CN110217271A - Fast railway based on image vision invades limit identification monitoring system and method - Google Patents
Fast railway based on image vision invades limit identification monitoring system and method Download PDFInfo
- Publication number
- CN110217271A CN110217271A CN201910463975.0A CN201910463975A CN110217271A CN 110217271 A CN110217271 A CN 110217271A CN 201910463975 A CN201910463975 A CN 201910463975A CN 110217271 A CN110217271 A CN 110217271A
- Authority
- CN
- China
- Prior art keywords
- train
- image
- range information
- foreign matter
- acquisition module
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000002390 adhesive tape Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention proposes a kind of fast railways based on image vision to invade limit identification monitoring system and method, the monitoring system includes the first acquisition module for acquiring train front distant view image and range information in real time, the second acquisition module for acquiring close shot image and range information in front of train in real time being set on train, and first acquisition module and the second acquisition module are connect with main control unit；The main control unit judges whether there is the distance between foreign body intrusion, the position of foreign matter, foreign matter and train according to the information that the first acquisition module and the second acquisition module acquire.The monitoring system structure is simple, can promptly and accurately judge that train front track with the presence or absence of the distance between foreign body intrusion, the position of foreign matter, foreign matter and train, improves the safety of rail traffic.Equipment can be mounted on independent operating on vehicle in use or engineering truck by the monitoring system, realize that zero couples with train communication system, have independence, real-time and stronger anti-interference ability.
Description
Technical field
The present invention relates to rail traffic security fields, and in particular to a kind of fast railway based on image vision invades limit identification
Monitor system and method.
Background technique
Foreign matter invades train travel limit (letter be " invading limit ") event, causes large effect to operation, and subway tunnel
It is interior, because the subway circulation time is long, safeguard not in place or person works carelessness etc., also resulting in device location variation in tunnel causes
Equipment invades subway driving limit, leads to train accident；Especially in the case where dispatching system fault conditions, due to train position
It cannot timely feedback, train colliding accident is caused to often occur；
The foreign matter for invading limit can be divided into following a few classes: 1) may influence the foreign matter of driving: balloon, umbrella on route, contact
The foreign matters such as the adhesive tape near net or rail, it is also possible to which train operation is caused indirectly to influence.2) foreign matter of driving: route is influenced
The equipment of limit, the external world are invaded into foreign matters such as the large-sized objects of people in side, will cause directly to threaten to train operation.3) contact net or steel
Foreign matter near rail: pantograph requires high-precision to match with contact net, and any foreign matter between bow net is likely to lead to contact net
The large-scale power supply trouble such as tripping.
The discovery and processing for invading limit object for trains such as railway, subways at present need a large amount of personnel mainly by manual patrol
It participates in, polling period is long, the vehicle human window phase of monitoring time generally at night, it is difficult to find the problem at the first time.Often
It is caused the accident because foreign matter invades in-orbit train travel limit.
The patents such as CN201010141132 and CN201310044445 give a kind of based on fixed monitoring foreign bodies system
System, every locking terminal equipment can only monitor the foreign body intrusion situation of fixed area；Deployed with devices quantity is more, monitoring area is limited, and
And need to carry out warning message communication transfer using communication system, there is certain time delay.
Summary of the invention
In order to overcome above-mentioned defect existing in the prior art, the object of the present invention is to provide a kind of based on image vision
Fast railway invades limit identification monitoring system and method.
In order to realize above-mentioned purpose of the invention, limit is invaded the present invention provides a kind of fast railway based on image vision and is known
Not Jian Ce system, including be set on train for acquiring the first acquisition of distant view image and range information in front of train in real time
Module, the second acquisition module for acquiring close shot image and range information in front of train in real time, first acquisition module and
Second acquisition module is connect with main control unit；
The information of information, the acquisition of the second acquisition module that the main control unit acquires the first acquisition module carries out figure
Picture, range information fusion, obtain realtime graphic, the range information of whole scene in front of train, and will obtain the real-time figure of whole scene
Picture, range information carry out deep learning analysis with the foreign matter characteristic information prestored, judge whether there is foreign body intrusion, foreign matter class
The distance between type, the position of foreign matter, foreign matter and train.
The monitoring system structure is simple, can promptly and accurately judge train front track with the presence or absence of foreign body intrusion, different
The distance between position, foreign matter and train of object improve the safety of rail traffic.Equipment can be mounted on by the monitoring system
On vehicle in use or engineering truck, there is independence, real-time and stronger anti-interference ability.
The application also proposed a kind of fast railway based on image vision and invade limit identification monitoring method, including following step
It is rapid:
The realtime graphic and range information of distant view in front of train are obtained in real time；
The realtime graphic and range information of close shot in front of train are obtained in real time；
By the realtime graphic and range information of the realtime graphic of the distant view and range information and close shot carry out image,
Range information fusion, obtains image, the range information of whole scene in front of train；
Track extraction is carried out by fused image, and steering and range information and operation vehicle letter according to track
Breath real-time dynamicly generates virtual train driving limit；
The image of whole scene, range information in front of obtained train are subjected to deep learning with the foreign matter characteristic information prestored
Analysis, judge virtual train driving limit in whether have between foreign matter, foreign matter type, the position of foreign matter, foreign matter and train away from
From.
The beneficial effects of the present invention are: the present invention is based on the identification of image analysis, safety monitoring and fast target, vision are real-time
The technologies such as ranging carry out real time distance using image, and according to real time imaging train travel limit；Pass through depth simultaneously
Practising algorithm has the function of target identification, greatly improves the real-time for invading limit monitoring, while can set to important near rail
Standby realize is arranged to monitor in real time.Equipment can be mounted on independent operating on vehicle in use or engineering truck by the monitoring system, with column
Vehicle communication system realizes zero coupling, has independence, real-time and stronger anti-interference ability.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of composition block diagram for embodiment that fast railway invades limit identification monitoring system；
Fig. 2 is the composition block diagram for the another embodiment that fast railway invades limit identification monitoring system；
Fig. 3 is the flow diagram that fast railway invades limit identification monitoring method.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that term " installation ", " connected ",
" connection " shall be understood in a broad sense, for example, it may be mechanical connection or electrical connection, the connection being also possible to inside two elements can
, can also indirectly connected through an intermediary, for the ordinary skill in the art to be to be connected directly, it can basis
Concrete condition understands the concrete meaning of above-mentioned term.
As depicted in figs. 1 and 2, the present invention provides a kind of fast railways based on image vision to invade limit identification monitoring system
It unites, acquires the first acquisition module of distant view image and range information in front of train, use for real-time including being set on train
The second acquisition module of close shot image and range information in front of acquisition train in real time, first acquisition module and the second acquisition
Module is connect with main control unit 4.First acquisition module and the second acquisition module are acquiring train just in real time under synchronous triggering signal
The image and range data in front.
The information of information, the acquisition of the second acquisition module that the main control unit acquires the first acquisition module carries out figure
Picture, range information fusion, obtain realtime graphic, the range information of whole scene in front of train, and will obtain the real-time figure of whole scene
Picture, range information carry out deep learning analysis with the foreign matter characteristic information prestored, judge whether there is foreign body intrusion, foreign matter class
The distance between type, the position of foreign matter, foreign matter and train.
The monitoring system further includes the display module 5 for showing the realtime graphic of whole scene, range information in front of train
With the sound and light alarm module 6 for alarm, when track 7 is there are when foreign body intrusion, main control unit 4 controls sound and light alarm module 6 and sends out
Alarm out.Also, main control unit 4 can control sound and light alarm module 6 to issue alternative sounds, different colours light, to be used for inhomogeneity
The prompt or warning of type alarm.Display module 5 is preferably but not limited to as human-computer interaction module, can be used as parameter input and in real time
Image data show, warning message output.
First acquisition module, the second acquisition module are mounted on immediately ahead of the driver's cabin of train, and main control unit 4 is mounted on driving
Below the bridge of room, display module 5 and sound and light alarm module 6 are generally positioned near driver's seat, are observed convenient for driver.
In the present embodiment, the first acquisition module includes the first binocular vision module 1 with telephoto lens, first binocular
Vision module 1 acquires distant view image in front of train, and the image that main control unit 4 acquires the first binocular vision module 1 utilizes binocular
Location algorithm obtains distant view range information.
Second acquisition module is preferably but not limited to following two structure:
The first: the second acquisition module includes the second binocular vision module 8, the acquisition of the second binocular vision module 8 column
Front side close shot image and range information.
The second binocular vision module 8 completes the Image Acquisition of short distance, main control unit using the optical lens of short focus
The image that second binocular vision module 8 acquires is obtained close shot range information using binocular location algorithm by 4.
Second: second acquisition module includes monocular vision module 2 and 3 D laser scanning module 3, the monocular
Vision module 2 acquires close shot image in front of train, and the 3 D laser scanning module 3 acquires close shot range information in front of train,
3 D laser scanning module 3 is by completing to close shot distance in front of train the three-dimensional distance information collection in entire detection range
The acquisition of information.The monocular image and three-dimensional distance information superposition that main control unit 4 acquires monocular vision module 2.
As shown in figure 3, the invention also provides a kind of fast railways based on image vision to invade limit identification monitoring method, packet
It includes following steps: obtaining the realtime graphic and range information of distant view in front of train in real time using above-mentioned monitoring system, obtain in real time
The realtime graphic and range information for taking close shot in front of train, by the realtime graphic of the distant view and range information and close shot
Realtime graphic and range information carry out image, range information fusion, obtain image, the range information of whole scene in front of train.
The realtime graphic of whole scene in front of train is carried out track 7 and extracted by main control unit 4.
The method of extraction are as follows: the first binocular vision module 1 obtains the image of distant view, and is measured often by binocular location algorithm
Distance of a pixel to the first binocular vision module 1；Take the image of a telephoto lens camera of the first binocular vision module 1
After data are filtered algorithm and binary conversion treatment, the information of errant 7 is extracted, and calculates 7 steering direction of track and angle, this
In the algorithm that is related to be all existing algorithm, and will not be described here in detail.
Virtual train is real-time dynamicly generated according to the steering of track 7, angle and distance information and operation information of vehicles
Driving limit:
" train travel limit " is the maximum Dynamic Envelope that train is formed under normal operating conditions, mainly by train
Outer profile size, technical parameter, orbital characteristics etc. determine, for fixed subway line, its train travel is limited on different location
Boundary is determining.
And " virtual train driving limit " be then " the train travel limit " that will determine turned to according to track, angle and distance
Parameter projects on the coordinate system of image, and shows " the virtual train driving limit " generated on the image, shows on the image
When " virtual train driving limit ", usually fixed with dummy line circle.
Limit is invaded if there is foreign matter is then determined with object in " the virtual train driving limit ", initial graph can be passed through here
Obtains whether there is object to invade limit as being compared with realtime graphic, can also use deep learning algorithm by realtime graphic with prestore
Foreign matter characteristic information carry out feature identification obtain whether there is object to invade limit.
And foreign matter is divided into many kinds, such as the adhesive tape near balloon, umbrella, contact net, rail, wall-mounted device, extraneous entrance
Large-sized object, animal, people, etc..
It is so that object is invaded in limited time in judgement, main control unit 4 is will to obtain whole scene by deep learning algorithm
Realtime graphic, range information and the foreign matter characteristic information that prestores carry out deep learning analysis, judge whether there is foreign body intrusion, different
The distance between position, foreign matter and train of object.
And the foreign matter characteristic information prestored is the foreign matter spy for carrying out that feature training is obtained to foreign matter deep learning algorithm early period
Model, such as wall-mounted device are levied, by acquiring the image of its different conditions, can be obtained accurately after a large amount of image training
Model, the late into the night learning algorithm and feature extracting method referred here to are existing method, are no longer described in detail.
Especially some critical facility equipment need key monitoring, and emphasis identifies that main control unit 4 is important to what is identified
Facilities and equipment state carries out real-time report, and record of depositing.
Critical facility equipment is closed guard gate or other fixed equipments at present；For determining route, closed guard gate or other are solid
The position of locking equipment and state be it is determining, closed guard gate or his fixed equipment can be identified by image recognition, will be initial
The image of state and the image comparison of captured in real-time can realize the monitoring of fixed equipment, whether monitor it in initial shape
On state position.Such as: closed guard gate was open originally, can save the state of closed guard gate at this time when system is run for the first time,
When system is in real-time monitoring operation, the image of closed guard gate can be obtained when train reaches this position also；Pass through original state image
It goes to judge whether people's air defense door state changes with the difference of the image of captured in real-time, such as closed guard gate moves certain position, or
Invade " train travel limit " etc..Other fixed equipments are same, such as wall-mounted device, fall off, then being scarce in this location device
It loses.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is defined by the claims and their equivalents.
Claims (7)
1. a kind of fast railway based on image vision invades limit identification monitoring system, it is characterised in that: including being set on train
For acquiring the first acquisition module of distant view image and range information in front of train in real time, it is close in front of train for acquiring in real time
Second acquisition module of scape image and range information, first acquisition module and the second acquisition module are connect with main control unit；
Information that the main control unit acquires the first acquisition module, the information of the second acquisition module acquisition carry out image, away from
Merged from information, obtain realtime graphic, the range information of whole scene in front of train, and by obtain whole scene realtime graphic, away from
Deep learning analysis is carried out with the foreign matter characteristic information prestored from information, judges whether there is foreign body intrusion, foreign matter type, foreign matter
The distance between position, foreign matter and train.
2. the fast railway according to claim 1 based on image vision invades limit identification monitoring system, it is characterised in that: institute
Stating the first acquisition module includes the first binocular vision module with telephoto lens, and the first binocular vision module acquires train
Front distant view image and range information.
3. the fast railway according to claim 1 based on image vision invades limit identification monitoring system, it is characterised in that: institute
Stating the second acquisition module includes the second binocular vision module, in front of the second binocular vision module acquisition train close shot image and
Range information.
4. the fast railway according to claim 1 based on image vision invades limit identification monitoring system, it is characterised in that: institute
Stating the second acquisition module includes monocular vision module and 3 D laser scanning module, the monocular vision module acquisition train front
Close shot image, 3 D laser scanning module acquisition train front close shot range information.
It further include for showing 5. the fast railway according to claim 1 based on image vision invades limit identification monitoring system
Show the display module of the realtime graphic of whole scene, range information in front of train.
6. the fast railway according to claim 1 based on image vision invades limit identification monitoring system, further include and master control
The sound and light alarm module of unit connection.
7. a kind of fast railway based on image vision invades limit identification monitoring method, which comprises the following steps:
The realtime graphic and range information of distant view in front of train are obtained in real time；
The realtime graphic and range information of close shot in front of train are obtained in real time；
The realtime graphic and range information of the realtime graphic of the distant view and range information and close shot are subjected to image, distance
Information fusion, obtains image, the range information of whole scene in front of train；
Track extraction is carried out by fused image, and steering and range information and operation information of vehicles reality according to track
When be dynamically generated virtual train driving limit；
The image of whole scene, range information in front of obtained train are subjected to deep learning point with the foreign matter characteristic information prestored
Analysis judges whether there is the distance between foreign matter, foreign matter type, the position of foreign matter, foreign matter and train in virtual train driving limit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463975.0A CN110217271A (en) | 2019-05-30 | 2019-05-30 | Fast railway based on image vision invades limit identification monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463975.0A CN110217271A (en) | 2019-05-30 | 2019-05-30 | Fast railway based on image vision invades limit identification monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110217271A true CN110217271A (en) | 2019-09-10 |
Family
ID=67819066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910463975.0A Pending CN110217271A (en) | 2019-05-30 | 2019-05-30 | Fast railway based on image vision invades limit identification monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110217271A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110596769A (en) * | 2019-09-29 | 2019-12-20 | 长沙理工大学 | Track foreign matter detection method, device, equipment and medium |
| CN110654422A (en) * | 2019-11-12 | 2020-01-07 | 中科(徐州)人工智能研究院有限公司 | Rail train driving assistance method, device and system |
| CN110712665A (en) * | 2019-10-22 | 2020-01-21 | 深圳市微度数字技术有限公司 | Intelligent auxiliary device for safe driving of locomotive |
| CN111062268A (en) * | 2019-11-28 | 2020-04-24 | 佳讯飞鸿（北京）智能科技研究院有限公司 | Trackside object intrusion detection method and system |
| CN111091076A (en) * | 2019-12-03 | 2020-05-01 | 西北工业大学 | Tunnel limit data measuring method based on stereoscopic vision |
| CN111899242A (en) * | 2020-07-29 | 2020-11-06 | 北京大成国测科技有限公司 | Intrusion detection method and device based on multi-source signals |
| CN112810669A (en) * | 2020-07-17 | 2021-05-18 | 周慧 | Intercity train operation control platform and method |
| CN113011252A (en) * | 2021-02-04 | 2021-06-22 | 成都希格玛光电科技有限公司 | Track foreign matter intrusion detection system and method |
| CN114529811A (en) * | 2020-11-04 | 2022-05-24 | 中国科学院沈阳自动化研究所 | Rapid and automatic identification and positioning method for foreign matters in subway tunnel |
| CN116834802A (en) * | 2023-07-03 | 2023-10-03 | 湖北空间智能技术有限公司 | Method, equipment and storage medium for detecting and positioning invaded objects in operation train track |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654502A (en) * | 2016-03-30 | 2016-06-08 | 广州市盛光微电子有限公司 | Panorama camera calibration device and method based on multiple lenses and multiple sensors |
| CN105719239A (en) * | 2016-01-21 | 2016-06-29 | 科盾科技股份有限公司 | Image splicing method and image splicing device |
| CN106156780A (en) * | 2016-06-29 | 2016-11-23 | 南京雅信科技集团有限公司 | The method getting rid of wrong report on track in foreign body intrusion identification |
| CN106254777A (en) * | 2016-08-23 | 2016-12-21 | 深圳市德盟科技有限公司 | A kind of integral intelligent starlight level monopod video camera |
| CN107087107A (en) * | 2017-05-05 | 2017-08-22 | 中国科学院计算技术研究所 | Image processing apparatus and method based on dual camera |
| CN107249096A (en) * | 2016-06-14 | 2017-10-13 | 杭州海康威视数字技术股份有限公司 | Panoramic camera and its image pickup method |
| CN107454318A (en) * | 2017-07-27 | 2017-12-08 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
| US20180043829A1 (en) * | 2016-08-10 | 2018-02-15 | Surround.IO Corporation | Method and Apparatus for Providing Automatic Mirror Setting Via Inward Facing Cameras |
| CN108399600A (en) * | 2018-02-23 | 2018-08-14 | 清华-伯克利深圳学院筹备办公室 | A kind of omnidirectional imaging system and method |
| CN108583620A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | The processor and early warning system of train assistance tracking early warning |
| CN108583622A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | Recognition methods, device, equipment and the medium of rail traffic situation |
| CN108983219A (en) * | 2018-08-17 | 2018-12-11 | 北京航空航天大学 | A kind of image information of traffic scene and the fusion method and system of radar information |
| CN109285136A (en) * | 2018-08-31 | 2019-01-29 | 清华-伯克利深圳学院筹备办公室 | A kind of Multiscale Fusion method, apparatus, storage medium and the terminal of image |
| CN109614957A (en) * | 2019-01-04 | 2019-04-12 | 王卫星 | A kind of railway shunting signals security early warning system |
-
2019
- 2019-05-30 CN CN201910463975.0A patent/CN110217271A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719239A (en) * | 2016-01-21 | 2016-06-29 | 科盾科技股份有限公司 | Image splicing method and image splicing device |
| CN105654502A (en) * | 2016-03-30 | 2016-06-08 | 广州市盛光微电子有限公司 | Panorama camera calibration device and method based on multiple lenses and multiple sensors |
| CN107249096A (en) * | 2016-06-14 | 2017-10-13 | 杭州海康威视数字技术股份有限公司 | Panoramic camera and its image pickup method |
| CN106156780A (en) * | 2016-06-29 | 2016-11-23 | 南京雅信科技集团有限公司 | The method getting rid of wrong report on track in foreign body intrusion identification |
| US20180043829A1 (en) * | 2016-08-10 | 2018-02-15 | Surround.IO Corporation | Method and Apparatus for Providing Automatic Mirror Setting Via Inward Facing Cameras |
| CN106254777A (en) * | 2016-08-23 | 2016-12-21 | 深圳市德盟科技有限公司 | A kind of integral intelligent starlight level monopod video camera |
| CN107087107A (en) * | 2017-05-05 | 2017-08-22 | 中国科学院计算技术研究所 | Image processing apparatus and method based on dual camera |
| CN107454318A (en) * | 2017-07-27 | 2017-12-08 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
| CN108399600A (en) * | 2018-02-23 | 2018-08-14 | 清华-伯克利深圳学院筹备办公室 | A kind of omnidirectional imaging system and method |
| CN108583620A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | The processor and early warning system of train assistance tracking early warning |
| CN108583622A (en) * | 2018-04-02 | 2018-09-28 | 交控科技股份有限公司 | Recognition methods, device, equipment and the medium of rail traffic situation |
| CN108983219A (en) * | 2018-08-17 | 2018-12-11 | 北京航空航天大学 | A kind of image information of traffic scene and the fusion method and system of radar information |
| CN109285136A (en) * | 2018-08-31 | 2019-01-29 | 清华-伯克利深圳学院筹备办公室 | A kind of Multiscale Fusion method, apparatus, storage medium and the terminal of image |
| CN109614957A (en) * | 2019-01-04 | 2019-04-12 | 王卫星 | A kind of railway shunting signals security early warning system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110596769A (en) * | 2019-09-29 | 2019-12-20 | 长沙理工大学 | Track foreign matter detection method, device, equipment and medium |
| CN110712665A (en) * | 2019-10-22 | 2020-01-21 | 深圳市微度数字技术有限公司 | Intelligent auxiliary device for safe driving of locomotive |
| CN110654422B (en) * | 2019-11-12 | 2022-02-01 | 银河水滴科技（北京）有限公司 | Rail train driving assistance method, device and system |
| CN110654422A (en) * | 2019-11-12 | 2020-01-07 | 中科(徐州)人工智能研究院有限公司 | Rail train driving assistance method, device and system |
| CN111062268A (en) * | 2019-11-28 | 2020-04-24 | 佳讯飞鸿（北京）智能科技研究院有限公司 | Trackside object intrusion detection method and system |
| CN111091076B (en) * | 2019-12-03 | 2022-03-11 | 西北工业大学 | Tunnel limit data measuring method based on stereoscopic vision |
| CN111091076A (en) * | 2019-12-03 | 2020-05-01 | 西北工业大学 | Tunnel limit data measuring method based on stereoscopic vision |
| CN112810669A (en) * | 2020-07-17 | 2021-05-18 | 周慧 | Intercity train operation control platform and method |
| CN111899242A (en) * | 2020-07-29 | 2020-11-06 | 北京大成国测科技有限公司 | Intrusion detection method and device based on multi-source signals |
| CN111899242B (en) * | 2020-07-29 | 2022-04-05 | 北京大成国测科技有限公司 | Intrusion detection method and device based on multi-source signals |
| CN114529811A (en) * | 2020-11-04 | 2022-05-24 | 中国科学院沈阳自动化研究所 | Rapid and automatic identification and positioning method for foreign matters in subway tunnel |
| CN113011252A (en) * | 2021-02-04 | 2021-06-22 | 成都希格玛光电科技有限公司 | Track foreign matter intrusion detection system and method |
| CN113011252B (en) * | 2021-02-04 | 2023-12-05 | 成都希格玛光电科技有限公司 | Rail foreign matter intrusion detection system and method |
| CN116834802A (en) * | 2023-07-03 | 2023-10-03 | 湖北空间智能技术有限公司 | Method, equipment and storage medium for detecting and positioning invaded objects in operation train track |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110217271A (en) | Fast railway based on image vision invades limit identification monitoring system and method | |
| TWI478835B (en) | System and method for preventing vehicle collision | |
| CN104691559B (en) | Monitoring station platform safety door and car door interval safe accessory system and its implementation | |
| CN102945603B (en) | Method for detecting traffic event and electronic police device | |
| CN106061793A (en) | Imaging system and method | |
| CN112180605B (en) | Auxiliary driving system based on augmented reality | |
| CN111198371A (en) | Forward-looking obstacle detection system | |
| WO2019069581A1 (en) | Image processing device and image processing method | |
| CN105679043A (en) | 3D radar intelligent bayonet system and processing method thereof | |
| CZ271698A3 (en) | Method of warning railway vehicle controller from presence of obstacle on the track and system for making the same | |
| JP2000244897A (en) | State recognition system and state recognition display generation method | |
| KR20090118582A (en) | Unexpcted accident monitoring system | |
| CN104134350A (en) | Intelligent dome camera system for traffic violation behavior recognition | |
| CN111717243B (en) | Rail transit monitoring system and method | |
| CN105185114A (en) | Device and method for collecting evidence of vehicle regulation-violating lane changing behavior | |
| CN107123270A (en) | A kind of intelligent managing and control system in building site for slag-soil truck | |
| CN105701453A (en) | Railway ballast vehicle with obstacle identification system and obstacle identification method | |
| CN106131485A (en) | A kind of continuous milling machine monitored by personnel's system and monitoring method | |
| JP2013067215A (en) | Camera device for monitoring movable platform fence | |
| KR102187021B1 (en) | Front low-speed vehicle notification system | |
| CN113562005A (en) | Intelligent monitoring and obstacle intrusion limit detecting system for driver behaviors of rail train | |
| BG113786A (en) | Equipment installed onboard railway trains for detection of objects and their subsequent classification | |
| CN108122414A (en) | The detection method and device of car on-board and off-board on highway | |
| CN106778619A (en) | A kind of pedestrian detection method combined based on laser and vision signal | |
| CN110908003A (en) | Active barrier detection system based on unmanned driving |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |