CLARK, A HETEROGENEOUS SENSOR FUSION METHOD FOR FINDING LANES AND OBSTACLES

In this paper, the authors describe Combined Likelihood Adding Radar Knowledge (CLARK), a new method that uses information fusion from video and radar forward-looking vehicle mounted sensors to provide land and obstacle detection. The method involves three stages: obstacle detection, lane detection, and simultaneous estimation of both obstacle and lane positions. Experimental results show that CLARK is able to accurately detect lane and obstacle position, even in the presence of significant noise.

  • Supplemental Notes:
    • Publication Date: April 2000
  • Corporate Authors:

    Ruhr-Universitat Bochum. Institut fur Neuroinformatik

    ,    

    University of Michigan, Dearborn

    Department of Electrical and Computer Engineering
    Dearborn, MI  United States  48128

    Robert Bosch GmbH

    ,    

    Fraunhofer-Institut fur Informations- und Datenverarbeitung

    ,    
  • Authors:
    • Beauvais, M
    • Lakshmanan, S
  • Publication Date: 2000

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00799443
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Files: PATH
  • Created Date: Oct 6 2000 12:00AM