This paper presents a real-time video-based automated traffic analysis system that can detect incidents such as slowdowns, traffic jams and stopped vehicles. Traffic speed and density are estimated and serve to detect incidents. Motion detection is performed using a system of estimating the background image and subtracting the current image of the input. Kalman filtering is used to track moving objects.

  • Availability:
  • Supplemental Notes:
    • Publication Date: 1998 Published By: Canadian Information Processing Society, Toronto ON
  • Corporate Authors:



    University of Hong Kong

    Department of Electrical and Electronic Engineering
    Pok Fu Lam Road
    ,   Hong Kong 
  • Authors:
    • Bourqui, P
  • Publication Date: 1998


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00777292
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Files: PATH
  • Created Date: Nov 17 1999 12:00AM