CN205890910U - Limit detecting device is invaded with track foreign matter that infrared light combines to visible light - Google Patents
Limit detecting device is invaded with track foreign matter that infrared light combines to visible light Download PDFInfo
- Publication number
- CN205890910U CN205890910U CN201620671947.XU CN201620671947U CN205890910U CN 205890910 U CN205890910 U CN 205890910U CN 201620671947 U CN201620671947 U CN 201620671947U CN 205890910 U CN205890910 U CN 205890910U
- Authority
- CN
- China
- Prior art keywords
- visible light
- infrared light
- foreign body
- terminal server
- detection device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The utility model discloses a limit detecting device is invaded with track foreign matter that infrared light combines to visible light, including video acquisition subassembly, digital video recorder, video processing server and terminal server, the video acquisition subassembly is including dividing the visible light camera and infrared camera machine of locating train head both sides, and digital video recorder receives image information and the storage that comes from the video acquisition subassembly, and the video processing server carries out digital video recorder 1 to image information to to calculate result feedback to terminal server, terminal server shows surveying the result. The utility model discloses a foreign matter is invaded and is limit detecting device through combining to have improved identifiability to visible light and infrared light, adopts the mode that the visible light camera is given first place to, the infrared camera machine is the assistance when light and visibility very good, when haze (overhead scene) or luminance not enough (tunnel low light level scene), the automatic switch -over to the infrared camera machine give first place to, the visible light is for subsidiary for the identification accuracy of this detecting device under extreme condition improves greatly.
Description
Technical field
This utility model is related to a kind of foreign body intrusion detection device, the rail that a kind of visible ray of specific design is combined with infrared light
Road foreign body intrusion detection device；Belong to technical field of rail traffic.
Background technology
With the development of traffic technique, the urban public transport such as train, subway is rapidly developed and is simultaneously achieved big
Area raises speed, and passenger and freight ability significantly improves, meanwhile, because mostly track is opening or semi-enclosed rail, that is, any
People or thing are all likely to enter orbital region, lead to running environment sufficiently complex.When train driver find track on someone or
Train evil spirit, when needing to stop, can not be stopped as automobile in short distance by the foreign body intrusions such as car immediately, generally stop away from
From needing hundreds of meters to several kilometers, rely on artificial detection necessarily infeasible.Therefore, in order to ensure traffic is normal, in order,
It is continued for, need in advance the foreign body intrusion on track to be detected.
The utility model patent of Application No. discloses a kind of railroad track foreign body intrusion inspection of employing image comparison techniques
Survey method and apparatus, foreign body intrusion detected using image comparative approach, can detect including foreign body intrusions such as people, animal, objects,
As long as foreign body intrusion enters on the track of working range, the real-time imaging captured by camera device will be changed, by comparing
Real-time imaging and sample image are so that it may find the appearance of foreign body intrusion.But, there is certain limitation in this kind of image comparative approach
Property, especially when light is not good, resolution is very poor, leads to result of detection adversely effected, and accuracy and reliability need to be carried
High.
Utility model content
For solving the deficiencies in the prior art, the purpose of this utility model is to provide a kind of visible ray to be combined with infrared light
Track foreign body intrusion detection device, to improve reliability and the accuracy of testing result.
In order to realize above-mentioned target, this utility model adopts the following technical scheme that:
The track foreign body intrusion detection device that visible ray is combined with infrared light, including video acquisition assembly, DVR,
Video processing service device and terminal server, described video acquisition assembly includes being divided into the visible image capturing of train head both sides
Machine and thermal camera, described DVR receives the image information from video acquisition assembly and stores, at described video
Reason server carries out fusion calculation to image information, and result of calculation is fed back to terminal server, described terminal server pair
Result of detection is shown.
Preferably, aforementioned visible light camera is all connected with DVR by video line with thermal camera.
It is highly preferred that aforementioned terminals server is computer.
More preferably, the communication interface of aforementioned computer is standard network interface rj45, passes through network with video processing service device
Communication realized by line.
It is further preferred that aforementioned visible light camera and thermal camera be installed in the windshield of train head and
Install near top, so ensure that and collect remote and clearly video image.
Yet further, aforementioned terminals server is provided with alarm, sends in time when foreign body intrusion information is detected
Alarm.
Of the present utility model have the beneficial effect that foreign body intrusion detection device of the present utility model by visible ray and red
Outer light be combined improve resolution it may be assumed that as light and visibility very good using based on visible light camera, infrared photography
Pattern supplemented by machine, thermal camera does video source modeling and processes；When having haze (overhead scene) or luminance shortage, (tunnel is low
Illumination scene) when, automatically switch to based on thermal camera, supplemented by visible ray it is seen that light does video source modeling processes so that this spy
Survey device recognition accuracy in extreme circumstances to greatly improve.
Brief description
Fig. 1 is the structural representation of a preferred embodiment of foreign body intrusion detection device of the present utility model.
The implication of in figure reference: 1, visible light camera, 2, thermal camera, 3, DVR, 4, at video
Reason server, 5, terminal server, 6, grid line, 7, video line.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, this utility model is made with specific introduction.
In description of the present utility model it is to be understood that term " " center ", " longitudinal ", " horizontal ", " on ", D score,
The orientation of instruction such as "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outward " or position relationship are
Based on orientation shown in the drawings or position relationship, it is for only for ease of description this utility model and simplifies description, rather than instruction
Or the hint device of indication or element must have specific orientation, with specific azimuth configuration and operation, be not therefore understood that
It is to restriction of the present utility model.Additionally, term " first ", " second " be only used for describe purpose, and it is not intended that instruction or
Hint relative importance.
Referring to Fig. 1, the track foreign body intrusion detection device that visible ray of the present utility model is combined with infrared light, including video
Acquisition component, DVR 3, video processing service device 4 and terminal server 5.
Wherein, video acquisition assembly includes visible light camera 1 and the thermal camera 2 being divided into train head both sides,
Two video cameras pass through the internal secondary development bag carrying and rapidly gather video information, and this two video cameras are all by regarding
Frequency line 7 is connected with DVR 3, and so, DVR 3 receives the image information from video acquisition assembly and deposits
Storage, then video processing service device 4 is transferred image information and is carried out fusion calculation to image information, and result of calculation is fed back to end
End server 5, terminal server 5 shows to result of detection.Terminal server 5 can be standard network interface using communication interface
The computer of rj45, passes through grid line 6 with video processing service device 4 and realizes communication, and, terminal server 5 is preferably provided with
Alarm, sends alarm prompt in time when foreign body intrusion information is detected.
It should be noted that visible light camera 1 and thermal camera 2 are installed in the windshield of train head and lean on
Nearly top is installed, and can either see the situation on distant place ground；It is also contemplated that seeing remote in the case of adaptation track corner as far as possible.
Additionally, the process that video processing service device 4 of the present utility model carries out fusion calculation to image information can be using existing
There is known method in technology, such as weighted mean method, his converter technique, PCA, laplacian pyramid method, small echo
Alternative approach etc., but these algorithms have some drawbacks, such as: big, picture quality affected by noise is low, and therefore, this practicality is newly
It is also proposed a kind of new algorithm in type, but this is not emphasis of the present utility model, is briefly illustrated below: this algorithm
Carry out multi-resolution decomposition based on profile wave convert method to source images, then carry out multidirectional in each resolution figure layer dividing
Solution；Then carry out color notation conversion space, go to l α β from rgb, in conjunction with the characteristic of the triple channel independence of l α β color space, to can
See that light image is merged with infrared image, specific as follows:
1), source coloured image is mapped to l α β space, obtains l, α, β component, then it is mapped to his space obtains i and divide
Amount；
2), i component is carried out with wbct conversion and obtains low frequency and the coefficient of each high-frequency sub-band Represent
The high-frequency sub-band in a image jth layer the 1st direction；
3), equally wbct conversion is carried out to infrared image, obtain low frequency and each high-frequency sub-band coefficient Represent the high-frequency sub-band in b image jth layer the 1st direction；
4), rule for the treatment of is taken to integrate using modulus value high frequency coefficient, that is,
5), to low frequency coefficient it is considered to the feature of infrared image and visible ray, with a measure coefficient:WhereinFor the average of regional area,For the average of whole infrared image,Standard deviation for region；ωir(i, j) and ωvi(i, j) represents infrared
The image and visible ray contribution degree in fusion image, blending algorithm is:
6) now carry out the gray value i ' after wbct inverse transformation is merged after, coefficient is merged；
7), because the dynamic range of the l component in l α β space is different from the dynamic range of gray level image, so can not be direct
Replace l component with the i ' after merging, and i ' will be carried out with the adjustment of dynamic range, be i.e. the remapping of gray scale:Wherein, lremapRepresent the brightness after remapping, ave (i ') represents average, σ represents standard deviation, conversion
Two width images before and after mapping can be made afterwards to have identical meansigma methodss and standard deviation, the scope of intensity profile is consistent；
8), lremap, α, β component inversion change to rgb space, the image after being merged.
Through inspection, the blending algorithm after this optimization can reduce noise to be affected on it, improves robustness.
To sum up, foreign body intrusion detection device of the present utility model improves knowledge by being combined to visible ray and infrared light
Do not spend, as light and visibility very good using based on visible light camera 1, the pattern supplemented by thermal camera 2, infrared photography
Machine 2 does video source modeling and processes；When having haze (overhead scene) or luminance shortage (tunnel low-illumination scene), automatically switch
To based on thermal camera 2, supplemented by visible ray it is seen that light do video source modeling process so that this detection device in extreme circumstances
Recognition accuracy greatly improve.
In description of the present utility model, it should be noted that unless otherwise clearly defined and limited, term " peace
Dress ", " being connected ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or integratedly
Connect；Can be to be mechanically connected or electrically connect；Can be to be joined directly together it is also possible to be indirectly connected to by intermediary,
It can be the connection of two element internals.For the ordinary skill in the art, above-mentioned art can be understood with concrete condition
Concrete meaning in this utility model for the language.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment of the present utility model or example.In this manual, the schematic table to above-mentioned term
State and be not necessarily referring to identical embodiment or example.And, the specific features of description, structure, material or feature can be
Combine in an appropriate manner in any one or more embodiments or example.
Of the present utility model ultimate principle, principal character and advantage have been shown and described above.The technical staff of the industry
It should be appreciated that above-described embodiment in any form limit this utility model, all by the way of equivalent or equivalent transformation
The technical scheme being obtained, all falls within protection domain of the present utility model.
Claims (6)
1. visible ray is combined with infrared light track foreign body intrusion detection device is it is characterised in that include video acquisition assembly, hard
Disk videocorder, video processing service device and terminal server, described video acquisition assembly includes being divided into train head both sides
Visible light camera and thermal camera, described DVR receives the image information from video acquisition assembly and stores,
Described video processing service device carries out fusion calculation to image information, and result of calculation is fed back to terminal server, described end
End server shows to result of detection.
2. visible ray according to claim 1 is combined with infrared light track foreign body intrusion detection device it is characterised in that
Described visible light camera is all connected with DVR by video line with thermal camera.
3. visible ray according to claim 1 is combined with infrared light track foreign body intrusion detection device it is characterised in that
Described terminal server is computer.
4. visible ray according to claim 3 is combined with infrared light track foreign body intrusion detection device it is characterised in that
The communication interface of described computer is standard network interface rj45, realizes communication with video processing service device by grid line.
5. visible ray according to claim 1 is combined with infrared light track foreign body intrusion detection device it is characterised in that
Described visible light camera and thermal camera are installed in the windshield of train head and install near top.
6. visible ray according to claim 1 is combined with infrared light track foreign body intrusion detection device it is characterised in that
Described terminal server is provided with alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620671947.XU CN205890910U (en) | 2016-06-29 | 2016-06-29 | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620671947.XU CN205890910U (en) | 2016-06-29 | 2016-06-29 | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205890910U true CN205890910U (en) | 2017-01-18 |
Family
ID=57769792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620671947.XU Active CN205890910U (en) | 2016-06-29 | 2016-06-29 | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205890910U (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
| CN107643065A (en) * | 2017-08-11 | 2018-01-30 | 广州地铁设计研究院有限公司 | The quick detection and analysis method of limit are invaded in a kind of tunnel |
| CN109784214A (en) * | 2018-12-27 | 2019-05-21 | 武汉理工大学 | A kind of detection device and method of railroad track foreign matter |
| CN116389695A (en) * | 2023-06-06 | 2023-07-04 | 深圳市城市公共安全技术研究院有限公司 | Building site monitoring method and device, building site inspection equipment and storage medium |
-
2016
- 2016-06-29 CN CN201620671947.XU patent/CN205890910U/en active Active
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
| CN107643065A (en) * | 2017-08-11 | 2018-01-30 | 广州地铁设计研究院有限公司 | The quick detection and analysis method of limit are invaded in a kind of tunnel |
| CN109784214A (en) * | 2018-12-27 | 2019-05-21 | 武汉理工大学 | A kind of detection device and method of railroad track foreign matter |
| CN116389695A (en) * | 2023-06-06 | 2023-07-04 | 深圳市城市公共安全技术研究院有限公司 | Building site monitoring method and device, building site inspection equipment and storage medium |
| CN116389695B (en) * | 2023-06-06 | 2023-09-01 | 深圳市城市公共安全技术研究院有限公司 | Building site monitoring method and device, building site inspection equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368706B (en) | Data fusion dynamic vehicle detection method based on millimeter wave radar and machine vision | |
| CN109878552B (en) | Foreign matter monitoring devices between track traffic platform door and train based on machine vision | |
| CN205890910U (en) | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light | |
| CN102175613B (en) | Image-brightness-characteristic-based pan/tilt/zoom (PTZ) video visibility detection method | |
| CN103021177B (en) | Method and system for processing traffic monitoring video image in foggy day | |
| CN106960179B (en) | Rail line Environmental security intelligent monitoring method and device | |
| CN107392103A (en) | The detection method and device of road surface lane line, electronic equipment | |
| CN105225482A (en) | Based on vehicle detecting system and the method for binocular stereo vision | |
| CN105574552A (en) | Vehicle ranging and collision early warning method based on monocular vision | |
| CN104902258A (en) | Multi-scene pedestrian volume counting method and system based on stereoscopic vision and binocular camera | |
| WO2012090200A1 (en) | Calibration device and method for use in a surveillance system for event detection | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN109887276B (en) | Night traffic jam detection method based on fusion of foreground extraction and deep learning | |
| CN112991369A (en) | Method for detecting overall dimension of running vehicle based on binocular vision | |
| WO2023155483A1 (en) | Vehicle type identification method, device, and system | |
| CN106096512A (en) | Utilize the detection device and method that vehicles or pedestrians are identified by depth camera | |
| CN202058221U (en) | Passenger flow statistic device based on binocular vision | |
| CN107862713A (en) | Video camera deflection for poll meeting-place detects method for early warning and module in real time | |
| CN102779412B (en) | Integrated video traffic information detection method and system | |
| CN110020642A (en) | A kind of visibility recognition methods based on vehicle detection | |
| Jiang et al. | Foreign object recognition technology for port transportation channel based on automatic image recognition | |
| CN113609942A (en) | Road intelligent monitoring system based on multi-view and multi-spectral fusion | |
| CN117197779A (en) | Track traffic foreign matter detection method, device and system based on binocular vision | |
| CN113561897B (en) | Method and system for judging ramp parking position of driving test vehicle based on panoramic all-round view | |
| CN115857040A (en) | Dynamic visual detection device and method for foreign matters on locomotive roof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220331 Address after: 211806 No. 111-13, Baihe Road, Pukou Economic Development Zone, Pukou District, Nanjing, Jiangsu Province Patentee after: Nanjing sushengtian Information Technology Co.,Ltd. Address before: 210006 No. 1002, building D1, Chenguang 1865 Creative Park, No. 388 Yingtian Street (No. 1 Zhengxue Road), Qinhuai District, Nanjing, Jiangsu Province Patentee before: NANJING YAXIN TECHNOLOGY GROUP Co.,Ltd. |
|
| TR01 | Transfer of patent right |