CN104567708B - Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision - Google Patents
Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision Download PDFInfo
- Publication number
- CN104567708B CN104567708B CN201510005918.XA CN201510005918A CN104567708B CN 104567708 B CN104567708 B CN 104567708B CN 201510005918 A CN201510005918 A CN 201510005918A CN 104567708 B CN104567708 B CN 104567708B
- Authority
- CN
- China
- Prior art keywords
- tunnel
- mrow
- section
- axis
- msup
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 59
- 230000036541 health Effects 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims description 46
- 238000012360 testing method Methods 0.000 claims abstract description 81
- 238000006073 displacement reaction Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 11
- 238000012800 visualization Methods 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims description 38
- 238000003384 imaging method Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 238000004062 sedimentation Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 238000013139 quantization Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000005055 memory storage Effects 0.000 claims 2
- 238000013459 approach Methods 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000003786 synthesis reaction Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000009434 installation Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- WHGYBXFWUBPSRW-FOUAGVGXSA-N beta-cyclodextrin Chemical compound OC[C@H]([C@H]([C@@H]([C@H]1O)O)O[C@H]2O[C@@H]([C@@H](O[C@H]3O[C@H](CO)[C@H]([C@@H]([C@H]3O)O)O[C@H]3O[C@H](CO)[C@H]([C@@H]([C@H]3O)O)O[C@H]3O[C@H](CO)[C@H]([C@@H]([C@H]3O)O)O[C@H]3O[C@H](CO)[C@H]([C@@H]([C@H]3O)O)O3)[C@H](O)[C@H]2O)CO)O[C@@H]1O[C@H]1[C@H](O)[C@@H](O)[C@@H]3O[C@@H]1CO WHGYBXFWUBPSRW-FOUAGVGXSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 231100000749 chronicity Toxicity 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N ferric oxide Chemical compound O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- ONUFESLQCSAYKA-UHFFFAOYSA-N iprodione Chemical compound O=C1N(C(=O)NC(C)C)CC(=O)N1C1=CC(Cl)=CC(Cl)=C1 ONUFESLQCSAYKA-UHFFFAOYSA-N 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000036244 malformation Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003534 oscillatory effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of full section of tunnel high speed dynamical health detection means based on active panoramic vision, its hardware includes：Tunnel testing car, active panoramic vision sensor, RFID reader and processor；System software includes：Comprehensive face laser intelligence parsing and cloud data acquiring unit, tunnel axis detection unit, noise reduction and adjustment processing unit, three-dimensional modeling and deformation analysis unit, full tunnel respectively save cross section benchmark database, full tunnel profile concatenation unit, displacement monitoring and settlement monitoring unit, full tunnel health examination result database and tunnel profile and become shifting amount three-dimensional visualization unit；By carrying out machine vision Treatment Analysis to tunnel inner wall laser scanning cross sectional slice image and identifying the horizontal and vertical deformation in tunnel.Present invention also offers a kind of full section of tunnel high speed dynamical health detection method based on active panoramic vision, the tunnel regular maintenance for subway and high ferro provides effective technical support.
Description
Technical field
The present invention relates to panorama LASER Light Source, omnibearing vision sensor, Digital Image Processing, Three Dimensional Reconfiguration and
Application of the computer vision technique in terms of the automatic detection in tunnel and three-dimensional modeling, more particularly to one kind are based on active panorama
The full section of tunnel high speed dynamical health detection means and method of vision, during being mainly used in subway and the operation of high ferro tunnel
Automatic health monitors.
Background technology
The health monitoring in subway and high ferro tunnel can be divided into two stages：Construction stage and operation stage.In railway tunnel
Operation during, the safety problem in tunnel is mainly influenceed by the following aspects：It is first, long-term in train operation process
Railway roadbed bulk settling caused by oscillatory load；Two be due to that most of major long tunnels are in complicated geological conditions, train lotus
The differential settlement of circuit caused by load in the axial direction；It is exactly finally the influence of tunnel perimeter building.And these influence meeting
The cracking of tunnel contour is caused, is deformed, a series of safety problems such as leak even comes off.
At present, the own comparative maturity of monitoring technology in constructing tunnel stage is directed to both at home and abroad, but during runing tunnel
It is far from enough to monitor attention degree.In fact, operation stage because time span is big, influence factor is complicated, disaster social influence is big,
Health monitoring to subway and high ferro tunnel more should sufficiently be paid attention to.The detection of tunnel contour can easily grasp tunnel
Headroom, the deformation in tunnel is monitored, therefore tunnel structure detection occupies an important position in railway transport course.
In the O＆M stage in tunnel, in order to not influence railroad embankment, the blank time can only be utilized, and during blank
Between be certain, this just needs rapidly to be detected, and the mode of traditional point standing posture Measure section deformation obviously can not meet
It is required that.The demand developed according to high ferro and city underground, high speed dynamical health monitoring is carried out to full section of tunnel, and require to monitor
Process can be synchronous with train operation, is easy to administrative staff in real time, continuously, rapidly to grasp tunnel change, fortune of eliminating the effects of the act in time
Defeated safe hidden danger.Require that completing section detects collection, analysis, processing, the transmission of data in the process, and quickly provide phase
The profiled outline and the threedimensional model in tunnel answered, so monitor and analyze various potential safety hazards in real time.
Tunnel testing has that the gradually changeable of tunnel deformation and chronicity, measuring point are more, circuit is long, amount of dynamic data is big, data
Analyze the features such as complicated.Contactless vehicle-mounted tunnel cross-section detection turns into main flow detection technique.At present, contactless vehicle-mounted tunnel
Road section detection scheme mainly employs laser technology and computer image processing technology etc..And it is widely used in domestic and international elder generation
On the track detection vehicle entered, detection efficiency is greatly improved.Have than more typical：The French use to come into operation in 2005
, can be in 300km speed by way of photogrammetric to improve the infrastructure high-speed detection train MGV of high-speed line maintenance
Contact net, track etc. are detected under degree；The GeoRail-Xpress synthetic detection vehicles of Germany can to visible on circuit and
Invisible part carries out totally digitilized measurement, collection and analysis；Be equipped with thereon by 4 dimension orbital environment cameras into circuit
And environmental detection set, the track detection device being made up of 6 laser sensors and 2 frame number line scan cameras, detection speed
Spend for 100km/h；The East-I types that Japanese track synthetic detection vehicle is come into operation with March, 2002 are most representative, the train
It is electric EMU using 700,6 are organized into groups, it is possible to implement 88 detection projects, wherein being used using the camera device at the top of train
Image processing techniques measures the situation of railway roadbed and peripheral structure thing, highest running speed 275km/h；The Plasser of Austria is public
Take charge of the EM250 type high speed track checking cars that speed per hour is 250km/h, Italian " Archimedes " number synthetic detection vehicle etc. and be all equipped with utilization
The velocity tunnel detection device of photogrammetric technology or laser assisted image processing techniques.
In summary, detected on laser technology and computer image processing technology in vehicle-mounted tunnel cross-section main excellent scarce
Putting is：Laser scanning measurement is not disturbed by ambient, but due to being limited by scanning point effect weakening, measures compound section
When precision it is low, problem is that scanning distance measuring method is restricted during traveling scanning point twist by mechanical gyro unit
Advance, scan frequency is not easy to be made too high, and point position measured in high speed traveling process is not at a cross section
Interior, this belongs to original reason error, it is necessary to improves measurement accuracy by repeatedly reciprocal measurement, is unfavorable for the survey to long distance tunnel
Amount.Simultaneously because repeatedly reciprocal dynamic measurement is high to positioning accuracy request, implement also more difficult.Therefore, some researchers
Propose using 30 ° of interval, 9 laser scanners of installation while tunnel cross-section be scanned, this also undoubtedly improve input and
O＆M cost, and such scanning is also only limited to several points, can not realize full face real time scan.
Although computer picture triangle is photogrammetric with higher dynamic measurement precision, during measurement easily by sunlight,
The ambient such as light disturbs and produces deviation in tunnel, is even failed when serious.Therefore complicated image procossing must be used
Algorithm progress is a certain degree of to be made up, such as by two-dimensional filtering and mode identification technology, is filtered out light image, identified Tunnel
Laser light belt position on wall etc..And common dynamic the measurement request per second hundreds of even sampling rate of thousands of frames, at present
Technology is difficult to the real-time storage of all images data, and laser light belt position is extracted and stored if by image processing techniques
Put, then image processing step can greatly increase processing time again, system for restricting sample rate, influence the real-time of system, uncomfortable
Together in the safety monitoring in high speed traveling process.
Therefore, how under high speed dynamic measuring condition simultaneously ensure high measurement accuracy, high sampling rate and quick three-dimensional
Modeling is that subway and high ferro tunnel monitor important topic automatically.
Chinese invention patent application number discloses one kind laser measurement building or cave profile section for 87101789,
It employs tuning fork slit oscillator in angle-measuring equipment, uses the step-by-step counting of three-level optical disc in transmission system and reset electric
Road, measurement accuracy have reached ± 2.5%, can obtain the pole coordinate parameter of section immediately through MICROCOMPUTER PROCESSING simultaneously in measurement, maximum
The numerical value such as clear height and clear span, section net area.The problem of this technology is primarily present is unsuitable in high speed traveling process
Monitoring.
Chinese invention patent application number is that 201410121950.X discloses a kind of tunnel safety tool car and detection method,
Examination and repair system includes switch board, display screen, front distance sensor, rear range sensor, swivel bearing mechanism and detection means；Letter
Breath acquisition system includes Universal rotary support, 3D holographic scanners and information storage module.The invention claims can be automatically and rapidly
Detection inner surface of tunnel there is crack or region the problems such as top layer comes off, while realizing rapid-maintenance, to tunnel
Zonal 3D information gatherings are carried out, foundation is provided for the later stage, so as to lift the efficiency of maintenance and information gathering and maintenance
Effect.But this technology scanning element is extremely limited, and any processing is not carried out to 3D holoscans result, it is still desirable to artificial
Holoscan image is observed to be identified.
Chinese invention patent application number be 201410009353.8 disclose a kind of intelligent inspection device of railway tunnel and its
Application method, inspection device include control mainboard, cabinet, secondary light source, digital camera and alarm；Installed in control mainboard special
Use software；The digital photograph that special-purpose software is shot to digital camera is analyzed, handled and preserved；When result is beyond setting
During scope, alarm work；But had no in the patent and the image captured by digital camera is carried out in Automatic analysis
Hold and three-dimensional measurement is carried out to full section of tunnel.
Tunnel health monitoring includes tunnel structure and corrodes monitoring, structural deformation monitoring, structural internal force measure and ambient conditions
Monitoring, wherein especially structural deformation monitoring is extremely important, its Contents for Monitoring is mainly Longitudinal Settlement (the longitudinal axis change in tunnel
Shape), the convergent deformation of lateral displacement and section.
Several performance requirements of full section of tunnel high speed dynamical health detection method：1. the requirement of IMAQ speed；System
System is installed on Tunnel testing car, and under 120km/h detection speed, frequency acquisition will meet that at least collection one is comprehensive per 0.1m
Make and break face；2. the requirement of measurement accuracy；5mm must be less than to the static measurement error in the space of section；3. the requirement of reliability；Institute
The necessary stability of the hardware device of selection is high, and system must be able to the requirement for meeting long-time continuous stable operation；4. automation is strong
The requirement of health diagnostic assessment；The deformation of tunnel generation is automatically analyzed, establishes tunnel deformation Three-Dimensional Dynamic model, and is formed corresponding
Early warning mechanism；Required 5. operation and maintenance is simplified；To full section of tunnel carry out high speed dynamical health monitoring, the collection of data,
Analysis, processing, transmission are to be automatically performed, it is not necessary to artificial intervention.
The content of the invention
In order to overcome, the automation and intelligent level of existing tunnel health detecting method are low, are difficult to enter tunnel
The deficiencies of row high-acruracy survey, high sampling rate and quick three-dimensional modeling, the present invention provide a kind of for entering to full section of tunnel
Row high speed dynamical health is monitored, it is possible to increase tunnel health detection is automated and intelligent level, the malformation to tunnel are entered
Row is high-precision to be automatically analyzed and assesses, and realizes that tunnel deformation Three-Dimensional Dynamic models.
Realize foregoing invention content, it is necessary to solve five key problems：(1) a kind of panorama LASER Light Source is realized；(2)
Realize that a kind of energy quick high accuracy obtains the active panoramic vision sensor of actual object depth information；(3) accurately estimate
Longitudinal mileage coordinate of orbital direction；(4) using computer vision technique to the three-dimensional rebuilding method in tunnel；(5) establish empty
Spatial database storage issue tunnel deformation data establishes tunnel deformation Three-Dimensional Dynamic model, and forms early warning mechanism.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of full section of tunnel high speed dynamical health detection means and method based on active panoramic vision, its hardware bag
Include：Tunnel testing car, active panoramic vision sensor, RFID reader, wirelessly receive and send unit, controller, station level communication
System or central monitoring center server；Described central monitoring center server is made up of complete described station level communication system
Tunnel safety detects net, and what the reception of described station level communication system configured from described Tunnel testing car wirelessly receives and sends unit
The tunnel cross section laser scanning image sended over, and tunnel cross section laser scanning image is pacified by full tunnel in time
Full inspection survey grid sends described central monitoring center server to.
Active panoramic vision sensor, RFID reader are configured with described Tunnel testing car, measuring wheel, is wirelessly connect
Transmitting element and controller, described active panoramic vision sensor are arranged on the central front of described Tunnel testing car,
Described RFID reader reads the RFID information that configuration disposes on tunnel inner wall, the bottom installation of described Tunnel testing car
One measuring wheel, described controller read the pulse equivalency of photoelectric encoder in measuring wheel and estimate described Tunnel testing car
Travel distance Zi；Described controller reads the tunnel cross section laser scanning figure acquired in active panoramic vision sensor
As and with the travel distance Z of described Tunnel testing cariIt is the storage that filename is stored in described controller with present moment
In unit；When described Tunnel testing car reaches next website, described controller wirelessly receives and sends list by described
Tunnel cross section laser scanning image in the memory cell of described controller is sent to described station level communication system by member.
Described active panoramic vision sensor, its hardware mainly include：Omnibearing vision sensor, panorama laser are thrown
Penetrate light source；Described omnibearing vision sensor is fixedly and coaxially connected with described panorama laser projection light source.
The omnibearing vision sensor includes hyperboloid minute surface, upper lid, transparent semicircle outer cover, lower fixed seat, shooting
Unit fixed seat, image unit, connection unit and upper cover；Described hyperboloid minute surface is fixed on described upper lid, described
Connection unit links into an integrated entity described lower fixed seat and transparent semicircle outer cover, described transparent semicircle outer cover with it is described
Upper lid and described upper cover be fixed together, described image unit is fixed in described image unit fixed seat, institute
The image unit fixed seat stated is fixed on described lower fixed seat, the described shooting in described omnibearing vision sensor
The output of unit is connected by kilomega network data-interface with described controller.
Described panorama laser projection light source includes lid, conical minute surface, transparent housing, ring shape Laser emission on light source
Device and base；Ring shape generating laser is fixed on base, the transmitting light axial line and datum axle of ring shape generating laser
Heart line is consistent, and conical minute surface is fixed on to cover on light source is for reflecting the circle laser that ring shape laser transmitter projects come out
Tunnel inner wall provides tunnel disconnected section panoramic scanning light, and the axial line of conical minute surface is consistent with lid axial line on light source, transparent
The base for securing ring shape generating laser and lid on the light source for securing conical minute surface are integrated into panorama laser by outer cover
Projection source；The center overlapping of axles of the central shaft of ring shape generating laser and conical minute surface.
When described active panoramic vision sensor assembles, by the central shaft of described ring shape generating laser, institute
The central shaft arrangement of the central shaft for the conical minute surface stated, the central shaft of described hyperboloid minute surface and described image unit exists
On same axial line.
Before Tunnel testing car will enter tunnel, alignment system can provide the positional information of Tunnel testing car, when tunnel is examined
When measuring car position and tunnel portal mileage are in the range of 10 meters, control machine starts measuring system, active panoramic vision sensor
Into collection information state, simultaneity factor clock system starts, the corresponding temporal information of record each position information.
Tunnel mouth, hole Nei Hechu holes installation electronic tag spaced apart, amendment mileage positioning is aided in complete using RFID
Section is accurately positioned.
When Tunnel testing car travels in a detector segments, except needing to obtain tunnel cross-section relative to measuring system
X, outside Y-coordinate, longitudinal mileage coordinate Z of direction along ng a path should be also obtained, for determining the position of each Measure section in tunnel,
That is accurate distance of the section away from measurement original position.Need distance travelled to detect the real-time of Tunnel testing car for this.
In Tunnel testing car bottom installation measuring wheel, advance, measuring wheel does pure rolling, the wheel shaft of steamboat in orbital plane
It is upper that photoelectric encoder is housed, the distance that steamboat passes by rail level can be read according to encoder.
The tunnel that described central monitoring center server receives Tunnel testing car by full tunnel safety detection net is horizontal
After section laser scanning image, the travel distance Z of described Tunnel testing car is read firstiWith the tunnel that present moment is filename
Road cross section laser scanning image；Then panorama laser on tunnel cross section is parsed from tunnel cross section laser scanning image
The spatial coordinate location value in incident point, i.e., the three dimensional point cloud on tunnel cross section；Then with the walking of Tunnel testing car away from
From ZiTunnel cross section on three dimensional point cloud reconstruct full tunnel inner wall threedimensional model；Finally according to the complete of newest structure
Tunnel inner wall threedimensional model is contrasted with the full tunnel inner wall threedimensional model initially built, analyzes tunnel deformation quantity.
The acquisition of tunnel cross-section cloud data, the acquisition mode of tunneling data is regarding with active panoramic vision sensor
Centered on point, the travel distance Z of Tunnel testing car is parsediTunnel cross section on tunnel face on target point (x, y) it is flat
Face two-dimensional coordinate, then according to travel distance ZiCalculating has (x, y, z) three-dimensional coordinate of a cloud in tunnel face.
Omnibearing vision sensor demarcating module, for determining the X-Y scheme in three dimensions point and video camera imaging plane
The parameter of mapping relations between picture point, calibrated parameter are stored in described memory cell.
Comprehensive face laser intelligence parsing and cloud data acquiring unit, for being carried out to laser scanning panoramic image data
Processing, laser projection information is parsed on laser scanning panoramic picture and calculates spatial positional information, finally gives tunnel
Inner wall edge cloud data.
Tunnel axis extraction unit, for drawing tunnel linear deformation figure according to tunnel axis, to carry out three-dimensional modeling；
Here will be along continuous 10 scanning cross-sections in tunnel axis direction as a section, each adjacent scanning in laser scanning above
Section is at intervals of 100mm, and thus by the cloud data unit of 1000mm in a section to extract axis, extracting the method for axis is
Face of cylinder fitting is carried out to the tunnel point cloud after segmentation.
Noise reduction and adjustment processing unit, the length for further handling to obtain to described tunnel axis extraction module are
1000mm tunnels cloud data carries out noise reduction and adjustment processing.
Three-dimensional modeling and deformation analysis unit, for tunnel deformation visualization processing；It is mainly identical in tunnel by comparing
Deformation quantity on position, with reflect that tunnel is local or a certain section in convergent deformation situation.
Full tunnel profile concatenation unit, for the segmented three-dimensional reconstruction result in full tunnel to be spliced.
Displacement monitoring and settlement monitoring unit, global displacement and sedimentation to tunnel have the measurement of quantization.
Tunnel profile become shifting amount three-dimensional visualization unit, for the global displacement to tunnel and sedimentation have quantization, can
Depending on the expression of change；Three-dimensional visualization handles the numerical value that measurement is obtained, deflection information is changed into intuitively, with Figure and Image
It is representing, with the physical quantity of time and spatial variations be presented to tunnel safety monitoring personnel；Here positive deformation is represented with red, used
Blueness represents that negative shape becomes, and color, which is more deeply felt, shows that deformation is bigger；For RGB color, GB color components are arranged to zero, R
Component aligns deformation data from 0~255 and mapped, corresponding to 0~255mm positive deformation；RG color components are arranged to zero,
G components map from 0~255 pair of negative deformation data, become corresponding to 0~-255mm negative shape；Then to full tunnel central shaft
It is color-coded on the section corresponding to tunnel corresponding to the vertical section deformation quantity each saved on line；Finally according to full tunnel center
Coordinate value on axis connects broken line mode is each saved on central axis, shows that whole tunnel is indulged with visual means
The deformation situation of section.
Beneficial effects of the present invention are mainly manifested in：
1) a kind of brand-new automation tunnel health examination mode is provided；
2) gather the three-dimensional spatial information in tunnel in time during physical examination is done to subterranean tunnel, be Urban underground Tunnel
Three-dimensional modeling provides and primitively descends basic spatial database；
3) automatically detection judges existing various defects in tunnel, is provided for the maintenance of subterranean tunnel, final acceptance of construction
Effective technical support.
Brief description of the drawings
Fig. 1 is a kind of structure chart of omnibearing vision sensor；
Fig. 2 is single view catadioptric omnibearing vision sensor imaging model, Fig. 2 (a) perspective imaging processes, and Fig. 2 (b) is passed
Sensor plane, Fig. 2 (c) planes of delineation；
Fig. 3 is the schematic diagram that active panoramic vision sensor carries out tunnel inner wall range measurement；
Fig. 4 is the structure chart of panorama laser projection light source；
Fig. 5 is a kind of structure chart of active panoramic vision sensor；
Fig. 6 is the schematic diagram for carrying out laser scanning inspection to tunnel inner wall using active panoramic vision sensor；
Fig. 7 is a kind of macroscopical schematic diagram of totality detected using active panoramic vision sensor subterranean tunnel；
Fig. 8 is saved in the case of some azimuth of omnibearing vision sensor for one in tunnel inner wall, radial deformation
Amount and the distribution relation figure of cloud data；
Fig. 9 is tunnel longitudinal deformation schematic diagram；
Figure 10 is tunnel lateral direction deformation schematic diagram；
Figure 11 is the tunnel graphics reconstructed with point cloud；
Figure 12 is the process chart that Tunnel testing car carries out tunnel health examination；
Figure 13 is the spliced one section of tunnel figure of Surface Reconstruction from Data Cloud from tunnel collection；
Figure 14 is several important geometry variable schematic diagrames on tunnel inner wall surface；
Figure 15 is tunnel cross sectional profile diagram；
Figure 16 is that deformation process chart in tunnel is analyzed and processed in central monitoring center server.
Embodiment
Embodiment 1
Reference picture 1~16, a kind of full section of tunnel high speed dynamical health detection means based on active panoramic vision with
Method, its hardware include：Tunnel testing car, active panoramic vision sensor, RFID reader, wirelessly receive and send unit, control
Device, station level communication system or central monitoring center server processed.Central monitoring center server is made up of station level communication system
Full tunnel safety detection net, what the reception of station level communication system configured from Tunnel testing car wirelessly receives and sends what unit sended over
Tunnel cross section laser scanning image, and tunnel cross section laser scanning image is detected into net by full tunnel safety in time and passed
Give central monitoring center server.
Active panoramic vision sensor, RFID reader are configured with Tunnel testing car, measuring wheel, wirelessly receives and sends list
Member and controller, active panoramic vision sensor are arranged on the central front of Tunnel testing car, and RFID reader reads configuration
A measuring wheel is installed in the RFID information disposed on tunnel inner wall, the bottom of Tunnel testing car, and controller is read in measuring wheel
The pulse equivalency of photoelectric encoder and the travel distance Z for estimating Tunnel testing cari；Controller reads active panoramic vision sensing
Tunnel cross section laser scanning image acquired in device and with the travel distance Z of Tunnel testing cariIt is filename with present moment
It is stored in the memory cell of controller；When Tunnel testing car reaches next website, controller is by wirelessly receiving and sending list
Tunnel cross section laser scanning image in the memory cell of controller is sent to station level communication system by member.
Active panoramic vision sensor, its hardware mainly include：Omnibearing vision sensor, panorama laser projection light
Source；Omnibearing vision sensor is fixedly and coaxially connected with panorama laser projection light source.
Omnibearing vision sensor, as shown in Figure 1, including hyperboloid minute surface 2, upper lid 1, transparent semicircle outer cover 3, under
Fixed seat 4, image unit fixed seat 5, image unit 6, connection unit 7 and upper cover 8.Hyperboloid minute surface 2 is fixed on lid 1,
Connection unit 7 links into an integrated entity lower fixed seat 4 and transparent semicircle outer cover 3, transparent semicircle outer cover 3 and upper lid 1 and on
Cover 8 is fixed by screws in together, and image unit 6 is screwed in image unit fixed seat 5, image unit fixed seat 5
It is screwed on lower fixed seat 4, the output of the image unit in omnibearing vision sensor passes through kilomega network data-interface
It is connected with controller.
The sample frequency of image unit is needed under 120km/h detection speed, and frequency acquisition will meet at least per 0.1m
A tunnel cross section is gathered, sample frequency is calculated and meets to be more than 333.3fps conditions.The sampling resolution of image unit,
According to the requirement of measurement accuracy, 5mm must be less than to the static measurement error in the space of section；The detection of omnibearing vision sensor
Imaging center is 3m from the longest distance of tunnel edge, corresponding to a half range of the imager chip short-and-medium axle of video camera, if not
If considering that interpolation improves resolution ratio, the sampling resolution of image unit needs more than 1200 pixels.Summary situation, takes the photograph
As the high-speed camera of Unit selection CR3000 × 2, resolution ratio is 1696 × 1710, sample frequency 540fps, high-speed internal memory 16GB.
Panorama laser projection light source includes lid, conical minute surface, transparent housing, ring shape generating laser and bottom on light source
Seat.Ring shape generating laser is fixed on base, transmitting light axial line and the base axial line one of ring shape generating laser
Cause, it is in tunnel that conical minute surface, which is fixed on and covered on light source for reflecting the circle laser that ring shape laser transmitter projects come out,
Wall provides tunnel disconnected section panoramic scanning light, and the axial line of conical minute surface is consistent with lid axial line on light source, and transparent housing will
Lid is integrated into panorama laser projection light on the base for securing ring shape generating laser and the light source for securing conical minute surface
The center overlapping of axles of source, the central shaft of ring shape generating laser and conical minute surface.Active panoramic vision sensor assembling
When, by the central shaft of ring shape generating laser, the central shaft of conical minute surface, hyperboloid minute surface central shaft and image unit
Central shaft arrangement on same axial line.
Before Tunnel testing car will enter tunnel, alignment system can provide the positional information of Tunnel testing car, when tunnel is examined
When measuring car position and tunnel portal mileage are in the range of 10 meters, control machine starts measuring system, active panoramic vision sensor
Into collection information state, simultaneity factor clock system starts, the corresponding temporal information of record each position information.
Tunnel mouth, hole Nei Hechu holes installation electronic tag spaced apart, i.e. RFID, amendment mileage is aided in determine using RFID
Complete being accurately positioned for section in position.
RFID be fixed on tunnel mouth, hole Nei Hechu holes it is spaced apart on, here by the tunnel at fixed RFID
The datum mark of road section and the intersection point of tunnel axis as measurement, is tunnel building uniform coordinate benchmark Bi(x,y,z)；RFID
Memory cell in store the spatial positional information B of tunnel fixing pointi(x,y,z)；The spatial positional information B of tunnel fixing pointi
(x, y, z) be after tunnel is built up through pinpoint high-acruracy survey obtained by；The spatial positional information B of tunnel fixing pointi(x,y,z)
Fixed cycle is needed to be safeguarded and corrected during tunnel operation, to ensure these spatial positional informations Bi(x, y, z) can make
For the absolute coordinate benchmark in tunnel.
Controller includes：RFID data reading unit, for reading the space bit for being fixed on RFID in tunnel wall and being stored
Confidence ceases；Running distance evaluation unit, by reading the umber of pulse of photoelectric encoder and estimating Tunnel testing using formula (3)
The running distance of car；Tunnel cross section laser scanning image is read, memory cell, for reading active panoramic vision sensor
Acquired tunnel cross section laser scanning image, and with the travel distance Z of Tunnel testing cariProtected with present moment for filename
In the memory cell that controller be present；Tunnel cross section laser scanning image data transmission unit, for by the storage of controller
Tunnel cross section laser scanning image in unit is sent to station level communication system；Accompanying drawing 12 is that controller carries out tunnel health body
The process chart of inspection.
When Tunnel testing car travels in a detector segments, except needing to obtain tunnel cross-section relative to measuring system
X, outside Y-coordinate, longitudinal mileage coordinate Z of direction along ng a path should be also obtained, for determining the position of each Measure section in tunnel,
That is accurate distance of the section away from measurement original position, need distance travelled to detect the real-time of Tunnel testing car for this.
The dynamic positioning of Tunnel testing car relies primarily on photoelectric encoder, and a ranging is installed in the bottom of Tunnel testing car
Wheel, determine Tunnel testing car original position with reference to track-circuit signalling and eliminate longitudinal cumulative errors.Photoelectric encoder can be with
1000~2000 pulses of output/turn, travelled by vehicle can be calculated according to the number of pulses and measuring wheel wheel diameter that collect
Distance, it is fixed to be improved using many algorithms such as FT methods, slide system skidding algorithm, Multi-sensor Fusion algorithms in practical application
The precision of position.Meanwhile mileage alignment system can also calibrate Tunnel testing car initial position, fixed point according to track-circuit signalling clearly
Except the cumulative errors in dynamic measurement process.
In Tunnel testing car bottom installation measuring wheel, advance, measuring wheel does pure rolling, the wheel shaft of steamboat in orbital plane
It is upper that photoelectric encoder is housed, the distance that steamboat passes by rail level can be read according to encoder.If a diameter of D of steamboat, is loaded on
P is elected in the graduation of photoelectric encoder thereon as, and the pulse equivalency that encoder is calculated by formula (1) is (suitable per individual pulse
In the air line distance that steamboat is passed by) δ,
A diameter of Φ 58 of measuring wheel, the photoelectric encoder graduation on measuring wheel are 2000, and the pulse equivalency of encoder is used
Formula (2) is calculated,
The travel distance Z of Tunnel testing cariZ pulse is sent with photoelectric encoder to be calculated, computational methods such as formula
(3) shown in,
Zi=Z δ=0.0911Z (3)
In order to allow be arranged on Tunnel testing car on active panoramic vision sensor acquired in tunnel cross section laser
Scan image is associated with locus during captured image, uses the travel distance Z with Tunnel testing car hereiFor text
Part name preserves tunnel cross section laser scanning image data；When the station level in Tunnel testing car process of passing through tunnel wirelessly
Tunnel cross section laser scanning image data are sent to central monitoring center server through station level communication system.
The tunnel health detection flow of Tunnel testing car as shown in Figure 12, Tunnel testing car will enter tunnel before, tunnel
Control machine on road detection car, which is read, is fixed on the spatial positional information that RFID in tunnel wall is stored, and control machine starts measurement system
System, active panoramic vision sensor enter collection information state, and simultaneity factor clock system starts, and records each position
The corresponding temporal information of information simultaneously calibrates the initial position of Tunnel testing car；Controller reads photoelectric encoder in measuring wheel
Pulse equivalency and the travel distance Z for estimating Tunnel testing cari；Controller reads the tunnel acquired in active panoramic vision sensor
Road cross section laser scanning image and with the travel distance Z of Tunnel testing cariIt is that filename is stored in controller with present moment
Memory cell in；When Tunnel testing car reaches next website, controller is by wirelessly receiving and sending unit by controller
Tunnel cross section laser scanning image in memory cell is sent to station level communication system；As Tunnel testing car is with 120km/h
Speed move ahead, controller constantly read tunnel cross section laser scanning image acquired in active panoramic vision sensor and
Read the pulse equivalency of photoelectric encoder in measuring wheel and estimate the travel distance Z of Tunnel testing cari, and with Tunnel testing car
Travel distance ZiIt is that filename is stored in the memory cell of controller with present moment, until when the control on Tunnel testing car
It is machine-readable that to take the information being fixed in tunnel wall in RFID be tunnel exit；Now, controller stops passing to active panoramic vision
Sensor acquisition view data, the panorama laser projection light source closed in active panoramic vision sensor, and by tunnel exit
The tunnel cross section laser scanning image hair being fixed in spatial positional information and memory cell that RFID in tunnel wall is stored
Give station level communication system；So Tunnel testing car is scanned to the health examination end of scan in tunnel, the health examination in tunnel
Cross section laser scanning image obtained in journey is sent to the full tunnel in central monitoring center server through station level communication system
In the laser scanning image storehouse of road cross section.
The tunnel cross section that central monitoring center server receives Tunnel testing car by full tunnel safety detection net swashs
After photoscan picture, the travel distance Z of Tunnel testing car is read firstiWith the tunnel cross section laser that present moment is filename
Scan image；Then the space of panorama laser projection point on tunnel cross section is parsed from tunnel cross section laser scanning image
Coordinate position value, i.e., the three dimensional point cloud on tunnel cross section；Then with the travel distance Z of Tunnel testing cariTunnel it is horizontal
Three dimensional point cloud on section reconstructs full tunnel inner wall threedimensional model；It is finally three-dimensional according to the full tunnel inner wall of newest structure
Model is contrasted with the full tunnel inner wall threedimensional model initially built, analyzes tunnel deformation quantity.
Mainly include in central monitoring center server：Omnibearing vision sensor demarcation unit, active panoramic vision
It is transducer calibration database, J sections tunnel cross-section view data reading unit, full tunnel cross section laser scanning image storehouse, complete
Azimuth plane laser intelligence parses and cloud data acquiring unit, tunnel axis detection unit, noise reduction and adjustment processing unit, three
Dimension modeling and deformation analysis unit, full tunnel respectively save cross section benchmark database, full tunnel profile concatenation unit, displacement monitoring
Axis coordinate reference data storehouse, full tunnel health examination result database and tunnel are respectively saved with settlement monitoring unit, full tunnel
Vertical section becomes shifting amount three-dimensional visualization unit；Handling process is as shown in Figure 16.
Omnibearing vision sensor demarcates unit, for determining the X-Y scheme in three dimensions point and video camera imaging plane
The parameter of mapping relations between picture point, the omnibearing vision sensor of single view is employed in of the invention, by hyperboloid catadioptric
The omnibearing vision sensor that mirror image principle is formed has single view imaging characteristic；Its image-forming principle is as shown in Figure 3.In order to
The mapping relations established in three dimensions point and imaging plane picture point, here using Micus í k perspective projection imaging model,
As shown in Fig. 2 in the imaging model, two different reference planes, the plane of delineation (u', v') and sensor plane are considered
(u ", v "), the plane of delineation is related to the CCD of video camera, is represented with pixel coordinate system.Sensor plane be one assume and
The orthogonal plane of minute surface optical axis, its center origin are the intersection points of optical axis and the plane；With the focus of hyperboloid minute surface, i.e. single view
OmCoordinate system, z " axle and minute surface optical axis alignment are established for origin；If X=[X, Y, Z]TFor in space a bit, u "=[u ", v "]TIt is
X is in the projection of sensor plane, u'=[u', v']TIt is the pixel of its corresponding plane of delineation；Space coordinates point X is first passed through
Projective transform matrix is projected on minute surface at A points, and A points focus on camera optics central point C by mirror-reflection, and hand over sensor
U in plane "=[u ", v "]TPoint, u " point pass through affine transformation to point u'=on the plane of delineation [u', v']T；Whole single view is catadioptric
Penetrate camera imaging model to describe by spatial point to catadioptric mirror point, the point on catadioptric mirror point to imaging plane,
The process for the pixel that point on imaging plane is formed in image to plane of delineation point again.
Catadioptric minute surface is represented to the conversion between sensor plane with formula (17)；
In formula, X ∈ R4Representation space point X secondary coordinate, and P=[R | T] ∈ R3×4For projective transform matrix, R ∈ R3×3For sky
Between point to catadioptric mirror point spin matrix, T ∈ R3×1Translation matrix for spatial point to catadioptric mirror point.
Represented by sensor plane to the conversion the plane of delineation with formula (18)：
U "=Au '+t (18)
In formula, A ∈ R2×2, t ∈ R2×1。
Scaramuzza replaces formula on the basis of Micusik perspective projection models with a function f=g/h
(17) function g, h in, i.e., the relation between three dimensions point and two dimensional surface point is characterized with function f, obtains formula (19),
Due to bi-curved rotational symmetry, Scaramuzza deploys multinomial come described function f with Taylor, uses formula
(20) represent：
F (| | u " | |)=a0+a1||u″||+a2||u″||2+...+an||u″||N (20)
In formula, | | u " | | for the distance of the point on imaging plane to the planar central point.
The premise of Scaramuzza and Micusik model is all preferable catadioptric camera model, due to actually adding
Work can introduce some errors when assembling omnibearing vision sensor；It is assumed here that the omnibearing vision sensor of demarcation meets ideal
Model, there will be the simplified model conversion formula that the non-ideal model of certain error substitutes into Scaramuzza propositions, obtain public affairs
Formula (21)；
Specific calibration process is that around omnibearing vision sensor one week scaling board is shot into some groups of panoramic pictures, foundation
Some equatioies of pixel in spatial point and imaging plane, optimal solution, the result of calculation such as institute of table 1 are obtained using optimization algorithm
Show, be the calibrating parameters of the omnibearing vision sensor used in the present invention；
The ODVS of table 1 calibration result
After the inside and outside parameter for calibrating omnibearing vision sensor, picture point and incident light with regard to an imaging plane can be established
Corresponding relation between line, i.e. incidence angle, as formula (5) represents；
In formula, αβThe incidence angle of tunnel inner wall certain point is represented, | | u " | | put down for the point on imaging plane to image
The distance of face central point, a0、a1、a2、aNFor the inside and outside parameter of the omnibearing vision sensor of demarcation, one is established by formula (5)
Open the mapping table between imaging plane any pixel point and incidence angle；Specific derivation and implementation method on calibration formula
See reference document, Yi-ping Tang, QingWang, Ming-li Zong, Jun Jiang, and Yi-hua Zhu, Design
Of Vertically Aligned Binocular Omnistereo Vision Sensor, EURASIP Journal on
Image and Video Processing, 2010, P1~24；Calibrated result can establish image coordinate and locus
Between mapping relations, as shown in Figure 3；Calibration result is stored in active panoramic vision sensor nominal data storehouse.
J saves tunnel cross-section view data reading unit, for full tunnel cross section laser scanning image to be segmented
Analysis；Since the entrance in tunnel untill outlet, full tunnel is divided into some sections, by the use of h (j) as section variable, h (j) with
Tunnel testing car is along the displacement Z on tunnel longitudinal directioniBetween relation with formula (16) represent,
H (j)=INT (Zi/10)+1 (16)
After it have chosen a certain section h (j), the displacement Z included in the section is obtained according to formula (16)i, then with
All displacement Z in the sectioniAs filename tunnel cross section is read from full tunnel cross section laser scanning image storehouse
Laser scanning image.
Comprehensive face laser intelligence parsing and cloud data acquiring unit, for displacement Z all in h (j) sectionsi
Tunnel cross section laser scanning image handled, obtain tunnel inner wall edge cloud data；Parsing is in laser scanning panorama
The method in the red laser incident point on image is to be greater than according to the brightness of the pixel in red laser incident point on imaging plane
Mean flow rate, be that the RGB color of panorama sketch is changed into HIS color spaces first, then will be on imaging plane it is flat
1.2 times of threshold values as extraction red laser incident point of equal brightness, in order to obtain the accurate location of laser projection line, the present invention
The center of laser projection line is extracted using Gaussian approximation method, specific implementation algorithm is：
Step1：Initial orientation angle beta=0 is set；
Step2：Retrieved on laser scanning panoramic picture with azimuthal angle beta since the central point of laser scanning panoramic picture
Red laser incident point, for, there is the pixel that several continuous red lasers project, selecting HIS here in azimuthal angle beta
Three contiguous pixels of the I component in color space, i.e. brightness value close to peak estimate laser by Gaussian approximation method
The center of the incident line；Circular is provided by formula (7),
In formula, f (i-1), f (i) and f (i+1) are respectively brightness value of three adjacent pixels close to highest brightness value, and d is
Correction value, i represent the ith pixel point since image center；Therefore the center of obtained laser projection line is estimated
For (i+d), the value corresponds in formula (5) | | u " | |；
Step3：The incident angle α of the laser projection point is calculated with formula (5)β, and according to laser scanning panoramic picture number
According to filename information, i.e., with displacement ZiFor the form of filename, Tunnel testing car is obtained along tunnel longitudinal direction
Displacement Zi, then Tunnel testing car is calculated along the displacement Z on tunnel longitudinal direction with formula (4)iAnd azimuth
Laser projection point in the case of β '=β on tunnel inner wall is to the distance between the central axis of active panoramic vision sensor
d(z,β)；The spatial coordinate location value of the laser projection point is finally calculated with formula (8)；
In formula, ZiRegarded for Tunnel testing car along the displacement on tunnel longitudinal direction, H panoramic scannings light to comprehensive
Feel the single view O of sensormAir line distance, d(z,β)For along the position Z on tunnel longitudinal directioniWith azimuthal angle beta '=β situations
Under laser projection point on tunnel inner wall to the distance between the central axis of active panoramic vision sensor, x, y, z points
Not Wei laser projection point relative to the single view O of omnibearing vision sensormCoordinate value, β is azimuth；
Step4：Change azimuth to continue to retrieve laser projection point, i.e. β=β+Δ β, Δ β=1；
Step5：Judge azimuthal angle beta=360, if set up, retrieval terminates；Otherwise go to Step2.
The contour edge cloud data in tunnel lateral direction section has been obtained by above-mentioned processing.
Tunnel axis detection unit, for drawing tunnel linear deformation figure according to tunnel axis, built to carry out three-dimensional
Mould；Here will be each adjacent in laser scanning above along continuous 10 scanning cross-sections in tunnel axis direction as a section
The cloud data unit of 1000mm in one section is thus extracted axis, extracts the side of axis by scanning cross-section at intervals of 100mm
Method is that face of cylinder fitting is carried out to the tunnel point cloud after segmentation, as follows the step of the fitting algorithm of the face of cylinder：
STEP1：Read obtain after the parsing of comprehensive face laser intelligence and the processing of cloud data acquiring unit along tunnel axle
The cloud data in continuous 10 sections in line direction, form three-dimensional coordinate matrix P=(X, Y, Z)；
STEP2：130 points of representational cloud are chosen, as shown in the point in accompanying drawing 11 and accompanying drawing 15, form three-dimensional sit
Mark matrix P(1)=(X(1),Y(1),Z(1))；
STEP3：With u(0)=(X(1),Y(1), π, 0) it is initial value, solved to obtain according to formula (9), (10), (11)
In formula, R(h(j),β)To be fitted the radius on the face of cylinder, eiFor tunnel inner wall marginal point cloud to the distance between axis；
Constraints
U=(x0,y0,λ,φ)T (11)
In formula, x0,y0For the X-coordinate and Y-coordinate value on a fixing point on tunnel axis to be asked, λ is tunnel to be asked
Angle of the axis between the projection line and Z axis of XOZ planes, φ are the angle between tunnel axis to be asked and XOZ planes；
Relation in formula between each variable is as shown in Figure 14；
STEP4：Appropriate increase cloud data forms three-dimensional coordinate matrix P to 13000 points(2)=(X(2),Y(2),Z(2))；
STEP5：WithFor initial value, solved to obtain according to formula (9), (10), (11)
STEP6：Order：
Pi=(X(2),Y(2),Z(2)),
E is calculated using formula (12)i；
In formula：pi=(xi,yi,zi) it is any one measurement point coordinates, c=(x in original point cloud0,y0,z0) it is the face of cylinder
A fixed point coordinates on axis,For the axis direction unit vector on the face of cylinder.
STEP7：Delete eiMore than the point of some critical value, three-dimensional coordinate matrix P is formed(3)=(X(3),Y(3),Z(3))；
STEP8：WithFor initial value, according to formula (9), (10), (11) solve
Arrive
STEP9：Calculate the coordinate of a fixing point and the direction vector of axis in face of cylinder axis：
In above-mentioned calculating, face of cylinder axis is exactly tunnel axis, u1 (i)To correspond to X-coordinate on tunnel axis in
Value, u are approached in axis extraction process2 (i)To correspond to Y-coordinate approaching during axis detection on tunnel axis
Value, u3 (i)It is included angle X of the tunnel axis between the projection line and Z axis of XOZ planes in the value of approaching of axis, u4 (i)For tunnel
In the value of approaching of axis, i is the approximation computation during axis detection for included angle between road axis and XOZ planes
Number, as shown in Figure 14.A point on the central axis that length is 1000mm tunnels has been obtained by above-mentioned algorithm process
And its direction vector.
Noise reduction and adjustment processing unit, the length for further handling to obtain to tunnel axis extraction module are 1000mm
Tunnel cloud data carries out noise reduction and adjustment processing；According to plane strain condition, put cloud in theory at same angle, i.e., for
It is azimuthal angle beta for omnibearing vision sensor, the radial coordinate in tunnel is equal in the case of same azimuthal angle beta；According to measurement
Back propagation net, due to the accidental error of measurement, the tunnel radial coordinate of same azimuthal angle beta will be in normal distribution, i.e.,
WhenWhen, there is relationship below；
A cloud is divided into 360 groups, even β0={ 0 °, 1 °, 2 ° ..., 359 ° }, Statistical Radius coordinate is with putting cloud quantity
Relation；In order to facilitate calculating and observing, with radial displacement ρ in accompanying drawing 8(cs2)- R is used as abscissa, and it is wide to be divided into some 1mm
Section, ordinate represents the point cloud quantity in each section；Radial displacement deviation average is rough error more than the point of 3 times of standard deviations
Point, is deleted；The each group point cloud for traveling through all azimuthal angle betas carries out noise reduction in this manner.
The radial coordinate of same azimuthal angle beta is still unequal after noise reduction, needs to carry out to improve the fitting precision of elliptic cylinder
Adjustment, the measured value of the radial coordinate of same azimuthal angle beta is adjusted to average value, that is, obtains the radial coordinate of same azimuthal angle beta
Average value ρ*；Three-dimensional coordinate matrix is re-formed after adjustment, with cylindrical coordinate P*=(Z(cs2),β*,ρ*) represent；Here
Three-dimensional modeling and deformation analysis unit, for tunnel deformation visualization processing；It is mainly identical in tunnel by comparing
Deformation quantity on position, with reflect that tunnel is local or a certain section in convergent deformation situation；As shown in Figure 10, its algorithm master
Handle as follows：
STEP1：The three-dimensional point cloud coordinates matrix P that importing is represented with cylindrical coordinate*=(Z(cs2),β*,ρ*), initialization process,
J=1；
STEP2：Jth section three dimensional point cloud is read, using ellipse fitting algorithm EFA, by the tunnel contour line point of two dimension
Cloud is fitted to ellipse：
(βe,ρe)=EFA (β*,ρ*)(14)
Realization on ellipse fitting algorithm EFA is referring to paper DELALOYE D.Development of a new
methodology for measuring deformation in tunnels and shafts with terrestrial
laser scanning(LIDAR)using elliptical fitting algorithms[M.S.Thesis][D]
.Kingston：Queen ' s University, 2012；
STEP3：With (βe,ρe) it is directrix, the line segment of parallel Z axis is bus, elliptic cylinder (this that generation length is h (j)
Locate h (j)=1000mm)：
STEP4：The radial displacement ρ of elliptic cylinder each pointe-R(h(j),β)As deflection, the radial displacement of three-dimensional is generated
Cloud atlas；Wherein, ρeIt is calculated with formula (14), R(h(j),β)For measure first full tunnel cross section when formula (14) calculate
Obtain, be stored in full tunnel and respectively save in the benchmark database of cross section；Calculating ρe-R(h(j),β)When made with h (j) and azimuthal angle beta
R is obtained for index(h(j),β)；Here positive deformation is represented with red, represents that negative shape becomes with blueness, color, which is more deeply felt, shows that deformation is bigger；
For RGB color, GB color components are arranged to zero, R component is carried out from the positive deformation data of 0~255 pair of radial displacement
Mapping, corresponding to 0~10mm positive deformation；RG color components are arranged into zero, G components from 0~255 pair of radial displacement negative shape to become
Data are mapped, and are become corresponding to 0~-10mm negative shape.
In the full tunnel cross section measured first, tunnel axis extraction unit, noise reduction and adjustment processing unit are performed, so
(β is calculated using formula (14) ellipse fitting algorithm EFA afterwardse,ρe), by R(h(j),β)=ρe, wherein：H (j) is jth section tunnel
Road, β are azimuth, this R(h(j),β)Value is stored in full tunnel as the benchmark of measurement and respectively saved in the benchmark database of cross section；Together
When by face of cylinder fitting algorithm implementing result, the coordinate of a fixing point on axisX=u1 (3), y
=u2 (3),As kernel of section coordinate basis Ph(j)(x, y, z) is stored in full tunnel and respectively saves axis coordinate basis number
According in storehouse.
Full tunnel profile concatenation unit, for the segmented three-dimensional reconstruction result in full tunnel to be spliced；With regard to same tunnel
For road section, its SECTION EQUATION under absolute coordinate system and its SECTION EQUATION under relative coordinate system only have the horizontal seat in center
Mark is different with center ordinate；The effect of tunnel axis can express the posture and tendency information in tunnel, under normal circumstances jth section
The axis that the axis in tunnel and jth+1 save tunnel is continuous, and on the other hand, the present invention is in tunnel contour marginal point cloud number
According to gatherer process and continuously；It has been divided into several to save in whole tunnel when being monitored due to full tunnel deformation, has each saved
Length is h (j)；The centre coordinate in jth section tunnel has been obtained in the processing of tunnel axis extraction unit
Certain point i.e. on the axis in tunnel, and direction vectorPin
To the narrow structure feature in tunnel, the center for saving tunnel with centre coordinate and normal vector the estimation jth+1 in jth section tunnel here is sat
Mark, then save the centre coordinate in tunnel with jth+1 and normal vector estimation jth+2 saves the centre coordinate ... in tunnel, so complete
The splicing of the axis in full tunnel；In the full tunnel profile measured first, full tunnel axis is preserved in database
Each coordinate value Ph(j)(x, y, z), as the reference data compared in being measured as subsequent tunnel linear deformation；Accompanying drawing 13 is some
Save the spliced design sketch in tunnel.
Displacement monitoring and settlement monitoring unit, global displacement and sedimentation to tunnel have the measurement of quantization；As tunnel
On global displacement and the main central axis displacement deformation for being reflected in tunnel of sedimentation, according in the processing of tunnel axis extraction unit
The centre coordinate and direction vector in jth section tunnel are obtainedWith
Centre coordinate and normal vector the estimation jth+1 in jth section tunnel save the centre coordinate ... in tunnel, are then saved with jth+1 in tunnel
Heart coordinate and normal vector estimation jth+2 save the centre coordinate ... in tunnel, and each of this full tunnel axis has been calculated successively
Coordinate value P'h(j)(x',y',z')；Displacement monitoring is mainly reflected in X-direction, and settlement monitoring is mainly reflected in Y direction, such as
Shown in accompanying drawing 9；With a reference value P of the centre coordinate in jth section tunnelh(j)The jth section that x in (x, y, z) obtains with this measurement
The centre coordinate P' in tunnelh(j)X' in (x', y', z') compares, and obtainsExactly jth section tunnel
Shift offset；With a reference value P of the centre coordinate in jth section tunnelh(j)The jth section that y in (x, y, z) obtains with this measurement
The centre coordinate P' in tunnelh(j)Y' in (x', y', z') compares, and obtains Δ yh(j)=y'-y, Δ yh(j)Exactly jth section tunnel
Settle offset；The displacement each saved on full tunnel central axis deformation is calculated by above-mentioned；Finally by the shifting of each section
Position deformation Δ xh(j)With Δ yh(j)It is stored in Test database；By it is above-mentioned be calculated be tunnel profile relative position
Move and settling data amount；The spatial positional information for being fixed on RFID in tunnel wall using reading and being stored, and in this, as absolute
Coordinate basis obtains absolute displacement and the settling data amount of tunnel profile.
Tunnel profile become shifting amount three-dimensional visualization unit, for the global displacement to tunnel and sedimentation have quantization, can
Depending on the expression of change；Three-dimensional visualization handles the numerical value that measurement is obtained, deflection information is changed into intuitively, with Figure and Image
It is representing, with the physical quantity of time and spatial variations be presented to tunnel safety monitoring personnel；Here positive deformation is represented with red, used
Blueness represents that negative shape becomes, and color, which is more deeply felt, shows that deformation is bigger；For RGB color, GB color components are arranged to zero, R
Component aligns deformation data from 0~255 and mapped, corresponding to 0~255mm positive deformation；RG color components are arranged to zero,
G components map from 0~255 pair of negative deformation data, become corresponding to 0~-255mm negative shape；Then to full tunnel central shaft
It is color-coded on the section corresponding to tunnel corresponding to the vertical section deformation quantity each saved on line；Finally according to full tunnel center
Coordinate value on axis connects broken line mode is each saved on central axis, shows that whole tunnel is indulged with visual means
The deformation situation of section.
Embodiment 2
In the present embodiment, remaining implementation is similar, except that increasing storage on the controller on Tunnel testing car
Capacity, tunnel scan image is sent jointly into central monitoring center service by network after Tunnel testing car test, which is surveyed, to be terminated
Device.
Embodiment 3
In the present embodiment, remaining implementation is similar, except that it is different according to tunnel cross section, in tunnel axis
Using the method for seeking tunnel cross section barycenter in extraction unit, the axis using the barycenter line in each cross section as tunnel,
Distance by the use of tunnel inner wall marginal point to axis is used as tunnel deformation detection parameters.
Embodiment 4
In the present embodiment, remaining implementation is similar, except that the detection speed of Tunnel testing car is different, for than
The more at a slow speed or faster detection speed of embodiment 1, using the shooting speed camera adaptable with it.
Embodiment 5
In the present embodiment, remaining implementation is similar, except that installing active panoramic vision on Tunnel testing car
The position of sensor, active panoramic vision sensor configuration is in Tunnel testing tailstock portion.
Embodiment 6
In the present embodiment, remaining implementation is similar, except that in the subway train and bullet train of normal operation
The active panoramic vision sensor of upper configuration, RFID reader, measuring wheel, wirelessly receive and send unit and controller.
Embodiment 7
In the present embodiment, remaining implementation is similar, except that the parsing of comprehensive face laser intelligence and cloud data
In controller on Tunnel testing car, controller is located online to tunnel cross section laser scanning image for acquiring unit configuration
Reason, is then sent to central monitoring center server by the contour edge cloud data in tunnel lateral direction section by network；In order to
Tunnel cross section laser scanning image can be handled in the controller, it is necessary to which active panoramic vision sensor is demarcated into number
According to storehouse configuration in the memory cell of controller；In addition just directly to the cloud data in tunnel in central monitoring center server
Handled, avoid the transmission of mass image data.
Claims (8)
1. a kind of full section of tunnel high speed dynamical health detection means based on active panoramic vision, including Tunnel testing car and
Processor, it is characterised in that described Tunnel testing car is included in the detection car body walked on tunnel track, installed in detection
Active panoramic vision sensor, RFID reader and measuring wheel on car body；
Described active panoramic vision sensor includes co-axially fixed panorama laser projection light source and all-directional vision sensing
Device, described panorama laser projection light source are used to provide tunnel disconnected section panoramic scanning light for tunnel inner wall, and described is comprehensive
Vision sensor is used for the panoramic picture for gathering tunnel inner wall；
Described panorama laser projection light source includes base, the ring shape generating laser being fixed on base, and for reflecting
The circle laser that ring shape laser transmitter projects come out provides the cone of tunnel disconnected section panoramic scanning light for tunnel inner wall
Minute surface；
Described RFID reader, the tunnel reference data of RFID memory storages on tunnel inner wall is fixed on for reading；
Described measuring wheel, for calculating the travel distance of Tunnel testing car；
Described processor, for parsing the three dimensional point cloud on tunnel cross section from described panoramic picture, and tie
The travel distance for closing Tunnel testing car reconstructs full tunnel inner wall threedimensional model, then by the full tunnel inner wall threedimensional model of structure with
Initial full tunnel inner wall threedimensional model is contrasted, and analyzes tunnel deformation quantity；
Described processor includes：
Omnibearing vision sensor demarcates unit, for determining the X-Y scheme picture point in three dimensions point and video camera imaging plane
Between mapping relations parameter；
J saves tunnel cross-section view data reading unit, for the segmentation of full tunnel cross section laser scanning image to be saved in order
Read and analyzed；
Comprehensive face laser intelligence parsing and cloud data acquiring unit, for displacement Z all in being saved to JiTunnel it is horizontal
Section laser scanning image is handled, and obtains tunnel inner wall edge cloud data；
Tunnel axis detection unit, for drawing tunnel linear deformation figure according to tunnel axis, to carry out three-dimensional modeling；
Noise reduction and adjustment processing unit, for the tunnel point cloud number for further handling described tunnel axis extraction module to obtain
According to progress noise reduction and adjustment processing；
Three-dimensional modeling and deformation analysis unit, for tunnel deformation visualization processing；
Full tunnel profile concatenation unit, for the segmented three-dimensional reconstruction result in full tunnel to be spliced；
Displacement monitoring and settlement monitoring unit, there is the measurement of quantization for the global displacement to tunnel and sedimentation；
Tunnel profile become shifting amount three-dimensional visualization unit, for the global displacement to tunnel and sedimentation have quantization and visualize
Expression.
A kind of 2. high quick-action of full section of tunnel of the full section of tunnel high speed dynamical health detection means based on described in claim 1
State health detecting method, it is characterised in that including step：
1) control Tunnel testing car is walked on tunnel track, is used panorama laser projection light source to provide tunnel for tunnel inner wall and is broken
Section panoramic scanning light, and tunnel cross section laser scanning image is gathered by omnibearing vision sensor, while utilize RFID
Reader reads the tunnel reference data for being fixed on RFID memory storages on tunnel inner wall；
2) running distance of Tunnel testing car is estimated, and tunnel cross section laser scanning image is associated into storage with running distance
Deposit；
3) the space coordinates position of panorama laser projection point on tunnel cross section is parsed from tunnel cross section laser scanning image
Put value, i.e., the three dimensional point cloud on tunnel cross section；
4) according to described running distance and corresponding three dimensional point cloud, full tunnel inner wall threedimensional model is reconstructed；
5) the full tunnel inner wall threedimensional model of structure is contrasted with the full tunnel inner wall threedimensional model initially built, analyzes tunnel
Road deformation quantity.
3. full section of tunnel high speed dynamical health detection method as claimed in claim 2, it is characterised in that be divided into full tunnel
Some sections, the variable by the use of h (j) as section, h (j) and Tunnel testing car are along the displacement Z on tunnel longitudinal directioniBetween
Relation formula (16) expression,
H (j)=INT (Zi/10)+1 (16)
After it have chosen a certain section h (j), the displacement Z included in the section is obtained according to formula (16)i, then with the section
All displacement ZiAs filename tunnel cross section is read from described full tunnel cross section laser scanning image storehouse
Laser scanning image.
4. full section of tunnel high speed dynamical health detection method as claimed in claim 3, it is characterised in that for being saved to h (j)
Interior all displacement ZiTunnel cross section laser scanning image handled, obtain tunnel inner wall edge cloud data；
Implementing algorithm is：
Step1：Initial orientation angle beta=0 is set；
Step2：Laser is retrieved since the central point of laser scanning panoramic picture with azimuthal angle beta on laser scanning panoramic picture
Incident point, for, there is the pixel of several continuous laser projections, selecting I points in HIS color spaces in azimuthal angle beta
Amount, i.e. brightness value estimate by Gaussian approximation method the centre bit of laser projection line close to three contiguous pixels of peak
Put；Circular is provided by formula (7),
<mrow>
<mi>d</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>ln</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>ln</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mo>&lsqb;</mo>
<mi>ln</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mn>2</mn>
<mi>ln</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>)</mo>
<mo>+</mo>
<mi>ln</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>)</mo>
<mo>&rsqb;</mo>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>7</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula, f (i-1), f (i) and f (i+1) are respectively brightness value of three adjacent pixels close to highest brightness value, and d is amendment
Value, i represent the ith pixel point since image center；Therefore the center for estimating obtained laser projection line is (i+
d)；
Step3：Calculate the incident angle α of the laser projection pointβ, and according to Tunnel testing car along moving on tunnel longitudinal direction
Distance Zi, Tunnel testing car is calculated along the displacement Z on tunnel longitudinal directioniWith azimuthal angle beta ' in the case of=β in tunnel
Laser projection point on wall is to the distance between the central axis of active panoramic vision sensor d(z,β)；Finally use formula (8)
Calculate the spatial coordinate location value of the laser projection point；
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>z</mi>
<mo>=</mo>
<msub>
<mi>Z</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mi>H</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>y</mi>
<mo>=</mo>
<msub>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>z</mi>
<mo>,</mo>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
</msub>
<mo>&times;</mo>
<mi>s</mi>
<mi>i</mi>
<mi>n</mi>
<mi>&beta;</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>x</mi>
<mo>=</mo>
<msub>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>z</mi>
<mo>,</mo>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
</msub>
<mo>&times;</mo>
<mi>cos</mi>
<mi>&beta;</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula, ZiPassed for Tunnel testing car along the displacement on tunnel longitudinal direction, H panoramic scannings light to omni-directional visual
The single view O of sensormAir line distance, d(z,β)For along the position Z on tunnel longitudinal directioniWith azimuthal angle beta ' in the case of=β
Laser projection point on tunnel inner wall is the distance between to the central axis of active panoramic vision sensor, x, y, and z is respectively
Laser projection point is relative to the single view O of omnibearing vision sensormCoordinate value, β is azimuth；
Step4：Change azimuth to continue to retrieve laser projection point, i.e. β=β+Δ β, Δ β=1；
Step5：Judge azimuthal angle beta=360, if set up, retrieval terminates；Otherwise go to Step2.
5. full section of tunnel high speed dynamical health detection method as claimed in claim 4, it is characterised in that building three-dimensional mould
During type, linear deformation figure in tunnel is drawn according to tunnel axis, the method for extracting axis is that the tunnel point cloud after segmentation is justified
Cylinder is fitted, as follows the step of the fitting algorithm of the face of cylinder：
STEP1：Read obtain after the parsing of comprehensive face laser intelligence and the processing of cloud data acquiring unit along tunnel axis side
To the cloud data in several continuous sections, three-dimensional coordinate matrix P=(X, Y, Z) is formed；
STEP2：Representational cloud is chosen, forms three-dimensional coordinate matrix P(1)=(X(1),Y(1),Z(1))；
STEP3：With u(0)=(X(1),Y(1), π, 0) it is initial value, solved to obtain according to formula (9), (10), (11)
<mrow>
<mi>min</mi>
<mi> </mi>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>e</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>R</mi>
<mrow>
<mo>(</mo>
<mi>h</mi>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
<mo>,</mo>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>9</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula, R(h(j),β)To be fitted the radius on the face of cylinder, eiFor tunnel inner wall marginal point cloud to the distance between axis；
Constraints
U=(x0,y0,λ,φ)T (11)
In formula, x0,y0For the X-coordinate and Y-coordinate value on a fixing point on tunnel axis to be asked, λ is tunnel axis to be asked
Angle of the line between the projection line and Z axis of XOZ planes, φ are the angle between tunnel axis to be asked and XOZ planes；
STEP4：Appropriate increase cloud data, forms three-dimensional coordinate matrix P(2)=(X(2),Y(2),Z(2))；
STEP5：WithFor initial value, solved to obtain according to formula (9), (10), (11)
STEP6：Order：
Pi=(X(2),Y(2),Z(2)),
<mrow>
<mi>c</mi>
<mo>=</mo>
<mrow>
<mo>(</mo>
<msup>
<msub>
<mi>u</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>,</mo>
<msup>
<msub>
<mi>u</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>,</mo>
<mover>
<msup>
<mi>Z</mi>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>,</mo>
</mrow>
<mrow>
<mover>
<mi>a</mi>
<mo>&RightArrow;</mo>
</mover>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>cos</mi>
<mi> </mi>
<msup>
<msub>
<mi>u</mi>
<mn>3</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mi>cos</mi>
<mi> </mi>
<msup>
<msub>
<mi>u</mi>
<mn>4</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>,</mo>
<mi>sin</mi>
<mi> </mi>
<msup>
<msub>
<mi>u</mi>
<mn>3</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mi>cos</mi>
<mi> </mi>
<msup>
<msub>
<mi>u</mi>
<mn>4</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>,</mo>
<mi>sin</mi>
<mi> </mi>
<msup>
<msub>
<mi>u</mi>
<mn>4</mn>
</msub>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
</mrow>
E is calculated using formula (12)i；
<mrow>
<msub>
<mi>e</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>p</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<mover>
<mi>a</mi>
<mo>&RightArrow;</mo>
</mover>
<mo>|</mo>
<mo>|</mo>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>12</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula：pi=(xi,yi,zi) it is any one measurement point coordinates, c=(x in original point cloud0,y0,z0) it is face of cylinder axis
On a fixed point coordinates,For the axis direction unit vector on the face of cylinder；
STEP7：Delete eiMore than the point of some critical value, three-dimensional coordinate matrix P is formed(3)=(X(3),Y(3),Z(3))；
STEP8：WithFor initial value, solved to obtain according to formula (9), (10), (11)
STEP9：Calculate the coordinate of a fixing point and the direction vector of axis in face of cylinder axis：
In above-mentioned calculating, face of cylinder axis is exactly tunnel axis, u1 (i)To correspond to X-coordinate on tunnel axis in axis
Value, u are approached in extraction process2 (i)To approach value, u during axis detection corresponding to Y-coordinate on tunnel axis3 (i)It is included angle X of the tunnel axis between the projection line and Z axis of XOZ planes in the value of approaching of axis, u4 (i)For in tunnel
In the value of approaching of axis, i is time of the approximation computation during axis detection for included angle between axis and XOZ planes
Number.
6. full section of tunnel high speed dynamical health detection method as claimed in claim 5, it is characterised in that in step 5),
The algorithm of deformation quantity in tunnel in same position is as follows：
STEP1：The three-dimensional point cloud coordinates matrix P that importing is represented with cylindrical coordinate*=(Z(cs2),β*,ρ*), initialization process, j=
1；
STEP2：Jth section three dimensional point cloud is read, using ellipse fitting algorithm EFA, the tunnel contour line point cloud of two dimension is intended
Synthesis is oval：
(βe,ρe)=EFA (β*,ρ*) (14)
STEP3：With (βe,ρe) it is directrix, the line segment of parallel Z axis is bus, the elliptic cylinder that generation length is h (j), h (j)=
1000mm：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msup>
<mi>EX</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mi>s</mi>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>=</mo>
<msup>
<mi>&rho;</mi>
<mi>e</mi>
</msup>
<msup>
<mi>cos&beta;</mi>
<mi>e</mi>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mi>EY</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mi>s</mi>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>=</mo>
<msup>
<mi>&rho;</mi>
<mi>e</mi>
</msup>
<msup>
<mi>sin&beta;</mi>
<mi>e</mi>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mi>EZ</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mi>s</mi>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msup>
<mo>=</mo>
<mo>{</mo>
<mi>z</mi>
<mo>|</mo>
<mi>z</mi>
<mo>&Element;</mo>
<mo>&lsqb;</mo>
<mn>0</mn>
<mo>,</mo>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>}</mo>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>15</mn>
<mo>)</mo>
</mrow>
</mrow>
STEP4：The radial displacement ρ of elliptic cylinder each pointe-R(h(j),β)As deflection, three-dimensional radial displacement cloud atlas is generated；
Wherein, ρeIt is calculated with formula (14), R(h(j),β)For measure first full tunnel cross section when be calculated with formula (14)
, calculating ρe-R(h(j),β)When R obtained as index using h (j) and azimuthal angle beta(h(j),β)；For RGB color, by GB
Color component is arranged to zero, and R component maps from 0~255 pair of positive deformation data of radial displacement, corresponding to 0~10mm just
Deformation；RG color components are arranged into zero, G components to map from the negative deformation data of 0~255 pair of radial displacement, corresponding to 0
~-10mm negative shape becomes.
7. full section of tunnel high speed dynamical health detection method as claimed in claim 6, it is characterised in that by point in full tunnel
Section three-dimensionalreconstruction result is spliced；It has been divided into several to save in whole tunnel when being monitored due to full tunnel deformation, has each saved
Length is h (j)；The centre coordinate in jth section tunnel has been obtained in the processing of tunnel axis extraction unit
That is the certain point on the axis in tunnel and direction vectorFor
The narrow structure feature in tunnel, the centre coordinate in tunnel is saved with centre coordinate and normal vector the estimation jth+1 in jth section tunnel, so
The centre coordinate in tunnel is saved with jth+1 afterwards and normal vector estimation jth+2 saves the centre coordinate in tunnel, complete full tunnel by that analogy
Axis splicing.
8. full section of tunnel high speed dynamical health detection method as claimed in claim 7, it is characterised in that described method is also
There is the measurement of quantization including the global displacement to tunnel and sedimentation；Mainly tunnel is reflected in as the global displacement in tunnel and sedimentation
Central axis displacement deformation on, according to tunnel axis extraction unit processing in obtained jth section tunnel centre coordinate and
Direction vectorWith the centre coordinate and normal vector in jth section tunnel
Estimate that jth+1 saves the centre coordinate in tunnel, then save the centre coordinate in tunnel with jth+1 and normal vector estimation jth+2 saves tunnel
Centre coordinate, each coordinate value P' of this full tunnel axis has been calculated successivelyh(j)(x',y',z')；Displacement monitoring master
X-direction is reflected in, settlement monitoring is mainly reflected in Y direction；With a reference value P of the centre coordinate in jth section tunnelh(j)
The jth section tunnel that x in (x, y, z) obtains with this measurement
Centre coordinate P'h(j)X ' in (x', y', z') compares, and obtains Δ xh(j)=x'-x, Δ xh(j)It is exactly the position in jth section tunnel
Move offset；With a reference value P of the centre coordinate in jth section tunnelh(j)The jth section tunnel that y in (x, y, z) obtains with this measurement
The centre coordinate P' in roadh(j)Y' in (x', y', z') compares, and obtains Δ yh(j)=y'-y, Δ yh(j)It is exactly the heavy of jth section tunnel
Offset drops；The displacement each saved on full tunnel central axis deformation is calculated by above-mentioned；Finally by the displacement of each section
Deform Δ xh(j)With Δ yh(j)It is stored in Test database；By it is above-mentioned be calculated be tunnel profile relative displacement
With settling data amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510005918.XA CN104567708B (en) | 2015-01-06 | 2015-01-06 | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510005918.XA CN104567708B (en) | 2015-01-06 | 2015-01-06 | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104567708A CN104567708A (en) | 2015-04-29 |
| CN104567708B true CN104567708B (en) | 2018-03-16 |
Family
ID=53084334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510005918.XA Active CN104567708B (en) | 2015-01-06 | 2015-01-06 | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104567708B (en) |
Families Citing this family (62)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104089653A (en) * | 2014-07-11 | 2014-10-08 | 中国路桥工程有限责任公司 | Automated remote measurement and control system of tunnel construction stress and deformation |
| CN104992467B (en) * | 2015-07-20 | 2018-08-21 | 四川隧唐科技股份有限公司 | Unmanned plane assists vehicle mounted road acquisition 3 d modeling system and its implementation |
| CN106572325A (en) * | 2015-10-13 | 2017-04-19 | 上海宝信软件股份有限公司 | Virtual-reality-technology-based tunnel monitoring equipment inspection system |
| CN105424724B (en) * | 2015-10-22 | 2018-05-25 | 汤一平 | Cannon Inner thorax flaw inspection device and methods based on active panoramic vision |
| CN106887020A (en) * | 2015-12-12 | 2017-06-23 | 星际空间（天津）科技发展有限公司 | A kind of road vertical and horizontal section acquisition methods based on LiDAR point cloud |
| CN105423940B (en) * | 2015-12-25 | 2017-12-26 | 同济大学 | A kind of subway tunnel structure cross section deformation device for fast detecting |
| CN106124512B (en) * | 2016-03-18 | 2019-07-05 | 中铁二院工程集团有限责任公司 | Suspension type monorail box beam inspection device |
| CN106053475B (en) * | 2016-05-24 | 2018-10-23 | 浙江工业大学 | Tunnel defect tunneling boring dynamic device for fast detecting based on active panoramic vision |
| CN106052584B (en) * | 2016-05-24 | 2017-07-04 | 上海工程技术大学 | A kind of view-based access control model and the orbit space linear measurement method of Inertia information fusion |
| CN106152950B (en) * | 2016-07-29 | 2018-12-25 | 上海岩土工程勘察设计研究院有限公司 | One kind being based on lining section geometrical characteristic motion scan data mileage localization method |
| CN106548510A (en) * | 2016-11-07 | 2017-03-29 | 上海岩土工程勘察设计研究院有限公司 | Shield tunnel construction model generation method |
| CN106767402B (en) * | 2016-11-30 | 2023-01-06 | 华中科技大学 | Shield tunnel apparent quality detection method and system |
| CN106841216A (en) * | 2017-02-28 | 2017-06-13 | 浙江工业大学 | Tunnel defect automatic identification equipment based on panoramic picture CNN |
| CN106930784B (en) * | 2017-03-08 | 2018-11-20 | 中交第二航务工程局有限公司 | Tunnel monitoring method based on 3 D laser scanning |
| CN107289900A (en) * | 2017-06-22 | 2017-10-24 | 首都师范大学 | A kind of dynamic is without control tunnel cross-section detection means, analysis system and method |
| CN107393006B (en) * | 2017-07-26 | 2021-02-12 | 河海大学 | Method for measuring integral deformation of tunnel |
| CN107345792A (en) * | 2017-08-23 | 2017-11-14 | 南京火眼猴信息科技有限公司 | A kind of vcehicular tunnel surface and internal detection car |
| CN107830812B (en) * | 2017-09-14 | 2019-10-18 | 同济大学 | A kind of laser reflection piece implementation method suitable for positioning in tunnel with deformation analysis |
| EP3460729A1 (en) * | 2017-09-26 | 2019-03-27 | Ricoh Company, Ltd. | Information processing apparatus, system of assessing structural object, method of assessing structural object system of assessing structural object, and carrier means |
| CN107830839B (en) * | 2017-10-11 | 2020-06-26 | 北京工业大学 | Ground three-dimensional laser scanning data processing method and device |
| CN107677365B (en) * | 2017-10-19 | 2019-12-31 | 招商局重庆交通科研设计院有限公司 | Rapid detection device and method for illumination brightness of highway tunnel |
| CN108053477B (en) * | 2017-12-20 | 2021-07-02 | 北京华航无线电测量研究所 | Numerical processing method for deformation in pipeline |
| CN108413892B (en) * | 2018-01-30 | 2020-05-05 | 华侨大学 | Method and device for detecting three-dimensional surface topography of whole circumference of diamond wire saw |
| CN108180856A (en) * | 2018-01-30 | 2018-06-19 | 中国地质大学（武汉） | A kind of tunnel deformation monitoring method, equipment and storage device based on laser data |
| CN108593654B (en) * | 2018-03-28 | 2020-08-25 | 北京交通大学 | Tunnel image acquisition system and method |
| CN108507533A (en) * | 2018-04-24 | 2018-09-07 | 招商局重庆交通科研设计院有限公司 | The continuous robot measurement of tunnel cross-section |
| CN108648156B (en) * | 2018-05-08 | 2021-04-16 | 北京邮电大学 | Method and device for marking stray points in point cloud data, electronic equipment and storage medium |
| CN108663013A (en) * | 2018-05-24 | 2018-10-16 | 上海应用技术大学 | Single point extensometer and tunnel excavation advance core deformation measurement method |
| CN109029277A (en) * | 2018-06-27 | 2018-12-18 | 常州沃翌智能科技有限公司 | A kind of tunnel deformation monitoring system and method |
| CN108895976B (en) * | 2018-06-29 | 2020-06-05 | 国网智能科技股份有限公司 | Method and device for monitoring deformation of closed space equipment |
| CN109087291B (en) * | 2018-07-26 | 2021-08-27 | 杭州国翌科技有限公司 | Tunnel position information base establishing method and tunnel defect positioning method |
| CN109029350B (en) * | 2018-08-02 | 2023-05-23 | 南京航空航天大学 | Tunnel axis extraction and section convergence analysis method and device |
| CN109253706B (en) * | 2018-08-24 | 2020-07-03 | 中国科学技术大学 | Tunnel three-dimensional topography measuring method based on digital image |
| CN109238162A (en) * | 2018-09-25 | 2019-01-18 | 浙江科技学院 | A kind of tunnel 3 d deformation monitoring and method for early warning |
| CN109407111B (en) * | 2018-09-27 | 2021-05-14 | 长沙科达智能装备股份有限公司 | Method for identifying characteristics of tunnel three-dimensional scanner |
| CN109341573A (en) * | 2018-09-30 | 2019-02-15 | 中国铁建重工集团有限公司 | A kind of tunnel-liner profile Clearance Detection |
| CN109583486A (en) * | 2018-11-21 | 2019-04-05 | 银河水滴科技（北京）有限公司 | A kind of method and device detecting environmental abnormality region to be measured |
| JP6591131B1 (en) * | 2019-02-07 | 2019-10-16 | 三菱電機株式会社 | Structure measuring apparatus and structure measuring method |
| CN110108217A (en) * | 2019-03-22 | 2019-08-09 | 中交第二航务工程局有限公司 | A kind of tunnel just props up and two linings invade limit value and thickness analysis method |
| CN110411361B (en) * | 2019-05-15 | 2021-08-17 | 首都师范大学 | Laser detection data processing method for mobile tunnel |
| CN112446852B (en) * | 2019-08-30 | 2023-12-15 | 成都唐源电气股份有限公司 | Tunnel imaging plane display method and defect intelligent recognition system |
| US12045966B2 (en) | 2019-10-08 | 2024-07-23 | Shanghai Oriental Maritime Engineering Technology Co., Ltd. | Tunnel-inspection image acquisition device, tunnel-inspection system, and tunnel-inspection method |
| CN110593957B (en) * | 2019-10-08 | 2021-09-28 | 上海市东方海事工程技术有限公司 | Tunnel inspection method |
| CN110726726A (en) * | 2019-10-30 | 2020-01-24 | 中南大学 | Quantitative detection method and system for tunnel forming quality and defects thereof |
| CN111145345A (en) * | 2019-12-31 | 2020-05-12 | 山东大学 | Tunnel construction area three-dimensional model construction method and system |
| CN111412851B (en) * | 2020-04-13 | 2021-09-07 | 成都大亦科技有限公司 | Method for measuring deformation based on laser |
| CN111447363A (en) * | 2020-04-14 | 2020-07-24 | 中原工学院 | Tunnel wireless panoramic video monitoring system |
| CN111540002A (en) * | 2020-04-24 | 2020-08-14 | 西安正源井像电子科技有限公司 | Method and device for detecting tubular column through laser scanning visual three-dimensional modeling |
| CN111595255A (en) * | 2020-05-14 | 2020-08-28 | 南京航空航天大学 | Tunnel defect real-time prompting device and prompting method |
| CN111833449B (en) * | 2020-06-30 | 2023-10-31 | 南京航空航天大学 | Three-dimensional reconstruction and intelligent defect identification method for internal environment of subway tunnel |
| CN111811420B (en) * | 2020-07-16 | 2021-10-29 | 山东大学 | Tunnel three-dimensional contour integral absolute deformation monitoring method and system |
| CN111750798B (en) * | 2020-08-19 | 2024-10-11 | 江苏悟空风行科技有限公司 | Real-time automatic monitoring device for tunnel deformation |
| CN112325935A (en) * | 2020-10-30 | 2021-02-05 | 湖北省水利水电规划勘测设计院 | Safety performance monitoring system of deeply buried tunnel |
| CN112097669B (en) * | 2020-11-17 | 2021-02-12 | 南京派光智慧感知信息技术有限公司 | Method for monitoring deformation of structure in tunnel based on laser ranging |
| CN113630622B (en) * | 2021-06-18 | 2024-04-26 | 中图云创智能科技(北京)有限公司 | Panoramic video image processing method, server, target equipment, device and system |
| US11995764B2 (en) | 2021-06-30 | 2024-05-28 | Here Global B.V. | Method, apparatus and computer program product for tunnel detection from a point cloud |
| CN113516654A (en) * | 2021-09-07 | 2021-10-19 | 风脉能源（武汉）股份有限公司 | Method and system for identifying abnormal part of inner wall of core hole based on vision |
| CN114636383B (en) * | 2022-01-27 | 2023-08-22 | 深圳大学 | Dynamic deformation measurement method for immersed tube tunnel tube joint construction process |
| CN115790430B (en) * | 2022-11-22 | 2024-09-10 | 上海勃发空间信息技术有限公司 | Three-dimensional deformation detection method under high-speed dynamic condition |
| CN116186868B (en) * | 2023-04-27 | 2023-06-23 | 中国铁路设计集团有限公司 | Existing railway line fitting and accurate adjusting method |
| CN117168344B (en) * | 2023-11-03 | 2024-01-26 | 杭州鲁尔物联科技有限公司 | Monocular panorama looking around deformation monitoring method and device and computer equipment |
| CN118274734B (en) * | 2024-06-03 | 2024-07-26 | 长江三峡集团实业发展(北京)有限公司 | Tunnel deformation analysis method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19513116A1 (en) * | 1995-04-07 | 1996-10-10 | Misoph Rotraud | Contactless measurement of tunnel profile or road surface e.g. motorway |
| CN101408410A (en) * | 2008-10-28 | 2009-04-15 | 山东科技大学 | Tunnel volume element deformation movable monitoring system and method |
| CN101943577A (en) * | 2010-08-16 | 2011-01-12 | 上海地铁盾构设备工程有限公司 | Metro tunnel fracture surface deformation detection system |
| CN102564335A (en) * | 2012-01-16 | 2012-07-11 | 苏州临点三维科技有限公司 | Method for measuring deformation of large-scale tunnel |
| CN102679959A (en) * | 2012-05-03 | 2012-09-19 | 浙江工业大学 | Omnibearing 3D (Three-Dimensional) modeling system based on initiative omnidirectional vision sensor |
| CN202782968U (en) * | 2012-09-21 | 2013-03-13 | 纵横皆景（武汉）信息技术有限公司 | Vehicle-mounted measure integrated system based on laser scanning and panorama images |
| CN103438823A (en) * | 2012-12-27 | 2013-12-11 | 广州市地下铁道总公司 | Tunnel section outline measuring method and device based on vision measurement |
| CN103852025A (en) * | 2014-03-19 | 2014-06-11 | 北京工业大学 | Method for monitoring vertical deformation in rail way underlying substratum by applying 3D laser scanning technology |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201706239U (en) * | 2010-04-09 | 2011-01-12 | 陕西硕华光电技术有限责任公司 | 360-degree annular line laser demarcation device light source |
| CN201772365U (en) * | 2010-08-27 | 2011-03-23 | 陕西硕华光电技术有限责任公司 | Novel approximately 360-degree annular line laser projector light source |
| CN103206926B (en) * | 2013-03-14 | 2016-03-30 | 南京楚通自动化科技有限公司 | A kind of panorama three-dimensional laser scanner |
-
2015
- 2015-01-06 CN CN201510005918.XA patent/CN104567708B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19513116A1 (en) * | 1995-04-07 | 1996-10-10 | Misoph Rotraud | Contactless measurement of tunnel profile or road surface e.g. motorway |
| CN101408410A (en) * | 2008-10-28 | 2009-04-15 | 山东科技大学 | Tunnel volume element deformation movable monitoring system and method |
| CN101943577A (en) * | 2010-08-16 | 2011-01-12 | 上海地铁盾构设备工程有限公司 | Metro tunnel fracture surface deformation detection system |
| CN102564335A (en) * | 2012-01-16 | 2012-07-11 | 苏州临点三维科技有限公司 | Method for measuring deformation of large-scale tunnel |
| CN102679959A (en) * | 2012-05-03 | 2012-09-19 | 浙江工业大学 | Omnibearing 3D (Three-Dimensional) modeling system based on initiative omnidirectional vision sensor |
| CN202782968U (en) * | 2012-09-21 | 2013-03-13 | 纵横皆景（武汉）信息技术有限公司 | Vehicle-mounted measure integrated system based on laser scanning and panorama images |
| CN103438823A (en) * | 2012-12-27 | 2013-12-11 | 广州市地下铁道总公司 | Tunnel section outline measuring method and device based on vision measurement |
| CN103852025A (en) * | 2014-03-19 | 2014-06-11 | 北京工业大学 | Method for monitoring vertical deformation in rail way underlying substratum by applying 3D laser scanning technology |
Non-Patent Citations (2)
| Title |
|---|
| 基于ASODVS的全景点云数据获取技术的研究;徐海涛等;《计算机测量与控制》;20140731;第22卷(第7期);第2284~2286页第0-2节、图1-3 * |
| 基于地面三维激光扫描技术的隧道全断面变形测量方法;谢雄耀等;《岩石力学与工程学报》;20131130;第32卷(第11期);摘要、第2215~2220页第2-3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104567708A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104567708B (en) | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision | |
| CN109870456B (en) | Rapid detection system and method for road surface health condition | |
| CN106049210B (en) | A kind of track condition Intelligent Measurement platform | |
| CN111931565B (en) | Autonomous inspection and hot spot identification method and system based on photovoltaic power station UAV | |
| CN101694084B (en) | Ground on-vehicle mobile detecting system | |
| CN110174136B (en) | Intelligent detection robot and intelligent detection method for underground pipeline | |
| CN106053475B (en) | Tunnel defect tunneling boring dynamic device for fast detecting based on active panoramic vision | |
| CN104005325B (en) | Based on pavement crack checkout gear and the method for the degree of depth and gray level image | |
| CN205138460U (en) | Motor vehicle contour dimension checking system | |
| CN106296814B (en) | Highway maintenance detection and virtual interactive interface method and system | |
| CN109029277A (en) | A kind of tunnel deformation monitoring system and method | |
| CN106525057A (en) | Generation system for high-precision road map | |
| CN114444158B (en) | Underground roadway deformation early warning method and system based on three-dimensional reconstruction | |
| CN111547084B (en) | Data processing method based on self-moving type rail transit moving three-dimensional scanning system | |
| CN105674993A (en) | Binocular camera-based high-precision visual sense positioning map generation system and method | |
| CN103778681A (en) | Vehicle-mounted high-speed road inspection system and data acquisition and processing method | |
| CN108733053A (en) | A kind of Intelligent road detection method based on robot | |
| CN104021676A (en) | Vehicle positioning and speed measuring method based on dynamic video feature of vehicle | |
| CN105905132A (en) | Intelligent rail state patrolling device and method | |
| CN105547635A (en) | Non-contact type structural dynamic response measurement method for wind tunnel test | |
| CN103456172A (en) | Traffic parameter measuring method based on videos | |
| CN109596121A (en) | A kind of motor-driven station Automatic Targets and space-location method | |
| CN114312877B (en) | Railway comprehensive inspection system | |
| CN110443819A (en) | A kind of track detection method and device of monorail train | |
| CN106524924A (en) | Track inspection vehicle position and attitude measurement system and method based on optical/inertia combination |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |