An Efficient Vehicle Queue and Dissipation Detection Algorithm Based on Spatial-Temporal Markov Random Field

Based on video processing technology, this paper proposes a spatial-temporal Markov random field method. This method can track the position changes of vehicles queue tail and head at intersections in real time, which accurately describes the formation and dissipation of the queue. When the tracking algorithm is used, first the authors decided on an allocation of an initial label. Then through the spatial-temporal Markov random field, they refined and optimized the label's allocation. In the refining process, the algorithm should consider the piece's relation between time and space, and the Markov model can be used, and then a label can be assigned to a piece. Experimental results show the accuracy rate is more than 92% by real-time tracking of tail and head positions under varying weather conditions and levels of illumination.

• Record URL:
  • https://doi.org/10.1061/9780784412442.049
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784412442
• Supplemental Notes:
  • © 2012 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Zhou, Jun
  • Cheng, Lin
• Conference:
  • Twelfth COTA International Conference of Transportation Professionals
  • Location: Beijing , China
  • Date: 2012-8-3 to 2012-8-6
• Publication Date: 2012-8

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References; Tables;
• Pagination: pp 468-474
• Monograph Title: CICTP 2012: Multimodal Transportation Systems—Convenient, Safe, Cost-Effective, Efficient

Subject/Index Terms

• TRT Terms: Algorithms; Intersections; Markov processes; Queuing theory; Real time data processing; Traffic queuing; Vehicle detectors; Video imaging detectors
• Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; I71: Traffic Theory;

Filing Info

• Accession Number: 01500128
• Record Type: Publication
• ISBN: 9780784412442
• Files: TRIS, ASCE
• Created Date: Nov 26 2013 9:57AM