CN109029377A - It is a kind of using visual analysis to detection car weight positioning square law device and system - Google Patents
It is a kind of using visual analysis to detection car weight positioning square law device and system Download PDFInfo
- Publication number
- CN109029377A CN109029377A CN201810775617.9A CN201810775617A CN109029377A CN 109029377 A CN109029377 A CN 109029377A CN 201810775617 A CN201810775617 A CN 201810775617A CN 109029377 A CN109029377 A CN 109029377A
- Authority
- CN
- China
- Prior art keywords
- tunnel
- image
- fastener
- cross sectional
- car weight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
- B61K9/10—Measuring installations for surveying permanent way for detecting cracks in rails or welds thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of using visual analysis to the method, apparatus and system of detection car weight positioning, if zeros data causes to detect truck position loss the displacement detector including detection vehicle in the process of moving, obtain the environmental parameter measured value of detection vehicle, according to the environmental parameter measured value, and tunnel environmental parameter value and the tunnel location information between corresponding relationship, to detection vehicle relocate.The scheme provided using each embodiment of the application can relocate the detection vehicle in tunnel when the displacement detector zeros data for detecting vehicle causes to detect truck position loss.
Description
Technical field
This application involves location technology more particularly to a kind of method, apparatus positioned using visual analysis to detection car weight
And system.
Background technique
In rail traffic, if raceway surface, such as fastener are broken defect, track surface scratch, chip off-falling, crackle, or
Person's tunnel-side is cracked, cable falls off, electronic box skew is opened etc. or tunnel environment is abnormal, such as invades boundary, leak, foreign matter
Deng, can all cause security risk to the normally travel of train, therefore, periodically to track condition and tunnel environment carry out detection seem
It is particularly important.
It is manually detected currently, being generally relied on to the detection of track condition and tunnel environment, not only human cost is high, effect
Rate is low, and can have the case where missing inspection, another important problem is that detection is usually in idle time at night section, no
Various information when normal operation can be utilized, thus by manually detecting to track condition and tunnel environment when cannot be to rail
The abnormal position in tunnel in road and tunnel is accurately positioned.
Conventional detection method is to place a detection vehicle in orbit to examine to track condition and tunnel environment
It surveys, and the place of railroad flaws and tunnel exception is positioned.In the prior art, usually by displacement detector come in real time
The real time position of record detection vehicle, to be positioned to the detection vehicle in tunnel.However, ought power to displacement detector
The work system that vehicle occurs powering off or detecting in device exits, collapses, stuck situation when, recorded on displacement detector in real time
Zeros data cause detect truck position lose, when detection vehicle continue when driving, the detection vehicle in tunnel can not be positioned,
To determine the position at the abnormal place of railroad flaws or tunnel.
Summary of the invention
In view of this, this application provides a kind of method, apparatus and system positioned using visual analysis to detection car weight,
It, can be newly fixed to the detection car weight in tunnel when the displacement detector zeros data for detecting vehicle causes to detect truck position loss
Position.
On the one hand, the embodiment of the present application provides a kind of method using visual analysis to detection car weight positioning, comprising:
If the displacement detector of detection vehicle in the process of moving join by zeros data, the environment for obtaining the detection vehicle
Number measured value；
According between the location information of the environmental parameter value and the tunnel in the environmental parameter measured value and tunnel
Corresponding relationship, to the detection car weight new definition.
In some embodiment of the invention, the environmental parameter measured value for obtaining the detection vehicle, according to the environmental parameter
Corresponding relationship between the location information of the environmental parameter value and the tunnel in measured value and tunnel, to the detection car weight
New definition includes:
Extending direction acquisition trajectory image along tunnel, and include multiple fasteners in collected orbital image；
According to the collected orbital image, the fastener in the orbital image is identified, and count and to identify
The number of the fastener；
According to the interval between the number of the fastener and each fastener to the detection car weight new definition.
In some embodiment of the invention, the environmental parameter measured value for obtaining the detection vehicle, according to the environmental parameter
Corresponding relationship between the location information of the environmental parameter value and the tunnel in measured value and tunnel, to the detection car weight
New definition includes:
Extending direction acquisition trajectory image and tunnel-side image along tunnel, the orbital image include multiple fasteners；
Splicing is carried out to the orbital image and tunnel-side image, obtains the spliced button comprising including fastener
The image of tunnel cross sectional at part position；
Spliced tunnel cross sectional image is pre-processed and passes through convolutional neural networks trained in advance and extracts institute
State the feature of spliced tunnel cross sectional image；
The history tunnel cross sectional image that will be stored in the feature of the spliced tunnel cross sectional image and database
Carry out aspect ratio to and identification, the history tunnel cross sectional image has its location information in tunnel, ties according to comparing
Fruit determines position of the spliced tunnel cross sectional image in tunnel, relocates to the detection vehicle.
Second aspect, the embodiment of the invention provides a kind of using visual analysis to the device of detection car weight positioning, comprising:
Acquiring unit, if displacement detector for detecting vehicle zeros data in the process of moving, obtains the inspection
The environmental parameter measured value of measuring car；
Bit location is reset, for according to the environmental parameter value in the environmental parameter measured value and tunnel and the tunnel
Location information between corresponding relationship, to the detection car weight new definition.
In some embodiment of the invention, the acquiring unit is used for the extending direction acquisition trajectory image along tunnel, and
It include multiple fasteners in collected orbital image；
The bit location that resets is for identifying the button in the orbital image according to the collected orbital image
Part, and count the number of the fastener identified；
According to the interval between the number of the fastener and each fastener to the detection car weight new definition.
In some embodiment of the invention, the acquiring unit is used for extending direction acquisition trajectory image and tunnel along tunnel
Road side wall image, the orbital image include multiple fasteners；
The bit location that resets is for carrying out splicing to the orbital image and tunnel-side image, after being spliced
The image comprising the tunnel cross sectional at the fastener position including fastener；Spliced tunnel cross sectional image is located in advance
Manage and pass through the feature that convolutional neural networks trained in advance extract the spliced tunnel cross sectional image；By the splicing
The history tunnel cross sectional image that is stored in the feature and database of tunnel cross sectional image afterwards carry out aspect ratio to and identification,
The history tunnel cross sectional image has its location information in tunnel, determines the spliced tunnel according to comparison result
Position of the road cross sectional image in tunnel relocates the detection vehicle.
The third aspect, the embodiment of the invention provides a kind of using visual analysis to the system of detection car weight positioning, comprising:
Multiple fasteners are fitted in rail flanges and by fixed device track are connected with sleeper；
Detect vehicle；
The detection vehicle includes relocation device, rf receiver unit, camera and displacement detector, wherein
The positioning device is the device described in second aspect using visual analysis to detection car weight positioning；
The camera, for acquiring tunnel-side image or orbital image；
Institute's displacement sensing device, for recording operating range, direction and the speed of detection vehicle in real time；
If detecting the displacement detector zeros data in the process of moving of vehicle, the camera acquisition trajectory image,
It and include multiple fasteners in collected orbital image；The bit location that resets identifies institute according to the orbital image is collected
The fastener in orbital image is stated, and counts the number of the fastener identified, according to the number of the fastener and each
Interval between fastener is to the detection car weight new definition；Or
If zeros data, the acquiring unit are used for along tunnel the displacement detector of detection vehicle in the process of moving
Extending direction acquisition trajectory image and tunnel-side image, the orbital image include multiple fasteners；It is described to reset bit location pair
The orbital image and tunnel-side image carry out splicing, obtain at the spliced fastener position comprising including fastener
The image of tunnel cross sectional；Spliced tunnel cross sectional image is pre-processed and passes through convolutional Neural net trained in advance
Network extracts the feature of the spliced tunnel cross sectional image；By the feature and number of the spliced tunnel cross sectional image
According to the history tunnel cross sectional image that is stored in library carry out aspect ratio to and identification, the history tunnel cross sectional image have it
Location information in tunnel determines position of the spliced tunnel cross sectional image in tunnel according to comparison result,
The detection vehicle is relocated.
One or more embodiment of the application provide using visual analysis to detection car weight positioning method, apparatus and
System, by obtain detection vehicle environmental parameter measured value, according to the environmental parameter value in environmental parameter measured value and tunnel with
Corresponding relationship between the location information in tunnel, to detection car weight new definition.When displacement detector zeros data causes to detect
It truck position can be to the detection car weight new definition in tunnel, so as to determine the abnormal place of railroad flaws or tunnel when losing
Position.
Detailed description of the invention
Attached drawing described here is only used for task of explanation, and is not intended to limit model disclosed in the present application in any way
It encloses.In addition, shape and proportional sizes of each component in figure etc. are only schematical, it is used to help the understanding to the application, and
It is not the specific shape and proportional sizes for limiting each component of the application.Those skilled in the art, can under teachings of the present application
Implement the application to select various possible shapes and proportional sizes as the case may be.In the accompanying drawings:
Fig. 1 is the flow chart in the application one embodiment using visual analysis to the method for detection car weight positioning；
Fig. 2 is the flow chart in another embodiment of the application using visual analysis to the method for detection car weight positioning；
Fig. 3 is the flow chart in another embodiment of the application using visual analysis to the method for detection car weight positioning；
Fig. 4 is the flow chart in another embodiment of the application using visual analysis to the method for detection car weight positioning；
Fig. 5 is the structural representation in another embodiment of the application using visual analysis to the device of detection car weight positioning
Figure；
Fig. 6 is the structural representation in another embodiment of the application using visual analysis to the system of detection car weight positioning
Figure.
Specific embodiment
Below in conjunction with the attached drawing in the application embodiment, the technical solution in the application embodiment is carried out clear
Chu is fully described by, it is clear that described embodiment is only a part of embodiment of the application, rather than whole realities
Apply mode.Based on the embodiment in the application, those of ordinary skill in the art institute without making creative work
The every other embodiment obtained, shall fall in the protection scope of this application.
Unless otherwise defined, all technical and scientific terms used herein and the technical field for belonging to the application
The normally understood meaning of technical staff is identical.The term used in the description of the present application is intended merely to description tool herein
The purpose of the embodiment of body, it is not intended that in limitation the application.
Fig. 1 is the flow chart using visual analysis to the method for detection car weight positioning in the application one embodiment.This
The method of embodiment can be by executing the device of detection car weight positioning using visual analysis, which can pass through hardware
And/or the mode of software is realized, and can generally be integrated in the processor for relocating service.The relocation device can be
It is configured on inspection vehicle and uses.Cunicular relevant information is stored in the database of the relocation processor, including but not limited to:
Tunnel title, geographical location information, length of tunnel, tunnel type, tunnel surface image, tunnel surface image information, tunnel side
Wall image, each position are marked on the location information etc. of the position of tunnel surface, the image of tunnel inner wall, fastener in the tunnel,
The relocation device can carry out communication to relocation processor to call the related letter in tunnel as needed by network
Breath.
As shown in Figure 1, the method positioned using visual analysis to detection car weight in the present embodiment includes following step
It is rapid:
S11. if the displacement detector zeros data in the process of moving of detection vehicle, the ring of the detection vehicle is obtained
Border measured value of parameters.
In the present embodiment using code-disc as displacement detector, but displacement detector of the invention is not limited to
This；Institute's displacement sensing device may be mounted at the outer edge of the wheel of detection vehicle, when track uplink of the detection vehicle in tunnel
Operating range, direction and the speed that detection vehicle can be obtained when sailing in real time, when the positioning system of detection vehicle normally exits, collapses,
When stuck or power down, the operating range recorded on displacement detector is reset, at this point, detection vehicle inclining due to tunnel inner orbit
Rake angle or the traveling inertia for detecting vehicle will continue to reverse direction operation a distance along driving direction or driving direction,
Lead to not determine position of the detection vehicle in tunnel.
When detecting the displacement detector zeros data in the process of moving of vehicle, the measurement portion on relocation device at this time
Part is started to work.The measuring part can be placed in detection vehicle on camera, radio-frequency card reader or other can obtain
Detect the component of the environmental parameter measured value of vehicle.
Such as: it is provided with camera on detection vehicle, the extending direction in the image acquisition areas of tunnel-side, along tunnel exists
Tunnel-side is arranged multiple for marking the position of tunnel surface mark with the first preset interval, and position mark includes tab character,
Tab character is marked on the position of tunnel surface for mark position, wherein the tab character can be number or English words
Mother etc..When the zeros data of displacement detector, the extending direction along tunnel acquires tunnel-side image, and collected
Tunnel-side image is marked comprising at least one position, according to collected tunnel-side image, is identified in the image of tunnel-side
Position mark and tab character, according to position mark in tab character to detection car weight new definition.Such as: when feelings such as generation power-off
When condition leads to displacement detector zeros data, it can to detect vehicle towards its traffic direction or the opposite direction of traffic direction
Traveling, until including at least one position target image in the collected side wall image of camera.
Such as: two tracks are arranged in the extending direction in tunnel along tunnel, preset on the rail level of two tracks with second
Multiple radio-frequency cards for being used to mark tunnel surface are arranged in interval, are stored with its location information in tunnel in the radio-frequency card,
When displacement detector zeros data, the radio-frequency information of at least described radio-frequency card is acquired along the extending direction in tunnel, according to adopting
Its location information in tunnel stored in the radio-frequency card collected is to detection car weight new definition.
S12. according between the location information of the environmental parameter and the tunnel in the environmental parameter measured value and tunnel
Corresponding relationship, to the detection car weight new definition.
It in this step, can be in advance in pair in relocation processor between storage environment parameter value and the position in tunnel
It should be related to, wherein in each embodiment provided herein, the environmental parameter measured value being previously mentioned refers to that camera acquires
The image or orbital image of the tunnel-side arrived, or refer to the radio frequency letter of the collected radio-frequency card of rf receiver unit
Number, the corresponding relationship between the parameter value in the tunnel being previously mentioned and the location information in the tunnel refers to that position is marked on tunnel table
Positional relationship or radio-frequency card positional relationship in tunnel of the positional relationship or fastener in face in tunnel.
According to the position of the environmental parameter value and tunnel stored in the environmental parameter measured value and relocation processor of acquisition
Corresponding relationship between setting, can be to the detection car weight new definition in tunnel.
Such as: in this step, camera acquires tunnel-side image, carries out to the image of collected tunnel-side pre-
Processing, such as: A D, binaryzation, image it is smooth, convert, enhance, restore, filtering etc. image preprocessings step, then to pre-
Treated, and image carries out feature extraction, extracts position mark and tab character in side wall image, the position that will be extracted later
It marks and tab character is marked with position pre-stored in relocation processor and tab character is matched, wherein be stored in advance
Position mark and tab character identify the position that position is marked in tunnel, according to matching result to detection car weight new definition.
Such as: in the embodiment of the present application, the extending direction along tunnel acquires the radiofrequency signal of at least one radio-frequency card, root
Being positioned according to its location information in tunnel stored in collected radio-frequency card to detection vehicle specifically can be by following step
It is rapid to realize: multiple first radio-frequency cards to be arranged with the second preset interval on the rail level in tunnel, default second interval is for example
It is 100 meters, the frequency range of the radio-frequency card is fixed frequency range, and user can be to its custom coding, for example, can in the radio-frequency card
Its location information in tunnel is at least stored in advance, radio frequency reception list is installed on the relocation device of the detection vehicle
Member can receive the radiofrequency signal that the radio-frequency card issues, and the radiofrequency signal issued according to the radio-frequency card is to the detection vehicle
It relocates.
It should be noted that above-mentioned acquisition tunnel-side image and identify the position in tunnel-side image mark and marker word
The radiofrequency signal of symbol and the radio-frequency card received and identified is technology known in those skilled in the art, herein without detailed
Thin expansion is described.
When using the method provided by the embodiments of the present application positioned using visual analysis to detection car weight, pass through detection vehicle
Corresponding relationship between the location information of the environmental parameter value and tunnel in environmental parameter measured value and tunnel, to detection vehicle into
Row positioning.Thus when the real-time positioning information recorded on displacement detector is reset, it can be to detection car weight new definition.
Fig. 2 is the flow chart using visual analysis to the method for detection car weight positioning in another embodiment of the application.
As shown in Fig. 2, the described method comprises the following steps:
S21. if detection vehicle displacement detector zeros data, the extending direction along tunnel are adopted in the process of moving
Collect tunnel-side image.
In this step, preset number camera can be set on detection vehicle, is imaged by the preset number
Head acquisition tunnel-side image, such as: 4 cameras towards different directions, each camera can be set on detection vehicle
The image for acquiring tunnel inner wall specific region, passes through the available tunnel-side complete image of four cameras.In the present embodiment
In, can along tunnel extending direction and along detection vehicle driving direction acquire tunnel-side image, can also be along tunnel
Extending direction and along detection vehicle driving direction opposite direction acquire tunnel-side image.
In the embodiment of the present application, detection vehicle can acquire tunnel before the defects of tunnel is detected and positioned
The image of road inner surface is simultaneously stored in weight processor, referred to as history tunnel-side image, wherein collected history tunnel
Side wall image includes at least following information: position of the history tunnel-side image in tunnel, acquires history tunnel-side image
The information such as time.
S22. the history tunnel-side image progress that will be stored in the collected tunnel-side image and database
Match, includes position of the history tunnel-side image in tunnel in the history tunnel-side image, according to matching result to institute
State detection car weight new definition.
In this step, collected tunnel-side image is sent to relocation processor by four cameras, reorientation
Processor is respectively handled the collected tunnel-side image of four cameras received, identifies four camera acquisitions
The tunnel-side image arrived, all history tunnel-side images progress that will be stored in recognition result and relocation processor
Match, traverse all history tunnel-side images stored in relocation processor, determines that detection vehicle stops fortune according to matching result
The location of when row, relocated to be realized to the detection vehicle in tunnel.
In other embodiments of the application, relocation processor is respectively to the four collected tunnels of camera received
Road side wall image is handled, and identifies the collected tunnel-side image of four cameras, later by constantly expanding search model
The mode enclosed traverses the history tunnel side stored in relocation processor in the pre-determined distance of displacement detector zeros data front and back
Wall image, by going through in pre-determined distance before and after the displacement detector zeros data stored in recognition result and relocation processor
History tunnel-side image is matched, the location of when determining that detection vehicle is out of service according to matching result, thus to tunnel
Interior detection vehicle, which is realized, to be relocated.
In other embodiments of the application, relocation processor can also be only to the collected tunnel side of a camera
Wall image is handled, and identifies the collected tunnel-side image of the camera, is stored in traversal relocation processor later
All history tunnel-side images carry out all history tunnel-side images stored in recognition result and relocation processor
Matching, the location of when determining that detection vehicle is out of service according to matching result, to be realized again to the detection vehicle in tunnel
Positioning.
In other embodiments of the application, relocation processor can also be only to the collected tunnel side of a camera
Wall image is handled, and identifies the collected tunnel-side image of the camera, passes through the side of constantly expansion search range later
The history tunnel-side stored in relocation processor in the pre-determined distance of front and back when formula traverses displacement detector zeros data
Image, by the history tunnel in recognition result and relocation processor when displacement detector zeros data in the preset time period of front and back
Road side wall image is matched, the location of when determining that detection vehicle is out of service according to matching result, thus in tunnel
It detects vehicle and realizes repositioning.
When using the method provided in an embodiment of the present invention positioned using visual analysis to detection car weight, by along tunnel
Extending direction acquires tunnel-side image, the history tunnel that will be stored in the side wall image of collected tunnel surface and database
Side wall image is matched, and includes position of the history tunnel-side image in tunnel, root in the history tunnel-side image
Detection vehicle is relocated according to matching result.To, when the real-time positioning information recorded on displacement detector is reset, energy
It is enough that detection vehicle is relocated again.
Fig. 3 is the flow chart using visual analysis to the method for detection car weight positioning in another embodiment of the application.
As shown in figure 3, the described method comprises the following steps:
S31. if the displacement detector zeros data in the process of moving of detection vehicle, the extending direction along tunnel is acquired
Orbital image, and include multiple fasteners in collected orbital image.
In this step, it is arranged between track and sleeper in two in tunnel multiple for connecting the button of track and sleeper
Part, the distance between fastener is fixed in tunnel, camera is provided on detection vehicle, in the image acquisition areas of camera
In domain, extending direction acquisition trajectory image and ambient enviroment image along tunnel, and collected orbital image includes multiple buttons
Part, wherein the ambient enviroment image can be the image around track, such as part tunnel-side image.
S32. it according to the collected orbital image, identifies fastener described in the orbital image, and counts and identify
The fastener number.
In this step, collected orbital image and ambient enviroment image can be pre-processed, extracts track
Fastener feature in image matches the fastener feature of extraction with fastener feature pre-stored in relocation processor,
So as to identify the fastener in orbital image, and count the number of the fastener identified.Wherein, in relocation processor in advance
The fastener of storage includes location information of the fastener in tunnel.
S33. according to the interval between the number of the fastener and each fastener to the detection car weight new definition.
In this step, due to the distance between fastener each in tunnel be it is fixed, according to the fastener identified
The position of vehicle is detected at interval between number and fastener when can determine displacement detector zeros data, so as to tunnel
Interior detection vehicle is relocated.
When using the method provided in an embodiment of the present invention positioned using visual analysis to detection car weight, pass through acquisition trajectory
Image identifies the fastener in orbital image, and counts fastener number, according to the interval between the fastener number identified and fastener
Position of the vehicle in tunnel is detected when can determine displacement detector zeros data.
Fig. 4 is the flow chart using visual analysis to the method for detection car weight positioning in another embodiment of the application.
As shown in Figure 4, which comprises
S41. if the displacement detector zeros data in the process of moving of detection vehicle, the extending direction along tunnel is acquired
Orbital image and tunnel-side image, the orbital image include multiple fasteners.
In this step, two cameras can be set at the wheel of detection vehicle two sides, be used for acquisition trajectory image, together
When can detection vehicle vehicle body on be arranged two cameras, for acquiring tunnel-side image.It can be along the traveling of detection vehicle
The opposite direction of direction or driving direction acquires tunnel track image and tunnel-side image, and the orbital image includes multiple buttons
Part.
S42. splicing is carried out to the orbital image and tunnel-side image, obtained spliced comprising including fastener
Fastener position at tunnel cross sectional image.
In this step, it can use merging algorithm for images to spell collected orbital image and tunnel-side image
Connecing processing, described image stitching algorithm may include feature point extraction and three matching, image registration and image co-registration steps,
In, the feature point extraction with match can by based on SRUF algorithm complete characteristics of image point sequence extraction, the SRUF
Algorithm and image registration and image fusion technology are the well-known techniques of those skilled in the art, and details are not described herein again.
S43. spliced tunnel cross sectional image is pre-processed and passes through convolutional neural networks trained in advance and mentioned
Take the feature of the spliced tunnel cross sectional image.
In this step, before tunnel environment is surveyed in detection car test, preparatory acquisition trajectory figure and tunnel-side figure are needed
Picture carries out splicing to the orbital image and tunnel-side image acquired in advance, the training as training convolutional neural networks
Image set is trained convolutional neural networks according to the image that training image is concentrated.Specifically, MATLAB can be passed through
(Matrix Laboratory, matrix labotstory) or Caffe even depth learn frame programming one convolutional neural networks of building.
When being trained to the convolutional neural networks, is concentrated from training image and obtain sample image, divide net on the sample image
Lattice are identified the feature of every a kind of sample image by convolutional neural networks, concentrate the every frame sample graph for including for training image
Picture identifies its feature by convolutional neural networks all in accordance with aforesaid way, can be learnt by above-mentioned training convolutional neural networks
To the corresponding characteristics of image of image of each classification.
Since convolutional neural networks trained in advance have learnt the corresponding characteristics of image of image of each classification, so passing through
Trained convolutional neural networks can determine the feature of spliced tunnel cross sectional image in advance.
S44. the history tunnel cross sectional that will be stored in the feature of the spliced tunnel cross sectional image and database
Image carry out aspect ratio to and identification, the history tunnel cross sectional image has its location information in tunnel, according to than
Position of the spliced tunnel cross sectional image in tunnel is determined to result, the detection vehicle is relocated.
In this step, according to the feature of spliced tunnel cross sectional image, and with the history tunnel that is stored in database
Which frame matching in road cross sectional image, since record has image place in each frame image in history tunnel cross sectional image
It realizes to can determine physical location of the detection vehicle in tunnel according to matching result to detection vehicle position in tunnel
Reorientation.
Using the method provided in an embodiment of the present invention positioned using visual analysis to detection car weight, after extracting splicing
Tunnel cross sectional image feature, determine that spliced tunnel cross sectional image exists by convolutional neural networks trained in advance
Position in tunnel, to realize to the detection car weight new definition in tunnel.
Fig. 5 is the structure chart using visual analysis to the device of detection car weight positioning in another embodiment of the application.
As shown in figure 5, the positioning device includes acquiring unit 51 and resets bit location 52.
Wherein, if acquiring unit 51 is used to detect the displacement detector of vehicle zeros data in the process of moving, acquisition
The environmental parameter measured value for detecting vehicle resets bit location 52 for the environmental parameter according to environmental parameter measured value and tunnel
Corresponding relationship between value and the location information in tunnel relocates detection vehicle.
In other embodiments of the invention, the acquiring unit is used for the extending direction acquisition trajectory image along tunnel,
It and include multiple fasteners in collected orbital image；The bit location that resets is used for according to the collected orbital image,
It identifies the fastener in the orbital image, and counts the number of the fastener identified；According to the number of the fastener
Interval between each fastener is to the detection car weight new definition.
In other of the invention embodiments, the acquiring unit be used for along tunnel extending direction acquisition trajectory image and
Tunnel-side image, the orbital image include multiple fasteners；The bit location that resets is for the orbital image and tunnel
Side wall image carries out splicing, obtains the image of the tunnel cross sectional at the spliced fastener position comprising including fastener；
After being pre-processed to spliced tunnel cross sectional image and pass through the convolutional neural networks extraction splicing trained in advance
Tunnel cross sectional image feature；The history that will be stored in the feature of the spliced tunnel cross sectional image and database
Tunnel cross sectional image carry out aspect ratio to and identification, the history tunnel cross sectional image have its in tunnel position letter
Breath, determines position of the spliced tunnel cross sectional image in tunnel according to comparison result, carries out to the detection vehicle
It relocates.
The device provided by the embodiments of the present application positioned using visual analysis to detection car weight, passes through the environment for obtaining detection
Measured value of parameters, according to corresponding between the environmental parameter value in environmental parameter measured value and tunnel and the location information in tunnel
Relationship positions detection vehicle.It, can be to the detection car weight in tunnel so as in displacement detector zeros data
New definition.
Fig. 6 is the structural representation using visual analysis to the system of detection car weight positioning in another embodiment of the application
Figure.As shown in fig. 6, the positioning system includes multiple position marks 61, multiple radio-frequency cards 62, multiple fasteners 63, detects vehicle 64,
In, the detection vehicle includes relocation device, rf receiver unit, camera and displacement detector, the relocation device,
Rf receiver unit, camera and displacement detector are separately positioned on detection vehicle, not shown herein.
Wherein, extending direction of multiple position marks 61 along tunnel is adopted with the image that the first preset interval is set to tunnel-side
Collect in area, position mark 61 includes tab character, and tab character is marked on the position of tunnel surface for mark position；Multiple radio-frequency cards
62 extending direction along tunnel is arranged in the first radio-frequency card 62 on the rail level in tunnel with the second preset interval and stores for issuing
There is the radiofrequency signal of its location information in tunnel, multiple fasteners 63 are fixed on rail flanges and make rail by fixed device
Road connects to achieve the purpose that trapped orbit with sleeper.
Detecting vehicle 64 includes relocation device, rf receiver unit, camera and displacement detector.
Wherein, the relocation device may include acquiring unit and reset bit location, if the acquiring unit is used for
The displacement detector zeros data in the process of moving for detecting vehicle, obtains the environmental parameter measured value of displacement detector, institute
It states and resets bit location between the location information according to the environmental parameter value and tunnel in environmental parameter measured value and tunnel
Corresponding relationship relocates detection vehicle.
The rf receiver unit is set to the vehicle body of detection vehicle, for receiving the radiofrequency signal of radio-frequency card sending；It is described
Camera is set to the vehicle body of detection vehicle, for acquiring tunnel-side image or orbital image, wherein acquisition tunnel-side figure
The camera of picture can be at least four, and the camera for acquiring the orbital image of tunnel-side can be at least two.Displacement detecting
Device is set to the outer of the wheel of detection vehicle, for recording operating range, direction and the speed of detection vehicle in real time.It needs
Bright, the exemplary only explanation of the number of camera, does not therefore limit the present invention herein.
In the present embodiment, the relocation device can be realized by way of hardware and/or software, and can generally collect
At in the processor for relocating service.The relocation device can be arranged in the enterprising enforcement of inspection vehicle and use.It is described to reset
Cunicular relevant information is stored in the database of bit processor, including but not limited to: tunnel title, geographical location information, tunnel
Road length, tunnel type, tunnel-side image, tunnel-side image information, each position are marked on the position of tunnel surface, trajectory diagram
Picture, the location information of fastener in the tunnel etc., the relocation device can by internet and relocation processor into
Row communication so that call the relevant information in tunnel as needed.
When displacement detector zeros data in the process of moving, the measuring part on relocation device is needed to obtain inspection
The environmental parameter measured value of measuring car, according to the location information of the environmental parameter value and tunnel in environmental parameter measured value and tunnel
Between corresponding relationship, redefine position of the detection vehicle in tunnel.
Such as: camera is provided on relocation device, in the image acquisition areas of tunnel-side, along the extension side in tunnel
Multiple for marking the position of tunnel surface to mark to being arranged in tunnel-side, position mark includes tab character, and tab character is used
It is marked on the position of tunnel surface in mark position, when displacement detector zeros data in the process of moving, along prolonging for tunnel
Direction acquisition tunnel-side image is stretched, and collected tunnel-side image includes at least one position target image, according to adopting
The tunnel-side image collected, identify tunnel-side image in position mark and tab character, according to position mark in marker word
Symbol is to detection car weight new definition.
Such as: two tracks are arranged in the extending direction in tunnel along tunnel, preset on the rail level of two tracks with second
Interval setting is multiple for marking the radio-frequency card of tunnel surface, and radio-frequency card is stored with its location information in tunnel, works as displacement
When detection device zeros data, the extending direction along tunnel acquires the radio-frequency information of at least one radio-frequency card, according to collected
Its location information in tunnel stored in radio-frequency card is to detection car weight new definition.
Such as: in this step, it is arranged between track and sleeper in two in tunnel multiple for connecting track and rail
The fastener of pillow, the distance between fastener is fixed in tunnel, camera is provided on detection vehicle, in the image of camera
In pickup area, extending direction acquisition trajectory image along tunnel, and the image of collected tunnel inner wall includes multiple fasteners.
Collected orbital image can be pre-processed, the fastener feature in orbital image be extracted, by extraction
Fastener feature is matched with fastener feature pre-stored in relocation processor, so as to identify the button in orbital image
Part, and count the number of the fastener identified.Wherein, pre-stored fastener includes fastener in tunnel in relocation processor
Location information.
Due to the distance between fastener each in tunnel be it is fixed, according to the fastener number and fastener identified
Between interval the position of vehicle is detected when can determine displacement detector zeros data, so as to the detection vehicle in tunnel
It is relocated.
Such as: preset number camera can be set on detection vehicle, be acquired by the preset number camera
Tunnel-side image, such as: 4 cameras towards different directions can be set on detection vehicle, and each camera acquires tunnel
The image of road inner wall specific region passes through the complete image of four available tunnel-sides of camera.In the present embodiment, may be used
It, can also be along the extension side in tunnel to acquire tunnel Derby image along the extending direction in tunnel and along the driving direction of detection vehicle
To and along detection vehicle driving direction opposite direction acquire tunnel-side image.
In the embodiment of the present application, detection vehicle can acquire tunnel before the defects of tunnel is detected and positioned
The image of road inner surface is simultaneously stored in relocation processor, referred to as history tunnel-side image, wherein collected history
Tunnel-side image includes at least following information: position of the history tunnel-side image in tunnel, acquires history tunnel-side
The information such as the time of image.
The image of collected tunnel surface is sent to relocation processor, relocation processor difference by four cameras
The collected tunnel-side image of four cameras received is handled, identifies the collected tunnel side of four cameras
Wall image matches all history tunnel-side images stored in recognition result and relocation processor, and traversal is reset
All history tunnel-side images stored in bit processor, locating position when determining that detection vehicle is out of service according to matching result
It sets, is relocated to be realized to the detection vehicle in tunnel.
In other embodiments of the application, relocation processor is respectively to the four collected tunnels of camera received
Road side wall image is handled, and identifies the collected tunnel-side image of four cameras, later by constantly expanding search model
The mode enclosed traverses the history tunnel side stored in relocation processor in the pre-determined distance of displacement detector zeros data front and back
Wall image, by going through in pre-determined distance before and after the displacement detector zeros data stored in recognition result and relocation processor
History tunnel-side image is matched, the location of when determining that detection vehicle is out of service according to matching result, thus to tunnel
Interior detection vehicle, which is realized, to be relocated.
In other embodiments of the application, relocation processor can also be only to a collected tunnel table of camera
The image in face is handled, and identifies the collected tunnel-side image of the camera, traverses store in relocation processor later
All history tunnel-side images, by all history tunnel-side images stored in recognition result and relocation processor into
Row matching, the location of when determining that detection vehicle is out of service according to matching result, to realize weight to the detection vehicle in tunnel
New definition.
In other embodiments of the application, relocation processor can also be only to the collected tunnel side of a camera
Wall image is handled, and identifies the collected tunnel-side image of the camera, passes through the side of constantly expansion search range later
The history tunnel-side stored in relocation processor in the pre-determined distance of front and back when formula traverses displacement detector zeros data
Image, by the history tunnel in recognition result and relocation processor when displacement detector zeros data in the pre-determined distance of front and back
Side wall image is matched, the location of when determining that detection vehicle is out of service according to matching result, thus to the inspection in tunnel
Measuring car, which is realized, to be relocated.
When using the system provided in an embodiment of the present invention positioned using visual analysis to detection car weight, detection can be utilized
Corresponding relationship between the environmental parameter of environmental parameter measured value and tunnel that vehicle obtains and the location information in tunnel, to inspection
Measuring car relocates.
It should be noted that in the system provided in an embodiment of the present invention positioned using visual analysis to detection car weight, it can
To select to realize reorientation using in a manner of which kind of according to the actual situation, it is not limited to by the way of can only be using one of fixation
Realize reorientation.Such as: a certain moment displacement detector zeros data in the process of moving, detection vehicle is in the mistake for continuing traveling
Cheng Zhong, rf receiver unit are initially received vision signal, then realize reorientation using the radio-frequency card in tunnel at this time；Such as:
In another moment displacement detector, zeros data, detection vehicle identify at first during continuing traveling in the process of moving
The mark character that out position is put on then realizes reorientation using the position mark of tunnel-side at this time.
Method or apparatus described in above-described embodiment that this specification provides can realize that business is patrolled by computer program
It collects and records on a storage medium, the storage medium can be read and be executed with computer, realize this specification embodiment institute
The effect of description scheme.Therefore, this specification also provides a kind of device using visual analysis to detection car weight positioning, including place
The memory for managing device and storage processor executable instruction realizes to include following step when described instruction is executed by the processor
It is rapid:
If the displacement detector of detection vehicle in the process of moving survey by zeros data, the environmental parameter for obtaining detection vehicle
Magnitude；
According between the location information of the environmental parameter value and the tunnel in the environmental parameter measured value and tunnel
Corresponding relationship positions the detection vehicle.
The storage medium may include the physical unit for storing information, usually by after information digitalization again with benefit
The media of the modes such as electricity consumption, magnetic or optics are stored.It may include: that letter is stored in the way of electric energy that the storage medium, which has,
The device of breath such as, various memory, such as RAM, ROM；The device of information is stored in the way of magnetic energy such as, hard disk, floppy disk, magnetic
Band, core memory, magnetic bubble memory, USB flash disk；Using optical mode storage information device such as, CD or DVD.Certainly, there are also it
Readable storage medium storing program for executing of his mode, such as quantum memory, graphene memory etc..
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
A kind of device that detection car weight is positioned using visual analysis described in above-described embodiment, according to the environment of detection vehicle
Corresponding relationship between the location information of the environmental parameter value and tunnel in measured value of parameters and tunnel, to detection car weight positioning.
This specification also provide it is a kind of using visual analysis to detection car weight positioning system, the system may include to
A few processor and the memory for storing computer executable instructions, the processor is realized above-mentioned when executing described instruction
The step of method described in any one or multiple embodiments.
It should be noted that system described above can also include others according to the description of method or Installation practice
Embodiment, concrete implementation mode are referred to the description of related method embodiment, do not repeat one by one herein.
A kind of system that detection car weight is positioned using visual analysis described in above-described embodiment, according to the environment of detection vehicle
Corresponding relationship between the location information of the environmental parameter value and tunnel in measured value of parameters and tunnel, to detection car weight positioning.
It should be noted that this specification device or system described above according to the description of related method embodiment also
It may include other embodiments, concrete implementation mode is referred to the description of embodiment of the method, does not go to live in the household of one's in-laws on getting married one by one herein
It states.All the embodiments in this specification are described in a progressive manner, and same and similar part is mutual between each embodiment
Mutually referring to each embodiment focuses on the differences from other embodiments.Especially for hardware+program
For class, storage medium+program embodiment, since it is substantially similar to the method embodiment, so be described relatively simple, it is related
Place illustrates referring to the part of embodiment of the method.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, vehicle-mounted human-computer interaction device, media player, navigation equipment, tablet computer or
The combination of any equipment in these equipment of person.
For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each module can be realized in the same or multiple software and or hardware when specification one or more, it can also be with
The module for realizing same function is realized by the combination of multiple submodule or subelement etc..Installation practice described above is only
It is only illustrative, for example, in addition the division of the unit, only a kind of logical function partition can have in actual implementation
Division mode, such as multiple units or components can be combined or can be integrated into another system or some features can be with
Ignore, or does not execute.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be logical
Some interfaces are crossed, the indirect coupling or communication connection of device or unit can be electrical property, mechanical or other forms.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is complete
Entirely can by by method and step carry out programming in logic come so that controller with logic gate, switch, specific integrated circuit, programmable
Logic controller realizes identical function with the form for being embedded in microcontroller etc..Therefore this controller is considered one kind
Hardware component, and the structure that the device for realizing various functions that its inside includes can also be considered as in hardware component.Or
Person even, can will be considered as realizing the device of various functions either the software module of implementation method can be hardware again
Structure in component.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method or equipment of element.
It will be understood by those skilled in the art that this specification one or more embodiment can provide as method, system or calculating
Machine program product.Therefore, this specification one or more embodiment can be used complete hardware embodiment, complete software embodiment or
The form of embodiment combining software and hardware aspects.Moreover, this specification one or more embodiment can be used at one or
It is multiple wherein include computer usable program code computer-usable storage medium (including but not limited to magnetic disk storage,
CD-ROM, optical memory etc.) on the form of computer program product implemented.
This specification one or more embodiment can computer executable instructions it is general on
It hereinafter describes, such as program module.Generally, program module includes executing particular task or realization particular abstract data type
Routine, programs, objects, component, data structure etc..This this specification one can also be practiced in a distributed computing environment
Or multiple embodiments, in these distributed computing environments, by being held by the connected remote processing devices of communication network
Row task.In a distributed computing environment, program module can be located at the local and remote computer including storage equipment
In storage medium.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ",
The description of " specific example " or " some examples " etc. means specific features described in conjunction with this embodiment or example, structure, material
Or feature is contained at least one embodiment or example of this specification.In the present specification, to the signal of above-mentioned term
Property statement must not necessarily be directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other,
Those skilled in the art can be by different embodiments or examples described in this specification and different embodiments or examples
Feature is combined.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (7)
1. a kind of method positioned using visual analysis to detection car weight characterized by comprising
If the displacement detector of detection vehicle in the process of moving survey by zeros data, the environmental parameter for obtaining the detection vehicle
Magnitude；
According to corresponding between the environmental parameter value in the environmental parameter measured value and tunnel and the location information in the tunnel
Relationship, to the detection car weight new definition；
Include: to the detection car weight new definition
Extending direction acquisition trajectory image along tunnel, and include multiple fasteners in collected orbital image；
According to the collected orbital image, the fastener in the orbital image is identified, according to the fastener pair identified
The detection car weight new definition.
2. the method according to claim 1 positioned using visual analysis to detection car weight, feature are existed,
Extending direction acquisition trajectory image along tunnel, and include multiple fasteners in collected orbital image；
According to the collected orbital image, identify the fastener in the orbital image, and count identify it is described
The number of fastener；
According to the interval between the number of the fastener and each fastener to the detection car weight new definition.
3. the method according to claim 1 positioned using visual analysis to detection car weight, which is characterized in that
Extending direction acquisition trajectory image and tunnel-side image along tunnel, the orbital image include multiple fasteners；
Splicing is carried out to the orbital image and tunnel-side image, obtains the spliced fastener position comprising including fastener
Set the image of the tunnel cross sectional at place；
Spliced tunnel cross sectional image is pre-processed and passes through convolutional neural networks trained in advance and extracts the spelling
The feature of tunnel cross sectional image after connecing；
The history tunnel cross sectional image stored in the feature of the spliced tunnel cross sectional image and database is carried out
Aspect ratio to and identification, the history tunnel cross sectional image has its location information in tunnel, true according to comparison result
Fixed position of the spliced tunnel cross sectional image in tunnel, relocates the detection vehicle.
4. a kind of device positioned using visual analysis to detection car weight characterized by comprising
Acquiring unit, if displacement detector for detecting vehicle zeros data in the process of moving, obtains the detection vehicle
Environmental parameter measured value；
Bit location is reset, for the position according to the environmental parameter value in the environmental parameter measured value and tunnel and the tunnel
Corresponding relationship between confidence breath, to the detection car weight new definition；
The acquiring unit is used for the extending direction acquisition trajectory image along tunnel, and comprising multiple in collected orbital image
Fastener；
The bit location that resets identifies the fastener in the orbital image for according to the collected orbital image,
According to the fastener identified to the detection car weight new definition.
5. the device according to claim 4 positioned using visual analysis to detection car weight, it is characterised in that
The acquiring unit is used for extending direction acquisition trajectory image and tunnel-side image along tunnel, the orbital image packet
Containing multiple fasteners；
The fastener that bit location is reset for identification in the orbital image, and count the number of the fastener identified
Mesh；According to the interval between the number of the fastener and each fastener to the detection car weight new definition.
6. the device according to claim 4 positioned using visual analysis to detection car weight, which is characterized in that the acquisition
Unit is used for extending direction acquisition trajectory image and tunnel-side image along tunnel, and the orbital image includes multiple fasteners；
The bit location that resets obtains spliced packet for carrying out splicing to the orbital image and tunnel-side image
Image containing the tunnel cross sectional at the fastener position including fastener；Spliced tunnel cross sectional image is pre-processed simultaneously
The feature of the spliced tunnel cross sectional image is extracted by convolutional neural networks trained in advance；It will be described spliced
The history tunnel cross sectional image that is stored in the feature and database of tunnel cross sectional image carry out aspect ratio to and identification, it is described
History tunnel cross sectional image has its location information in tunnel, determines that the spliced tunnel is horizontal according to comparison result
Position of the cross-sectional image in tunnel relocates the detection vehicle.
7. a kind of system positioned using visual analysis to detection car weight characterized by comprising
Multiple fasteners are fitted in rail flanges and by fixed device track are connected with sleeper；
Detect vehicle；
The detection vehicle includes relocation device, rf receiver unit, camera and displacement detector, wherein
The positioning device is the device as claimed in claim 4 using visual analysis to detection car weight positioning；
The camera, for acquiring tunnel-side image or orbital image；
Institute's displacement sensing device, for recording operating range, direction and the speed of detection vehicle in real time；
If detecting displacement detector zeros data, the camera acquisition trajectory image in the process of moving of vehicle, and adopt
It include multiple fasteners in the orbital image collected；The bit location that resets identifies the rail according to the orbital image is collected
The fastener in road image, and the number of the fastener identified is counted, according to the number of the fastener and each fastener
Between interval to the detection car weight new definition；Or
If zeros data, the acquiring unit are used for the extension along tunnel to the displacement detector of detection vehicle in the process of moving
Direction acquisition trajectory image and tunnel-side image, the orbital image include multiple fasteners；It is described reset bit location for pair
The orbital image and tunnel-side image carry out splicing, obtain at the spliced fastener position comprising including fastener
The image of tunnel cross sectional；Spliced tunnel cross sectional image is pre-processed and passes through convolutional Neural net trained in advance
Network extracts the feature of the spliced tunnel cross sectional image；By the feature and number of the spliced tunnel cross sectional image
According to the history tunnel cross sectional image that is stored in library carry out aspect ratio to and identification, the history tunnel cross sectional image have it
Location information in tunnel determines position of the spliced tunnel cross sectional image in tunnel according to comparison result,
The detection vehicle is relocated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810775617.9A CN109029377A (en) | 2018-07-16 | 2018-07-16 | It is a kind of using visual analysis to detection car weight positioning square law device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810775617.9A CN109029377A (en) | 2018-07-16 | 2018-07-16 | It is a kind of using visual analysis to detection car weight positioning square law device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109029377A true CN109029377A (en) | 2018-12-18 |
Family
ID=64642551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810775617.9A Pending CN109029377A (en) | 2018-07-16 | 2018-07-16 | It is a kind of using visual analysis to detection car weight positioning square law device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109029377A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242919A (en) * | 2020-01-10 | 2020-06-05 | 成都协创信和科技有限公司 | Absolute positioning method and positioning system based on sleeper defects on track path |
| CN111243022A (en) * | 2020-01-10 | 2020-06-05 | 成都协创信和科技有限公司 | Bottom layer absolute positioning method and positioning system based on track path |
| CN112393617A (en) * | 2020-03-26 | 2021-02-23 | 中冶长天国际工程有限责任公司 | Method, device, equipment and medium for detecting wheels of trolley of annular cooler |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104048969A (en) * | 2014-06-19 | 2014-09-17 | 樊晓东 | Tunnel defect recognition method |
| CN105407530A (en) * | 2015-12-08 | 2016-03-16 | 北京百度网讯科技有限公司 | Tunnel positioning method and device |
| CN105548205A (en) * | 2016-01-28 | 2016-05-04 | 北京工业大学 | Tunnel surface defect positioning method and positioning system |
| CN106096660A (en) * | 2016-06-22 | 2016-11-09 | 东南大学 | Convolutional neural networks based on independent composition analysis algorithm |
| CN106709462A (en) * | 2016-12-29 | 2017-05-24 | 天津中科智能识别产业技术研究院有限公司 | Indoor positioning method and device |
| CN108090912A (en) * | 2017-12-13 | 2018-05-29 | 李正伟 | A kind of track detection method and system based on image identification |
| CN108204985A (en) * | 2018-01-16 | 2018-06-26 | 上海同岩土木工程科技股份有限公司 | A kind of shield tunnel mileage localization method |
-
2018
- 2018-07-16 CN CN201810775617.9A patent/CN109029377A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104048969A (en) * | 2014-06-19 | 2014-09-17 | 樊晓东 | Tunnel defect recognition method |
| CN105407530A (en) * | 2015-12-08 | 2016-03-16 | 北京百度网讯科技有限公司 | Tunnel positioning method and device |
| CN105548205A (en) * | 2016-01-28 | 2016-05-04 | 北京工业大学 | Tunnel surface defect positioning method and positioning system |
| CN106096660A (en) * | 2016-06-22 | 2016-11-09 | 东南大学 | Convolutional neural networks based on independent composition analysis algorithm |
| CN106709462A (en) * | 2016-12-29 | 2017-05-24 | 天津中科智能识别产业技术研究院有限公司 | Indoor positioning method and device |
| CN108090912A (en) * | 2017-12-13 | 2018-05-29 | 李正伟 | A kind of track detection method and system based on image identification |
| CN108204985A (en) * | 2018-01-16 | 2018-06-26 | 上海同岩土木工程科技股份有限公司 | A kind of shield tunnel mileage localization method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242919A (en) * | 2020-01-10 | 2020-06-05 | 成都协创信和科技有限公司 | Absolute positioning method and positioning system based on sleeper defects on track path |
| CN111243022A (en) * | 2020-01-10 | 2020-06-05 | 成都协创信和科技有限公司 | Bottom layer absolute positioning method and positioning system based on track path |
| CN112393617A (en) * | 2020-03-26 | 2021-02-23 | 中冶长天国际工程有限责任公司 | Method, device, equipment and medium for detecting wheels of trolley of annular cooler |
| CN112393617B (en) * | 2020-03-26 | 2022-06-03 | 中冶长天国际工程有限责任公司 | Method, device, equipment and medium for detecting wheels of trolley of annular cooler |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109029373A (en) | The synthesized positioning method and device of vehicle are detected in a kind of tunnel | |
| CN109029372A (en) | A kind of detection vehicle localization method and device | |
| US9047668B2 (en) | Location determination for an object using visual data | |
| EP2697738B1 (en) | Method and system of rail component detection using vision technology | |
| CN109029377A (en) | It is a kind of using visual analysis to detection car weight positioning square law device and system | |
| CN103871077B (en) | A kind of extraction method of key frame in road vehicles monitoring video | |
| CN110674236A (en) | Moving target association method, device and equipment based on space-time trajectory matching and storage medium | |
| CN106156695B (en) | Outlet and/or entrance area recognition methods and device | |
| CN109615862A (en) | Road vehicle movement of traffic state parameter dynamic acquisition method and device | |
| CN102855508B (en) | Opening type campus anti-following system | |
| KR101645959B1 (en) | The Apparatus and Method for Tracking Objects Based on Multiple Overhead Cameras and a Site Map | |
| CN103514429B (en) | Detect the method and image processing equipment of the privileged site of object | |
| CN105807335A (en) | Vehicle chassis inspection method and system | |
| CN103699677A (en) | Criminal track map drawing system and method based on face recognition | |
| CN110647886A (en) | Interest point marking method and device, computer equipment and storage medium | |
| CN109029374A (en) | It is a kind of to analyze the method and device positioned to measuring car using visual pattern | |
| US10104494B2 (en) | Marker based activity transition models | |
| CN111121797B (en) | Road screening method, device, server and storage medium | |
| Lisanti et al. | A multi-camera image processing and visualization system for train safety assessment | |
| Ji et al. | Validation of global airport spatial locations from open databases using deep learning for runway detection | |
| CN110889338A (en) | Unsupervised railway track bed foreign matter detection and sample construction method and unsupervised railway track bed foreign matter detection and sample construction device | |
| CN111899505B (en) | Detection method and device for traffic restriction removal | |
| CN109029376A (en) | A kind of method for relocating and device detecting vehicle | |
| CN109029375A (en) | The method for relocating apparatus and system of vehicle is detected in a kind of tunnel | |
| Makrigiorgis et al. | How High can you Detect? Improved accuracy and efficiency at varying altitudes for Aerial Vehicle Detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201216 Address after: Building C6, Guishan Minbo Cultural Park, 39 Pingshan North Road, Gulou District, Xuzhou City, Jiangsu Province, 221000 Applicant after: Zhongke (Xuzhou) Artificial Intelligence Research Institute Co.,Ltd. Address before: Room 501-1753, Development Zone office building, 8 Xingsheng South Road, Miyun District Economic Development Zone, Beijing Applicant before: Yinhe waterdrop Technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |