CN105447479A - Traffic state video monitoring method for high-speed bayonet road - Google Patents
Traffic state video monitoring method for high-speed bayonet road Download PDFInfo
- Publication number
- CN105447479A CN105447479A CN201511003905.5A CN201511003905A CN105447479A CN 105447479 A CN105447479 A CN 105447479A CN 201511003905 A CN201511003905 A CN 201511003905A CN 105447479 A CN105447479 A CN 105447479A
- Authority
- CN
- China
- Prior art keywords
- video monitoring
- image
- video
- information
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
Abstract
The invention relates to a traffic state video monitoring method for a high-speed bayonet road. The traffic state video monitoring method comprises the following steps: acquiring video monitoring images, and coding the acquired video monitoring images; directly uploading the coded video monitoring images to a video management system via an Ethernet switch for recording of image signals, and uploading the picture signals to a video monitoring system for decoding and playback; building a time-space domain background model based on a Gaussian mixture model for a video monitoring image in a first cycle time; calculating the similarity between a current image and the time-space domain background model, extracting foregrounded information according to the similarity, and extracting the feature information of each connected region in the foregrounded information; and carrying out vehicle identification according to distance and area information of the connected region, and judging the crowding state of a monitored road section. The video monitoring method is simple and convenient to operate, and can be used for analysis and detection of traffic video, so as to improve the flexibility and the completeness of remote video monitoring.
Description
Technical field
The present invention relates to urban transportation technical field, be specifically related to a kind of high speed bayonet socket road traffic state video frequency monitoring method.
Background technology
Subway is a kind of convenient, convenient, free of contamination vehicles, is the important component part of big city capital construction.Along with the development of track traffic of saving trouble, track traffic plays a part more and more important in the life of people, and due to convenient, economy and the colleges and universities of track traffic, subway has become the primary selection of people's trip.Rush hour morning and evening, section, was the time period that metro accidents takes place frequently, once accident occurs, if fail to understand accident occurrence cause in time, metro operation unit cannot make in time solution targetedly.
Present stage, video system was monitored mainly through analog signalling, and this set expandability is poor, easily breaks down, and was difficult to carry out further application and development, once accident occurs, cannot realize United Dispatching.Digitized video monitoring system can realize remote monitoring, and being convenient to metro operation unit has situation and understand more timely, and process facilitates in time, have completeness, dirigibility, the harmony of data processing, and equipment easily maintains.And current video detection system not only accuracy of detection is high and still rest in the aspect of DETECTION OF TRAFFIC PARAMETERS, to differentiate that road traffic state also needs to carry out analyzing and processing to traffic parameter further, do not give full play of the due performance of video monitoring.
Summary of the invention
The object of the present invention is to provide a kind of high speed bayonet socket road traffic state video frequency monitoring method, the method can carry out analysis and resolution to traffic video, to improve dirigibility and the completeness of Video Remote monitoring.
For achieving the above object, present invention employs following technical scheme:
A kind of high speed bayonet socket road traffic state video frequency monitoring method, comprises the following steps:
(1) obtain video monitoring image, by video acquisition system, Real-time Collection is carried out to image in the rail traffic station Room, simultaneously and the video image taking the photograph collection is encoded;
(2) video image after coding is carried out record through the direct uploaded videos management system of Ethernet switch to picture signal, and then import video monitoring system into, carry out decoding playback;
(3) for the video monitoring image in time period 1, the time-space domain background model of video monitoring image is set up based on mixed Gauss model;
(4) calculate the similarity of present image and time-space domain background model, extract foreground information based on similarity, extract the characteristic information of each connected region in foreground information;
(5) utilize the Distance geometry area information of connected domain to carry out vehicle identification, if there is car, preserve vehicle characteristic information, and the background information removing information of vehicles upgrades background model; If without car, upgrade background model with present image, and export unimpeded, and to the signal counting how many times that blocks up exported, judge whether time second round terminates, if terminate, calculate the number of times exporting and block up, if export the number of times that blocks up to be greater than predetermined value, then prompting monitoring section is in congestion status;
(6) calculate the average velocity of different target within time period 1, so in computed image the mean value of all target average velocity as the speed parameter of present road;
(7) judge road traffic state according to the threshold speed set, speed parameter is less than the output of described threshold value and blocks up, and is more than or equal to described threshold value and exports unimpeded.
As shown from the above technical solution, high speed bayonet socket road traffic state video frequency monitoring method of the present invention, adopt video acquisition system, system for managing video and video monitoring system centralized control, fully realize resource sharing, adopt the transmission of network digitalization signal optical cable, make telemanagement, easy to maintenance, the method increase work efficiency and the resource utilization of whole system, enhance its applicability in mass transportation road conditions video surveillance applications.
Accompanying drawing explanation
Fig. 1 is method flow diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described:
As shown in Figure 1, the high speed bayonet socket road traffic state video frequency monitoring method of the present embodiment, comprises the following steps:
S1: obtain video monitoring image, by video acquisition system, Real-time Collection is carried out to image in the rail traffic station Room, simultaneously and the video image taking the photograph collection is encoded;
S2: the video image after coding is carried out record through the direct uploaded videos management system of Ethernet switch to picture signal, and then imports video monitoring system into, carry out decoding playback;
S3: for the video monitoring image in time period 1, sets up the time-space domain background model of video monitoring image based on mixed Gauss model;
S4: the similarity calculating present image and time-space domain background model, extracts foreground information based on similarity, extracts the characteristic information of each connected region in foreground information;
S5: utilize the Distance geometry area information of connected domain to carry out vehicle identification, if there is car, preserves vehicle characteristic information, and the background information removing information of vehicles upgrades background model; If without car, upgrade background model with present image, and export unimpeded, and to the signal counting how many times that blocks up exported, judge whether time second round terminates, if terminate, calculate the number of times exporting and block up, if export the number of times that blocks up to be greater than predetermined value, then prompting monitoring section is in congestion status;
S6: calculate the average velocity of different target within time period 1, so in computed image the mean value of all target average velocity as the speed parameter of present road;
S7: the threshold speed according to setting judges road traffic state, speed parameter is less than the output of described threshold value and blocks up, and is more than or equal to described threshold value and exports unimpeded.
Above-described embodiment is only be described the preferred embodiment of the present invention; not scope of the present invention is limited; under not departing from the present invention and designing the prerequisite of spirit; the various distortion that those of ordinary skill in the art make technical scheme of the present invention and improvement, all should fall in protection domain that claims of the present invention determines.
Claims (1)
1. a high speed bayonet socket road traffic state video frequency monitoring method, is characterized in that, comprise the following steps:
(1) obtain video monitoring image, by video acquisition system, Real-time Collection is carried out to image in the rail traffic station Room, simultaneously and the video image taking the photograph collection is encoded;
(2) video image after coding is carried out record through the direct uploaded videos management system of Ethernet switch to picture signal, and then import video monitoring system into, carry out decoding playback;
(3) for the video monitoring image in time period 1, the time-space domain background model of video monitoring image is set up based on mixed Gauss model;
(4) calculate the similarity of present image and time-space domain background model, extract foreground information based on similarity, extract the characteristic information of each connected region in foreground information;
(5) utilize the Distance geometry area information of connected domain to carry out vehicle identification, if there is car, preserve vehicle characteristic information, and the background information removing information of vehicles upgrades background model; If without car, upgrade background model with present image, and export unimpeded, and to the signal counting how many times that blocks up exported, judge whether time second round terminates, if terminate, calculate the number of times exporting and block up, if export the number of times that blocks up to be greater than predetermined value, then prompting monitoring section is in congestion status;
(6) calculate the average velocity of different target within time period 1, so in computed image the mean value of all target average velocity as the speed parameter of present road;
(7) judge road traffic state according to the threshold speed set, speed parameter is less than the output of described threshold value and blocks up, and is more than or equal to described threshold value and exports unimpeded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511003905.5A CN105447479A (en) | 2015-12-29 | 2015-12-29 | Traffic state video monitoring method for high-speed bayonet road |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511003905.5A CN105447479A (en) | 2015-12-29 | 2015-12-29 | Traffic state video monitoring method for high-speed bayonet road |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105447479A true CN105447479A (en) | 2016-03-30 |
Family
ID=55557639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511003905.5A Pending CN105447479A (en) | 2015-12-29 | 2015-12-29 | Traffic state video monitoring method for high-speed bayonet road |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447479A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106571037A (en) * | 2016-11-15 | 2017-04-19 | 同济大学 | Station detection technology-based expressway real-time road condition monitoring method |
| CN106652448A (en) * | 2016-12-13 | 2017-05-10 | 山姆帮你（天津）信息科技有限公司 | Road traffic state monitoring system on basis of video processing technologies |
| CN109509344A (en) * | 2017-09-14 | 2019-03-22 | 保定维特瑞光电能源科技有限公司 | A kind of road traffic state video monitoring method |
| CN112614338A (en) * | 2020-12-04 | 2021-04-06 | 程东 | Traffic jam prediction control system based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101562727A (en) * | 2008-04-15 | 2009-10-21 | 上海交技发展股份有限公司 | Track traffic video monitoring network management system |
| CN201429904Y (en) * | 2009-06-29 | 2010-03-24 | 长安大学 | Statistical system of traffic flow |
| CN102542805A (en) * | 2012-03-08 | 2012-07-04 | 南京理工大学常熟研究院有限公司 | Device for judging traffic jam based on videos |
-
2015
- 2015-12-29 CN CN201511003905.5A patent/CN105447479A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101562727A (en) * | 2008-04-15 | 2009-10-21 | 上海交技发展股份有限公司 | Track traffic video monitoring network management system |
| CN201429904Y (en) * | 2009-06-29 | 2010-03-24 | 长安大学 | Statistical system of traffic flow |
| CN102542805A (en) * | 2012-03-08 | 2012-07-04 | 南京理工大学常熟研究院有限公司 | Device for judging traffic jam based on videos |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106571037A (en) * | 2016-11-15 | 2017-04-19 | 同济大学 | Station detection technology-based expressway real-time road condition monitoring method |
| CN106652448A (en) * | 2016-12-13 | 2017-05-10 | 山姆帮你（天津）信息科技有限公司 | Road traffic state monitoring system on basis of video processing technologies |
| CN109509344A (en) * | 2017-09-14 | 2019-03-22 | 保定维特瑞光电能源科技有限公司 | A kind of road traffic state video monitoring method |
| CN112614338A (en) * | 2020-12-04 | 2021-04-06 | 程东 | Traffic jam prediction control system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447479A (en) | Traffic state video monitoring method for high-speed bayonet road | |
| CN104902227B (en) | A kind of substation safety cap wear condition video monitoring system | |
| CN106251578A (en) | Artificial abortion's early warning analysis method and system based on probe | |
| CN104464295B (en) | A kind of overhead Entrance ramp intelligence restricted driving method based on video | |
| CN104299426B (en) | A kind of traffic signal control system and method based on to pedestrian detection counting statistics | |
| CN101835034B (en) | Crowd characteristic counting system | |
| CN104680794A (en) | Vehicle-mounted monitoring terminal as well as bus lane monitoring method and system based on terminal | |
| CN106485927A (en) | A kind of intelligent transportation violation information harvester and acquisition method | |
| CN104021605A (en) | Real-time statistics system and method for public transport passenger flow | |
| CN205232359U (en) | Electronic equipment is estimated to flow of people | |
| CN104200667A (en) | Traffic jam grade detection method based on cellphone signal data | |
| CN205665896U (en) | Intersection signal lamp state recognition device | |
| CN103287464A (en) | Intelligent video surveillance system at railway crossing and implement method of system | |
| CN105551267B (en) | A kind of method that traffic signaling equipment is controlled by vehicle flowrate | |
| CN108012117A (en) | A kind of city based on background modeling is set up a stall detection method | |
| CN102493845A (en) | Monitoring and prewarning system for urban rail transit operating tunnel based on GIS (Geographic Information System) | |
| CN202662162U (en) | Dynamic vehicle license plate recognition and management system | |
| CN202003508U (en) | Bus lane illegal vehicle intruding detection equipment | |
| CN102324018A (en) | Pedestrian safety state recognition method and system of comprehensive transportation interchange service network | |
| CN105632171A (en) | Traffic road condition video monitoring method | |
| CN201689549U (en) | High-definition dynamic track tracking electronic policeman system | |
| CN105551268A (en) | System for controlling traffic signal controller through traffic flow | |
| CN204087500U (en) | A kind of based on the traffic signal control system to pedestrian detection counting statistics | |
| CN210666820U (en) | Pedestrian abnormal behavior detection system based on DSP edge calculation | |
| CN210865032U (en) | Urban waterlogging monitoring and early warning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160330 |
|
| RJ01 | Rejection of invention patent application after publication |