Development of Traffic Obstacles Detection System on Urban Tunnels with Heavy Traffic Flow
It will be further important to take safety measures to prevent accidents in tunnels that may result in tremendous social loss. This paper introduces algorithms to detect traffic obstacles, which automatically and precisely detects an unusual traffic flow at tunnels with heavy traffic flow. The algorithms for automatic detection of an unusual traffic flow detect unusual incidents of traffic flows (e.g., standing or escaping vehicles) based on processing of image data collected from multiple CCTV cameras installed in tunnels. The algorithms however were considered to have some problems in detecting a traffic obstacles in urban tunnels with heavy traffic flow, which are even ordinary vehicles standing at the end of a queue due to traffic jam may be detected as abnormal traffic flow, and the cameras installed at an insufficient height because of tunnel structure may cause invisible vehicles and/or fields of which image data would not be processed.
-
Corporate Authors:
1100 17th Street, NW, 12th Floor
Washington, DC United States 20036 -
Authors:
- Hasegawa, Eiichi
- Onda, Masatoshi
- Kazuno, Yoshihisa
- Kamijo, Shunsuke
-
Conference:
- 12th World Congress on Intelligent Transport Systems
- Location: San Francisco California, United States
- Date: 2005-11-6 to 2005-11-10
- Publication Date: 2005
Language
- English
Media Info
- Media Type: Print
- Features: CD-ROM; Figures; References; Tables;
- Pagination: 12p
- Monograph Title: Proceedings of the 12th World Congress on Intelligent Transport Systems
Subject/Index Terms
- TRT Terms: Algorithms; Closed circuit television; Disaster preparedness; High risk locations; Image processing; Incident detection; Traffic flow; Traffic queuing; Traffic safety; Tunnels
- Subject Areas: Bridges and other structures; Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning;
Filing Info
- Accession Number: 01016060
- Record Type: Publication
- Files: TRIS
- Created Date: Jan 31 2006 9:56AM