Detection and Classification of Highway Lanes Using Vehicle Motion Trajectories

This paper presents a vehicle tracking system that produces accurate vehicle motion trajectories which can be used for detecting lane centers and classifying lane types. A predictive trajectory merge-and-split algorithm is used for detecting partial or complete occlusions during vehicle movement, while a Kalman filter is used for vehicle tracking. Techniques for cluster analysis and trajectory representation are described and applied to describe lane geometry and lane categorization. Results from experiments using a pan-tilt-zoom traffic camera monitoring the junction of two intersecting highways indicate the real-time application of the approach.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Authors:
  • Melo, Jose
  • Naftel, Andrew
  • Bernardino, Alexandre
  • Santos-Victor, Jose
• Publication Date: 2006-6

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 188-200
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 7
  • Issue Number: 2
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Detection and identification systems; Detectors; Lane lines; Tracking systems; Traffic lanes; Traffic surveillance; Vehicle trajectories; Video cameras
• Subject Areas: Highways; Operations and Traffic Management; I70: Traffic and Transport;

Filing Info

• Accession Number: 01055858
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: BTRIS, TRIS
• Created Date: Aug 28 2007 10:56AM