overlapping region shown in Fig. 3
Plan.
When train passes through tunnel, video camera 1 and 2 obtains the image I1 and I2 at a certain such as t1 moment at moment, image I1
There is overlapping region O1 and I2 between.Data processing unit 17 is analyzed to the data of image I1 and I2 such that it is able to obtain
The current pose of train.Preferably, analysis can be identified to determine by the characteristic point of the image to being extracted in tunnel
Train three-dimensional coordinate (x- horizontal directions, y- vertical directions, z- depth directions) now.Especially, the data of depth direction can
Obtained with being the overlapping region O1 of image I1 and I2 by overlapping region as shown in Figure 3 and Figure 4.
Fig. 5 shows that t1 gathers the overlapping region of image with t2 moment vision sensors.Fig. 6 shows the weight shown in Fig. 5
Close the plan in region.
When train runs to forward the t2 moment with operating rate, vision sensor obtains next two field picture I3 and I4.In Fig. 5
In Fig. 6, dotted line represents the image I1 and I2 acquired in the t1 moment, and solid line represents the image I3 and I4 acquired in the t2 moment.Root
According to the present invention, in the ideal situation, the distance between video camera 1 and 2 is equal to train and is run with operating rate in a frame time
Distance, therefore, at the t2 moment, video camera 1 is located at the position of the video camera 2 at t1 moment.Now, image I3 has with I2 and overlaps
Region O2, as shown in Figure 5 and Figure 6.When by the data transfer of the image I3 and I4 at t2 moment to data processing unit 17, data
Processing unit 17 carries out feature extraction and matching primitives to overlapping region O2, thus obtain train current time (t2 moment) with it is upper
The coordinate difference at one moment (t1 moment), so that it is determined that the current vibration parameters of train.Especially, train work at present speed
Data processing unit 17 will be transferred to, with it is determined that vibration when consider train work at present speed with set operating rate it is inclined
Difference.
Preferably, when train is provided with multiple vision sensors (for example, the surrounding of train is respectively provided with a visual sensing
Device) when, it is combined by the analysis result to all the sensors, train can be obtained in current detection position and current detection
Temporal six-dimensional vibration numerical value, i.e. level, vertical, front and rear and pitching, driftage, the vibrating numerical in rolling.
Although having been disclosed for exemplary embodiment of the invention for illustrative purposes, those skilled in the art will
, it will be recognized that in the case where the spirit and scope of the present invention as disclosed in appended claims are not departed from, various changes
Type, addition and replacement are possible.
Claims (11)
1. vibration detecting system of a kind of rail vehicle based on video analysis in tunnel, it is characterised in that including：
At least one vision sensor, the vision sensor be installed at least one surface of the periphery of train for
The view data in tunnel is gathered in train process of passing through tunnel, each vision sensor includes being arranged along current of traffic
The first video camera and the second video camera；
Data processing unit, for processing the view data that the vision sensor is collected, and determines current time train
Vibration data,
Wherein, the distance between first video camera and second video camera are equal between train operating rate and camera frame
The product of time, thus, first video camera positioned at train rear is in current time acquired image and positioned at train
Second video camera in front has overlapping region in former frame moment acquired image, and
Wherein, the data processing unit carries out feature extraction and matching to the overlapping region such that it is able to it is determined that when current
Coordinate difference between the image and the image at former frame moment at quarter, is derived from the current vibration parameters of train.
2. vibration detecting system according to claim 1, it is characterised in that first video camera and second shooting
Machine is rigidly attached.
3. vibration detecting system according to claim 1, it is characterised in that the parameter of the video camera is demarcated in advance,
Or self-calibration is carried out in operation, wherein when self-calibration is carried out by image corresponding points in the scene of different angle shots
Relation is demarcated.
4. vibration detecting system according to claim 1, it is characterised in that the vibration detecting system further includes control
Molding block, for making the vision sensor be simultaneously or selectively acquired to image.
5. vibration detecting system according to claim 1, it is characterised in that the vision sensor further includes temperature
Compensation device, temperature-compensating is carried out for the parameter to the video camera.
6. vibration detecting system according to claim 1, it is characterised in that the vision sensor further includes arrangement
Light source between first video camera and second video camera.
7. vibration detecting system according to claim 6, it is characterised in that the light source is ordinary light source or structure light
Source.
8. vibration detecting system according to claim 1, it is characterised in that the vibration detecting system is included described in four
Vision sensor, four vision sensors are arranged in four outer surfaces of train.
9. vibration detecting system according to claim 1, it is characterised in that first video camera and second shooting
There is overlapping region, and the data processing unit between the image that synchronization is obtained by the overlapping region in machine
Carry out feature extraction and matching and can determine the absolute distance described in current time between vision sensor and tunnel.
10. vibration detecting system according to claim 1, it is characterised in that the train is the inspection for vibration detection
Measuring car or common train.
11. vibration detecting systems according to claim 1, it is characterised in that train work at present speed is transferred to institute
Data processing unit is stated, the vision sensor is determined with the deviation of setting operating rate with based on train work at present speed
The overlapping region, so that it is determined that the vibration of train.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621310475.1U CN206223458U (en) | 2016-12-01 | 2016-12-01 | Vibration detecting system of the rail vehicle based on video analysis in tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621310475.1U CN206223458U (en) | 2016-12-01 | 2016-12-01 | Vibration detecting system of the rail vehicle based on video analysis in tunnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206223458U true CN206223458U (en) | 2017-06-06 |
Family
ID=58783971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621310475.1U Expired - Fee Related CN206223458U (en) | 2016-12-01 | 2016-12-01 | Vibration detecting system of the rail vehicle based on video analysis in tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206223458U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108317997A (en) * | 2017-01-17 | 2018-07-24 | 大连因特视智能传感科技有限公司 | Vibration detecting system based on the rail vehicle of video analysis in tunnel |
-
2016
- 2016-12-01 CN CN201621310475.1U patent/CN206223458U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108317997A (en) * | 2017-01-17 | 2018-07-24 | 大连因特视智能传感科技有限公司 | Vibration detecting system based on the rail vehicle of video analysis in tunnel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN206177238U (en) | Vehicle gabarit size detection appearance | |
| CN103630088B (en) | High accuracy tunnel cross-section detection method based on bidifly light belt and device | |
| US20190031217A1 (en) | Method and measuring system for registering a fixed point adjacent a track | |
| CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
| CN101206229B (en) | Method for matching vehicle speed based on linear array CCD image | |
| KR102106452B1 (en) | AVM camera-based 3D laser vision object recognition and high-speed measuring system and method | |
| CN104749187A (en) | Tunnel lining disease detection device based on infrared temperature field and gray level image | |
| JP7352556B2 (en) | Method for commanding a set of one or more intervention tools mounted on a railway intervention vehicle | |
| CN103487034A (en) | Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target | |
| CN102382918B (en) | System and method for measuring blast furnace burden surface on line | |
| CN105403162B (en) | The automatic testing method of semitrailer outer profile size | |
| CN103499337A (en) | Vehicle-mounted monocular camera distance and height measuring device based on vertical target | |
| CN110189363A (en) | A kind of low multi-view video speed-measuring method of the mobile target of airdrome scene | |
| JP2014169939A (en) | Overhead wire position measuring apparatus and method | |
| CN109242035A (en) | Vehicle bottom fault detection means and method | |
| CN108317997A (en) | Vibration detecting system based on the rail vehicle of video analysis in tunnel | |
| CN107806824A (en) | The detection method and device of contact net geometric parameter under a kind of lower-speed state | |
| CN104112305A (en) | Passenger flow monitoring method and apparatus based on dual laser ranging | |
| US11247705B2 (en) | Train wheel measurement process, and associated system | |
| CN206223458U (en) | Vibration detecting system of the rail vehicle based on video analysis in tunnel | |
| CN105113376B (en) | Surface evenness detector and detection method based on optical detective technology | |
| CN208453013U (en) | Mobile detection robot carries the positioning system of 2D laser radar scanning axle | |
| CN209553217U (en) | A kind of railway clearance detection system combined based on laser and image | |
| CN104006804A (en) | Method for detecting offset of contact net based on observation benchmark instability compensation | |
| CN104019748B (en) | Observation standard unstability compensating type catenary offset detecting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170606 |