CN109101887A - The rail cars control method of view-based access control model analysis - Google Patents
The rail cars control method of view-based access control model analysis Download PDFInfo
- Publication number
- CN109101887A CN109101887A CN201810762547.3A CN201810762547A CN109101887A CN 109101887 A CN109101887 A CN 109101887A CN 201810762547 A CN201810762547 A CN 201810762547A CN 109101887 A CN109101887 A CN 109101887A
- Authority
- CN
- China
- Prior art keywords
- locomotive
- pantograph
- detection
- signal lamp
- vehicle
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61C—LOCOMOTIVES; MOTOR RAILCARS
- B61C17/00—Arrangement or disposition of parts; Details or accessories not otherwise provided for; Use of control gear and control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention belongs to fields of automation technology, more particularly, to a kind of rail cars control method of view-based access control model analysis, characterized by comprising: step 1, locomotive operation positioning；Step 2, signal lamp identification；The detection of other objects such as step 3, people, vehicle, roadblock；The character recognition of step 4, locomotive unit number；Step 5, the judgement of the state of pantograph.The present invention replaces the control means of conventional method to realize the automation of locomotive system using principle of stereoscopic vision, target detection, character recognition scheduling algorithm.Touchless visual control method, both manpower is saved under mine and, it is conducive to Central Control Center again to observe situation under mine in real time and operated control, introduce binocular camera shooting system, traditional two dimension monitoring is expanded into three-dimensional space, the three dimensional local information of target, and the function that cannot be completed using conventional planars camera systems such as operation positioning, target detection and the range estimations of the information realization rail cars are obtained using stereoscopic vision principle of parallax.
Description
Technical field
The invention belongs to fields of automation technology, more particularly, to a kind of rail cars controlling party of view-based access control model analysis
Method.
Background technique
Rail mounted transport system is the important component of sub-terrain mines production.Since sub-terrain mines production environment is poor, personnel's labour
Intensity is big, and the demand of rail cars automatic running is more and more stronger.Current rail cars automatic control system is all based on center
Master control issues control signal, and on-vehicle host receives control instruction and carries out the movement such as start and stop.This scheme requires underground whole network to cover
Lid, such as WiFi, Zigbee, 3G etc., due to needing whole network to cover, so construction investment is big.
Summary of the invention
The signal lamp that the object of the present invention is to provide a kind of by identifying vision system, track, tunnel situation, and make to have
The rail cars control method of the view-based access control model analysis of the movements such as gage locomotive can be started, be stopped, acceleration and deceleration.
The purpose of the present invention is what is realized by following technical proposals:
The rail cars control method of view-based access control model analysis of the invention, characterized by comprising:
Step 1, locomotive operation positioning
(1) in sub-terrain mines, video camera is installed at interval of certain distance along locomotive operation track, whether fixed point detection locomotive runs
Pass through；The distance interval of installation video camera is determined by effective shooting distance of video camera, to guarantee locomotive always in video camera system
Within the range of operation of system；
(2) it in the rectangle mark of locomotive side and back side setting yellow, and is marked in the mark using unified coding rule
This locomotive unit number, can effectively to identify different locomotives when detecting；
(3) when video camera identifies the mark with locomotive, then it is assumed that locomotive target occurs, and is identified at this time using character recognition
Number in mark is to determine the number information of current vehicle；
(4) distance of the target machine vehicle apart from video camera is calculated using Binocular Vision Principle, the installation of camera chain is combined with this
Location information, so that it may realize the running position positioning of different locomotives；
Step 2, signal lamp identification
(1) in locomotive front end, installation binocular camera carries out signal lamp identification and the identification of other objects；
(2) the location information feedback function for utilizing locomotive, judges the position of locomotive and track crossings or setting signal lamp
Distance opens the signal lamp identification function of locomotive when the distance reaches a certain range；
(3) color shown by the signal lamp using color detection cognitron front side, feeds back to locomotive then to control locomotive
Operating status；
The detection of other objects such as step 3, people, vehicle, roadblock
Other objects such as people, vehicle and roadblock in front of locomotive operation are detected using the binocular camera of locomotive front end；Due to machine
The running track of vehicle is relatively fixed, and locomotive running state includes straight trip substantially, turns left, turns right and four kinds of intersection situation, for
For every case, the accessible normal operation track imaging in the video that the binocular camera of locomotive front end is shot is
It can estimate, therefore be made comparisons according to the normal operation track imaging under different situations with current orbit imaging, be obtained current
Whether imaging has object appearance；
The character recognition of step 4, locomotive unit number
(1) locomotive body rear is equipped with special identifier, and front object is detected according to the color detection of the mark or characteristic matching
Body whether other locomotives；
(2) determine whether front detectable substance is people using edge feature；
(3) for the roadblock being especially arranged, the mark of special color should be set to, according to the color of setting or feature into
Row judgement；And for other situations, then it is assumed that be the appearance of other objects；
Step 5, the judgement of the state of pantograph
Whether contacted successfully with transmission line with transmission line level height comparable position installation phase machine testing pantograph；Due to by
Pantograph when rising and falling on angle between frame and lower wall bar it is different, and transmission line is being contacted with pantograph and is not being connect
Significant change can occur for height when touching, therefore be calculated above-mentioned geometric parameter to judge pantograph using video data
Working condition checks whether there is abnormal appearance.
In the detection of other objects such as the signal lamp identification and people, vehicle, roadblock, at three-dimensional video-frequency and image
The processing of the various features such as reason technology, aggregate color, shape and template progress different target.
In the state judgement of the pantograph, using image detection and divide determining pantograph position and transmission line position
It sets, then estimates the geometric parameters such as pantograph angle and transmission line height, carry out the judgement of pantograph working condition.
Advantages of the present invention:
The rail cars control method of view-based access control model analysis of the invention has broken the thought of Traditional control, using utilizing stereopsis
Feel that principle, target detection, character recognition scheduling algorithm replace the control means of conventional method, realizes locomotive system using computer vision
The automation of system.This touchless intuitive control method not only saves manpower under mine and, but also is conducive to center control
Situation under mine is observed in real time and is operated control in center processed.Traditional video and image taking is confined to the table of plane information
It reaches, the plan position information of shooting object can only be provided, this will receive limitation in many practical applications.Main wound of the invention
New point is to introduce binocular camera shooting system based on computer vision, and traditional two dimension monitoring is expanded to three-dimensional space, using vertical
Body vision principle of parallax obtains the three dimensional local information of target, and utilizes the operation positioning of the information realization rail cars, target
The function that the conventional planars camera system such as detection and range estimation cannot be completed.
Specific embodiment
A specific embodiment of the invention is further illustrated below.
The rail cars control method of view-based access control model analysis of the invention, characterized by comprising:
Step 1, locomotive operation positioning
(1) in sub-terrain mines, video camera is installed at interval of certain distance along locomotive operation track, whether fixed point detection locomotive runs
Pass through；The distance interval of installation video camera is determined by effective shooting distance of video camera, to guarantee locomotive always in video camera system
Within the range of operation of system；
(2) it in the rectangle mark of locomotive side and back side setting yellow, and is marked in the mark using unified coding rule
This locomotive unit number, can effectively to identify different locomotives when detecting；
(3) when video camera identifies the mark with locomotive, then it is assumed that locomotive target occurs, and is identified at this time using character recognition
Number in mark is to determine the number information of current vehicle；
(4) distance of the target machine vehicle apart from video camera is calculated using Binocular Vision Principle, the installation of camera chain is combined with this
Location information, so that it may realize the running position positioning of different locomotives；
Step 2, signal lamp identification
(1) in locomotive front end, installation binocular camera carries out signal lamp identification and the identification of other objects；
(2) the location information feedback function for utilizing locomotive, judges the position of locomotive and track crossings or setting signal lamp
Distance opens the signal lamp identification function of locomotive when the distance reaches a certain range；
(3) color shown by the signal lamp using color detection cognitron front side, feeds back to locomotive then to control locomotive
Operating status；
The detection of other objects such as step 3, people, vehicle, roadblock
Other objects such as people, vehicle and roadblock in front of locomotive operation are detected using the binocular camera of locomotive front end；Due to machine
The running track of vehicle is relatively fixed, and locomotive running state includes straight trip substantially, turns left, turns right and four kinds of intersection situation, for
For every case, the accessible normal operation track imaging in the video that the binocular camera of locomotive front end is shot is
It can estimate, therefore be made comparisons according to the normal operation track imaging under different situations with current orbit imaging, be obtained current
Whether imaging has object appearance；Orbital region is our focus, therefore above-mentioned detection is locked in one around orbital region
Determine range progress.Here detection is not limited to people, vehicle and roadblock, can also detect other objects in addition to this.
The character recognition of step 4, locomotive unit number
(1) locomotive body rear is equipped with special identifier, and front object is detected according to the color detection of the mark or characteristic matching
Body whether other locomotives；
(2) determine whether front detectable substance is people using edge feature；
(3) for the roadblock being especially arranged, the mark of special color should be set to, according to the color of setting or feature into
Row judgement；And for other situations, then it is assumed that be the appearance of other objects；
Step 5, the judgement of the state of pantograph
Whether contacted successfully with transmission line with transmission line level height comparable position installation phase machine testing pantograph；Due to by
Pantograph when rising and falling on angle between frame and lower wall bar it is different, and transmission line is being contacted with pantograph and is not being connect
Significant change can occur for height when touching, therefore be calculated above-mentioned geometric parameter to judge pantograph using video data
Working condition checks whether there is abnormal appearance.
In the detection of other objects such as the signal lamp identification and people, vehicle, roadblock, at three-dimensional video-frequency and image
The processing of the various features such as reason technology, aggregate color, shape and template progress different target.
In the state judgement of the pantograph, using image detection and divide determining pantograph position and transmission line position
It sets, then estimates the geometric parameters such as pantograph angle and transmission line height, carry out the judgement of pantograph working condition.
This method introduces binocular camera camera system and realizes locomotive using real-time stereoscopic video images processing technique
Operation positions, the identification of intersection traffic lights, the people's, vehicle, the real-time detection of roadblock and motorcycle pantograph in operational process
State etc..The appointed condition needed are as follows:
1) the rectangle mark of yellow is set in locomotive side and below, and marks the number of the locomotive in mark；Specific road
Barrier mark is also identified using special color, to detect and to identify；
2) in underground mine, positioning system is constituted at interval of certain distance installation binocular camera along locomotive operation track；
3) binocular camera is installed in front of locomotive and carries out the detection of signal lamp and the detection of objects in front；
4) in the position for needing to detect pantograph, video camera is set according to the level height of transmission line, for detecting pantograph work
Make state；
5) good illumination condition in mine.
Specific implementation method is following aspects:
1) object space information is estimated using principle of stereoscopic vision
It can be evaluated whether the three dimensional local information of target using the video that binocular camera is shot, and then can estimate locomotive to be positioned
Relative to the distance of video camera to realize that locomotive operation positions, it can estimate signal lamp and intersection at a distance from locomotive to control
Locomotive continues to run or stops, and can estimate the object occurred in front of locomotive at a distance from locomotive to adjust locomotive speed.
In stereoscopic vision, important technical point includes binocular camera correction, image Stereo matching and disparity computation.It is double
The correction of lens camera is to carry out parallel correction and horizontal contour correction to the optical axis of two cameras of stereoscopic camera, it is vertical
The basis that body vision is realized.The image that camera obtains is the information source of subsequent calculating, only the camera ability by strictly correcting
The accurate information of target object can be obtained, therefore the correction of stereoscopic camera is most important.Stereo matching is clapped binocular camera
The left images taken the photograph carry out matched process, it is the prerequisite for calculating parallax.Only target object is being found in left and right figure
The corresponding points of picture, can just calculate the parallax of respective point, and then calculate its location information.Disparity computation is the base to work in front
On plinth, the picture position difference operation of match point is carried out, is then then converted to three-dimensional spatial positional information.So far, it just obtains
The spatial positional information of target object.
2) target detection
Target detection includes the detection of signal lamp, the detection of locomotive, and the detection of locomotive objects in front (people, vehicle, roadblock etc.) is related to
Color detection, shape contour detection, the technical points such as template matching.
In the signal identification of locomotive identification, the identification of specific roadblock and signal lamp, since their color characteristic is very bright
It is aobvious, therefore identified using method for detecting color and position these objects.Color space has numerous selections, and this method uses YCbCr
Color detection is carried out in space thus can be certain because color is had the characteristics that separate coloration with brightness by YCbCr space
Degree reduces influence of the different illumination to color detection effect；And Y, Cb, Cr can pass through linear transformation by three primary colours R, G, B
It obtains, computational efficiency is relatively high, while avoiding the singularity of non-linear space.
Machine testing objects in front is imaged in front of locomotive when whether occurring, pre-estimate locomotive straight trip, left-hand rotation, right-hand rotation,
Normal imaging situation when occurring in the case of four kinds of intersection without object, then with current real-time detection to image carry out pair
Than.Track region is determined in comparison process, the difference occurred in the area will be by the result as object detection.It
Afterwards, if necessary to be further determined that the object detected, then can be judged whether according to color and shape contour feature
For other locomotives, specific roadblock and people.If it is not, then the object that inspection measures is unexpected object or barrier.
In pantograph state-detection, need to estimate the geometric parameters such as angle and the height of objects in images.Firstly, it is necessary to
It determines the position of pantograph and the position of transmission line in image and is split, then calculated in pantograph according to the result of segmentation
The height of angle and transmission line between frame and lower wall bar.
3) character recognition
After locomotive appears in video camera coverage and is identified, it is also necessary to the label on its vehicle body is identified, this
It needs to use character recognition technologies.Character recognition is realized using template matching, using the character of unified standard in different vehicle
On mark is numbered, this provides good condition for template matching.
The rail cars control method of view-based access control model analysis of the invention has broken the thought of Traditional control, vertical using utilizing
Body vision principle, target detection, character recognition scheduling algorithm replace the control means of conventional method, realize machine using computer vision
The automation of vehicle system.This touchless intuitive control method not only saves manpower under mine and, but also is conducive to
Centre control centre observes situation under mine in real time and is operated control.Traditional video and image taking is confined to plane information
Expression, can only provide shooting object plan position information, this will receive limitation in many practical applications.Master of the invention
It wants innovative point to be to introduce binocular camera shooting system based on computer vision, traditional two dimension monitoring is expanded into three-dimensional space, benefit
The three dimensional local information of target is obtained with stereoscopic vision principle of parallax, and positioned using the operation of the information realization rail cars,
The function that the conventional planars such as target detection and range estimation camera system cannot be completed.
Claims (3)
1. a kind of rail cars control method of view-based access control model analysis, characterized by comprising:
Step 1, locomotive operation positioning
(1) in sub-terrain mines, video camera is installed at interval of certain distance along locomotive operation track, whether fixed point detection locomotive runs
Pass through；The distance interval of installation video camera is determined by effective shooting distance of video camera, to guarantee locomotive always in video camera system
Within the range of operation of system；
(2) it in the rectangle mark of locomotive side and back side setting yellow, and is marked in the mark using unified coding rule
This locomotive unit number, can effectively to identify different locomotives when detecting；
(3) when video camera identifies the mark with locomotive, then it is assumed that locomotive target occurs, and is identified at this time using character recognition
Number in mark is to determine the number information of current vehicle；
(4) distance of the target machine vehicle apart from video camera is calculated using Binocular Vision Principle, the installation of camera chain is combined with this
Location information, so that it may realize the running position positioning of different locomotives；
Step 2, signal lamp identification
(1) in locomotive front end, installation binocular camera carries out signal lamp identification and the identification of other objects；
(2) the location information feedback function for utilizing locomotive, judges the position of locomotive and track crossings or setting signal lamp
Distance opens the signal lamp identification function of locomotive when the distance reaches a certain range；
(3) color shown by the signal lamp using color detection cognitron front side, feeds back to locomotive then to control locomotive
Operating status；
The detection of other objects such as step 3, people, vehicle, roadblock
Other objects such as people, vehicle and roadblock in front of locomotive operation are detected using the binocular camera of locomotive front end；Due to machine
The running track of vehicle is relatively fixed, and locomotive running state includes straight trip substantially, turns left, turns right and four kinds of intersection situation, for
For every case, the accessible normal operation track imaging in the video that the binocular camera of locomotive front end is shot is
It can estimate, therefore be made comparisons according to the normal operation track imaging under different situations with current orbit imaging, be obtained current
Whether imaging has object appearance；
The character recognition of step 4, locomotive unit number
(1) locomotive body rear is equipped with special identifier, and front object is detected according to the color detection of the mark or characteristic matching
Body whether other locomotives；
(2) determine whether front detectable substance is people using edge feature；
(3) for the roadblock being especially arranged, the mark of special color should be set to, according to the color of setting or feature into
Row judgement；And for other situations, then it is assumed that be the appearance of other objects；
Step 5, the judgement of the state of pantograph
Whether contacted successfully with transmission line with transmission line level height comparable position installation phase machine testing pantograph；Due to by
Pantograph when rising and falling on angle between frame and lower wall bar it is different, and transmission line is being contacted with pantograph and is not being connect
Significant change can occur for height when touching, therefore be calculated above-mentioned geometric parameter to judge pantograph using video data
Working condition checks whether there is abnormal appearance.
2. the rail cars control method of view-based access control model analysis according to claim 1, it is characterised in that in the letter
In the detection of other objects such as signal lamp identification and people, vehicle, roadblock, three-dimensional video-frequency and image processing techniques, aggregate color, shape are utilized
The processing of the various features such as shape and template progress different target.
3. the rail cars control method of view-based access control model analysis according to claim 1, it is characterised in that described by electricity
In the state judgement of bow, using image detection and divides determining pantograph position and transmission line position, then estimate pantograph angle
The geometric parameters such as degree and transmission line height, carry out the judgement of pantograph working condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810762547.3A CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810762547.3A CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109101887A true CN109101887A (en) | 2018-12-28 |
| CN109101887B CN109101887B (en) | 2022-03-15 |
Family
ID=64846177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810762547.3A Active CN109101887B (en) | 2018-07-12 | 2018-07-12 | Rail locomotive control method based on visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101887B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740526A (en) * | 2018-12-29 | 2019-05-10 | 清华大学苏州汽车研究院（吴江） | Signal lamp recognition methods, device, equipment and medium |
| CN111666947A (en) * | 2020-05-26 | 2020-09-15 | 成都唐源电气股份有限公司 | Pantograph head offset measurement method and system based on 3D imaging |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100322465A1 (en) * | 2007-08-06 | 2010-12-23 | Qr Limited | Pantograph damage and wear monitoring system |
| CN201825066U (en) * | 2010-10-20 | 2011-05-11 | 成都可益轨道技术有限公司 | Automatic locomotive ground signal and obstacle recognition system |
| CN102507601A (en) * | 2011-11-08 | 2012-06-20 | 南京大学 | Online abrasion detection method and system for pantograph of electric locomotive |
| CN205059645U (en) * | 2015-10-21 | 2016-03-02 | 武汉钢铁(集团)公司 | Railway freight car license number automatic identification system |
| CN105718902A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Contact net pantograph stagger value overrun defect recognition method and system |
| CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
-
2018
- 2018-07-12 CN CN201810762547.3A patent/CN109101887B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100322465A1 (en) * | 2007-08-06 | 2010-12-23 | Qr Limited | Pantograph damage and wear monitoring system |
| CN201825066U (en) * | 2010-10-20 | 2011-05-11 | 成都可益轨道技术有限公司 | Automatic locomotive ground signal and obstacle recognition system |
| CN102507601A (en) * | 2011-11-08 | 2012-06-20 | 南京大学 | Online abrasion detection method and system for pantograph of electric locomotive |
| CN205059645U (en) * | 2015-10-21 | 2016-03-02 | 武汉钢铁(集团)公司 | Railway freight car license number automatic identification system |
| CN105718902A (en) * | 2016-01-25 | 2016-06-29 | 成都国铁电气设备有限公司 | Contact net pantograph stagger value overrun defect recognition method and system |
| CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740526A (en) * | 2018-12-29 | 2019-05-10 | 清华大学苏州汽车研究院（吴江） | Signal lamp recognition methods, device, equipment and medium |
| CN109740526B (en) * | 2018-12-29 | 2023-06-20 | 清华大学苏州汽车研究院（吴江） | Signal lamp identification method, device, equipment and medium |
| CN111666947A (en) * | 2020-05-26 | 2020-09-15 | 成都唐源电气股份有限公司 | Pantograph head offset measurement method and system based on 3D imaging |
| CN111666947B (en) * | 2020-05-26 | 2023-08-04 | 成都唐源电气股份有限公司 | Pantograph head offset measuring method and system based on 3D imaging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109101887B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104949619B (en) | Vehicle stereoscopic image processing device | |
| CN105157608B (en) | A kind of detection method of overrun vehicle, apparatus and system | |
| US9280900B2 (en) | Vehicle external environment recognition device | |
| EP1981748B1 (en) | System for measuring speed of a train | |
| US11024051B2 (en) | Object detection device | |
| US9978276B2 (en) | Vehicle exterior environment recognition device | |
| US9349070B2 (en) | Vehicle external environment recognition device | |
| CN110126824A (en) | A kind of commercial vehicle AEBS system of integrated binocular camera and millimetre-wave radar | |
| CN106218492B (en) | A kind of night running light automatic switching control equipment and switching method | |
| Barrois et al. | 3D pose estimation of vehicles using a stereo camera | |
| CN111727437A (en) | Multispectral system providing pre-crash warning | |
| CN110097591A (en) | The detection method of bow net state | |
| Drulea et al. | Omnidirectional stereo vision using fisheye lenses | |
| CN106327461B (en) | A kind of image processing method and device for monitoring | |
| CN109101887A (en) | The rail cars control method of view-based access control model analysis | |
| WO2017094300A1 (en) | Image processing device, object recognition device, device conrol system, image processing method, and program | |
| CN106970581A (en) | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group | |
| CN109827516A (en) | A method of distance is measured by wheel | |
| US9524645B2 (en) | Filtering device and environment recognition system | |
| US9659376B2 (en) | Filtering device | |
| CN105335934B (en) | Disparity map computational methods and device | |
| CN108197590A (en) | A kind of pavement detection method, apparatus, terminal and storage medium | |
| JP2015179066A (en) | Parallax value derivation device, apparatus control system, moving body, robot, parallax value derivation method and program | |
| CN106197374A (en) | Car body angle excursion measuring method | |
| CN108317997A (en) | Vibration detecting system based on the rail vehicle of video analysis in tunnel |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |