CN105338304A - Tunnel operation safety incident detection system based on video recognition - Google Patents
Tunnel operation safety incident detection system based on video recognition Download PDFInfo
- Publication number
- CN105338304A CN105338304A CN201410395958.5A CN201410395958A CN105338304A CN 105338304 A CN105338304 A CN 105338304A CN 201410395958 A CN201410395958 A CN 201410395958A CN 105338304 A CN105338304 A CN 105338304A
- Authority
- CN
- China
- Prior art keywords
- module
- tunnel
- automatic identification
- automatic recognition
- identification 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
Landscapes
- Fire-Detection Mechanisms (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a tunnel operation safety incident detection system based on video recognition which is high in recognition accuracy and fast in recognition speed, and can be well applied to the tunnel. The system comprises a safety incident judgment and processing center, a fire disaster incident automatic recognition module, a vehicle target automatic recognition module, a pedestrian target automatic recognition module, an abandoned object target automatic recognition module, a traffic parameter extraction module, a light compensation module and an image speed reduction module, wherein the fire disaster incident automatic recognition module, the vehicle target automatic recognition module, the pedestrian target automatic recognition module, the abandoned object target automatic recognition module, the traffic parameter extraction module, the light compensation module and the image speed reduction module are all electrically connected with the safety incident judgment and processing center; and the fire disaster incident automatic recognition module, the vehicle target automatic recognition module, the pedestrian target automatic recognition module and the abandoned object target automatic recognition module share one high-definition camera.
Description
Technical field
The present invention relates to a kind of detection system, specifically refer to a kind of tunnel security of operation event detection system based on video identification.
Background technology
Video identification technology mainly comprises collection and transmission, the video detection of centre and analyzing and processing three links of rear end of head end video information.The vision signal that video identification needs head end video acquisition camera to provide steady and audible, video signal quality will directly have influence on the effect of video identification.It, by the middle intelligent analysis module embedded, identifies video pictures, detects, analyzes, filtering interfering, do target and Trajectories Toggle to the abnormal conditions in video pictures.Wherein intelligent video analysis module is the algorithm based on artificial intelligence and Pattern recognition principle.Intelligent video recognition system mainly contains following function: (1) can be distinguished the various objects such as people, animal, vehicle and carry out detecting and following the tracks of, and each video camera can be monitored 50 kinds of different targets simultaneously respectively.(2) can be accessed by the multiple detecting devicess such as video camera, gate inhibition, RFID, Intelligent fence, GPS, radar, and carry out analytical integration.(3) can arrange and virtually enclose boundary.(4) level of security is set according to security strategy (in the daytime/night, traffic busy/idle etc.), level of security can be set in specific region or the whole audience, and can creates or change alarm region.(5) when warning automatic linkage jumps out Pan/Tilt/Zoom camera image window, the The Cloud Terrace that system can be adopted to provide, lens control icon are manual or automatically lock target, and send alarm by sound, mail, phone, beeper etc.(6) can jump out interlock monitoring picture with double mouse click object, check object details.(7) impact that the sunlight reflection, sleety weather etc. that effectively can shield the water surface catch aims of systems thing.The functional requirement of single camera scene video intellectual analysis can tackle various light and environmental factor change, comprises due to--the light in shade, weather, region change, and the change that searchlight, reflective and wind etc. cause.(8) intrusion detecting: the invader that can differentiate human body size, and ignore toy and bird.(9) count: a video camera realizes the counting at multiple semi-cylindrical hills and multiple moving direction.(10) queue management: comprehensive statistical graph can be provided to report, understands flow, the stream of people/client's transfer ratio, average turn time etc.(11) abnormal behaviour detection: the abnormal behaviour such as can distinguish the slipping of people, run.(12) to go around detection: time of fire alarming of can presettingly going around.(13) crowded crowd's management: in setting regions, real-time statistics personnel amount, and report to the police according to the crowding threshold values preset.(14) leave over target acquisition: under busy crowded environment, detect in a camera scene and multiplely leave over target, leave over that object is minimum can reach 3% of picture size.(15) theft detection: can under busy crowded environment, detection lost objects.(16) detection of parking violating the regulations: under busy crowded environment, parking offense can be detected.(17) scribble, put up posters and tamper detection.(18) video camera audit function: to video camera different conditions, as disconnection, poor focusing, destroyed, mobile, there is no enough frame speed or the state such as cannot to detect due to weather such as mist, rain and snow to judge.
But video identification technology does not also apply to operation safety monitoring field, tunnel at present, due to the vehicle in tunnel, the speed of service is fast, and light is dark, and the recognition speed of video identification module of the prior art is slow, the low very difficult adaptation tunnel environment of recognition accuracy.
Summary of the invention
The technical problem to be solved in the present invention is, provides a kind of recognition accuracy high, and recognition speed is fast, well can apply to the tunnel security of operation event detection system based on video identification in tunnel.
For solving the problems of the technologies described above, technical scheme provided by the invention is: a kind of tunnel security of operation event detection system based on video identification, and it comprises security incident differentiation and processing center, the automatic identification module of event of fire, the automatic identification module of vehicle target, the automatic identification module of pedestrian target, sheds thing Motion parameters module, traffic parameter extraction module, light compensation module and image slowdown module; The automatic identification module of described event of fire, the automatic identification module of vehicle target, the automatic identification module of pedestrian target, shed thing Motion parameters module, traffic parameter extraction module, light compensation module and image slowdown module and be all electrically connected with processing center with security incident differentiation; Described light compensation module is for compensating the dim environment in tunnel; Described image slowdown module catches the target of running at high speed; The automatic identification module of described event of fire, the automatic identification module of vehicle target, the automatic identification module of pedestrian target and shed thing Motion parameters module share a high-definition camera.
As improvement, it also comprises smoke detector, and described smoke detector is electrically connected with processing center with security incident differentiation, for detecting the smokescope in tunnel.
As improvement, it also comprises heat detector, and described heat detector is electrically connected with processing center with security incident differentiation, for detecting the temperature in tunnel.
After adopting said structure, tool of the present invention has the following advantages: it comprises security incident differentiation and processing center, the automatic identification module of event of fire, the automatic identification module of vehicle target, the automatic identification module of pedestrian target, sheds thing Motion parameters module, traffic parameter extraction module, light compensation module and image slowdown module; Use Digital Image Processing and mode identification technology, by fault car in tunnel monitoring/parking offense event, pedestrian's event, shed the detection method of formal matter part, event of fire, realize the automatic detection of tunnel safety event, automatically record and automatic alarm.
It also comprises smoke detector and heat detector for detecting smokescope in tunnel and temperature in addition, and further auxiliary system carries out event of fire differentiation, improves differentiation rate.
In sum, the invention provides a kind of recognition accuracy high, recognition speed is fast, well can apply to the tunnel security of operation event detection system based on video identification in tunnel.
Accompanying drawing explanation
Fig. 1 is the structural representation based on the tunnel security of operation event detection system of video identification in the present invention.
As shown in the figure: 1, security incident differentiation and processing center, 2, the automatic identification module of event of fire, 3, the automatic identification module of vehicle target, 4, the automatic identification module of pedestrian target, 5, shed thing Motion parameters module, 6, traffic parameter extraction module, 7, smoke detector, 8, heat detector, 9, light compensation module, 10, image slowdown module.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
By reference to the accompanying drawings 1, based on a tunnel security of operation event detection system for video identification, it comprises security incident differentiation and processing center 1, the automatic identification module of event of fire 2, the automatic identification module of vehicle target 3, the automatic identification module 4 of pedestrian target, sheds thing Motion parameters module 5, traffic parameter extraction module 6, light compensation module 9 and image slowdown module 10; The automatic identification module of described event of fire 2, the automatic identification module of vehicle target 3, the automatic identification module 4 of pedestrian target, shed thing Motion parameters module 5, traffic parameter extraction module 6, light compensation module 9 and image slowdown module 10 and be all electrically connected with processing center 1 with security incident differentiation; Described light compensation module 9 is for compensating the dim environment in tunnel; Described image slowdown module 10 is with catching the target of running at high speed; The automatic identification module of described event of fire 2, the automatic identification module of vehicle target 3, the automatic identification module 4 of pedestrian target and shed thing Motion parameters module 5 and share a high-definition camera.
As improvement, it also comprises smoke detector 7, and described smoke detector 7 is electrically connected with processing center 1 with security incident differentiation, for detecting the smokescope in tunnel.
As improvement, it also comprises heat detector 8, and described heat detector 8 is electrically connected with processing center 1 with security incident differentiation, for detecting the temperature in tunnel.
It should be noted that, the automatic identification module of above-mentioned event of fire 2, the automatic identification module of vehicle target 3, the automatic identification module 4 of pedestrian target, shed in thing Motion parameters module 5, traffic parameter extraction module 6 prior art the module all having ripe standalone feature, the parameter that wherein said traffic parameter extraction module 6 extracts is car speed, tunnel occupation rate and tunnel traffic three parameters.
Be described the present invention and execution mode thereof above, this description does not have restricted, and shown in accompanying drawing is also one of embodiments of the present invention, and actual structure is not limited thereto.If generally speaking those of ordinary skill in the art enlightens by it, when not departing from the invention aim, designing the frame mode similar to this technical scheme and embodiment without creationary, all should protection scope of the present invention be belonged to.
Claims (3)
1. based on a tunnel security of operation event detection system for video identification, it is characterized in that: it comprises security incident differentiation and processing center (1), the automatic identification module of event of fire (2), the automatic identification module of vehicle target (3), the automatic identification module of pedestrian target (4), sheds thing Motion parameters module (5), traffic parameter extraction module (6), light compensation module (9) and image slowdown module (10); The automatic identification module of described event of fire (2), the automatic identification module of vehicle target (3), the automatic identification module of pedestrian target (4), shed thing Motion parameters module (5), traffic parameter extraction module (6), light compensation module (9) and image slowdown module (10) and be all electrically connected with processing center (1) with security incident differentiation; Described light compensation module (9) is for compensating the dim environment in tunnel; Described image slowdown module (10) is with catching the target of running at high speed; The automatic identification module of described event of fire (2), the automatic identification module of vehicle target (3), the automatic identification module of pedestrian target (4) and shed thing Motion parameters module (5) share a high-definition camera.
2. the tunnel security of operation event detection system based on video identification according to claim 1, it is characterized in that: it also comprises smoke detector (7), described smoke detector (7) is electrically connected with processing center (1) with security incident differentiation, for detecting the smokescope in tunnel.
3. the tunnel security of operation event detection system based on video identification according to claim 1, it is characterized in that: it also comprises heat detector (8), described heat detector (8) is electrically connected with processing center (1) with security incident differentiation, for detecting the temperature in tunnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410395958.5A CN105338304A (en) | 2014-08-13 | 2014-08-13 | Tunnel operation safety incident detection system based on video recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410395958.5A CN105338304A (en) | 2014-08-13 | 2014-08-13 | Tunnel operation safety incident detection system based on video recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105338304A true CN105338304A (en) | 2016-02-17 |
Family
ID=55288549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410395958.5A Pending CN105338304A (en) | 2014-08-13 | 2014-08-13 | Tunnel operation safety incident detection system based on video recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105338304A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157522A (en) * | 2016-08-31 | 2016-11-23 | 招商局重庆交通科研设计院有限公司 | Vcehicular tunnel vehicle spontaneous combustion early warning system and method based on hotness imaging |
| CN107067725A (en) * | 2017-05-26 | 2017-08-18 | 安徽皖通科技股份有限公司 | Tunnel road conditions dynamic early-warning and linkage method of disposal |
| CN110543908A (en) * | 2019-08-30 | 2019-12-06 | 北京航空航天大学 | control chart pattern recognition method based on dynamic observation window |
| CN110830767A (en) * | 2019-10-31 | 2020-02-21 | 深圳大学 | Active intelligent behavior analysis alarm device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
| CN101059897A (en) * | 2006-04-21 | 2007-10-24 | 同济大学 | A novel tunnel fire pre-warning system and control method |
| CN202904334U (en) * | 2012-10-16 | 2013-04-24 | 丽水市海威光控科技有限公司 | Highway tunnel remote monitoring system |
| CN203204835U (en) * | 2013-04-22 | 2013-09-18 | 百年金海安防科技有限公司 | System for detecting and analyzing events of falling objects and collision of vehicles |
| CN103400113A (en) * | 2013-07-10 | 2013-11-20 | 重庆大学 | Method for detecting pedestrian on expressway or in tunnel based on image processing |
-
2014
- 2014-08-13 CN CN201410395958.5A patent/CN105338304A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059897A (en) * | 2006-04-21 | 2007-10-24 | 同济大学 | A novel tunnel fire pre-warning system and control method |
| CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
| CN202904334U (en) * | 2012-10-16 | 2013-04-24 | 丽水市海威光控科技有限公司 | Highway tunnel remote monitoring system |
| CN203204835U (en) * | 2013-04-22 | 2013-09-18 | 百年金海安防科技有限公司 | System for detecting and analyzing events of falling objects and collision of vehicles |
| CN103400113A (en) * | 2013-07-10 | 2013-11-20 | 重庆大学 | Method for detecting pedestrian on expressway or in tunnel based on image processing |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157522A (en) * | 2016-08-31 | 2016-11-23 | 招商局重庆交通科研设计院有限公司 | Vcehicular tunnel vehicle spontaneous combustion early warning system and method based on hotness imaging |
| CN107067725A (en) * | 2017-05-26 | 2017-08-18 | 安徽皖通科技股份有限公司 | Tunnel road conditions dynamic early-warning and linkage method of disposal |
| CN110543908A (en) * | 2019-08-30 | 2019-12-06 | 北京航空航天大学 | control chart pattern recognition method based on dynamic observation window |
| CN110543908B (en) * | 2019-08-30 | 2022-03-25 | 北京航空航天大学 | Control chart pattern recognition method based on dynamic observation window |
| CN110830767A (en) * | 2019-10-31 | 2020-02-21 | 深圳大学 | Active intelligent behavior analysis alarm device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101095528B1 (en) | An outomatic sensing system for traffic accident and method thereof | |
| CN201766663U (en) | Residential property monitoring system | |
| CN101835032B (en) | Multi-camera crowd-gathered message statistic device and method | |
| US20100013656A1 (en) | Area monitoring using prototypical tracks | |
| CN204856896U (en) | Radar traffic incident automatic check out system | |
| CN101898567B (en) | Railway foreign body limit-intruding monitoring system based on intelligent video | |
| CN208335464U (en) | A kind of traffic events monitoring device based on video and radar | |
| CN103456024B (en) | A kind of moving target gets over line determination methods | |
| CN108648456A (en) | A kind of traffic events monitoring device and method based on video and radar | |
| CN101123721A (en) | An intelligent video monitoring system and its monitoring method | |
| CN105141885A (en) | Method for video monitoring and device | |
| CN108734966A (en) | A kind of traffic video comprehensive analysis cloud platform system | |
| CN102665071A (en) | Intelligent processing and search method for social security video monitoring images | |
| CN102945603A (en) | Method for detecting traffic event and electronic police device | |
| KR20060031832A (en) | A smart visual security system based on real-time behavior analysis and situation cognizance | |
| CN105338304A (en) | Tunnel operation safety incident detection system based on video recognition | |
| CN106355162A (en) | Method for detecting intrusion on basis of video monitoring | |
| CN107590834A (en) | A kind of road traffic accident video detecting method and system | |
| CN103152558B (en) | Based on the intrusion detection method of scene Recognition | |
| CN109859487A (en) | One kind being based on the illegal monitoring method of AI high point panorama intelligent transportation and system | |
| CN113593161A (en) | Perimeter intrusion detection method | |
| CN101848369B (en) | Method for detecting video stop event based on self-adapting double-background model | |
| CN105389991B (en) | A kind of adaptive Jaywalking snapshot method | |
| CN103489202A (en) | Intrusion detection method based on videos | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| DD01 | Delivery of document by public notice |
Addressee: NANNING FENGWEI SCIENCE & TECHNOLOGY CO., LTD. Document name: Notification of Publication of the Application for Invention |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| DD01 | Delivery of document by public notice |
Addressee: NANNING FENGWEI SCIENCE & TECHNOLOGY CO., LTD. Document name: Notification of Patent Invention Entering into Substantive Examination Stage |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: NANNING FENGWEI SCIENCE & TECHNOLOGY CO., LTD. Document name: Notification that Application Deemed to be Withdrawn |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160217 |