A Reliable and Robust Lane Detection System Based on the Parallel Use of Three Algorithms for Driving Safety Assistance

This article proposes the use of a reliable and robust lane detection system, whose aim is to prevent the driver drifting off or running off the road. Research has indicated that up to a third of road traffic incidents occur without any conflict; rather, they are attributed to problems with staying on the roadway. The authors' road following system is based on a frontal on-board monocular camera. In order to get a high degree of reliability and robustness, an original combination of three different algorithms is performed. Low level results from the first two algorithms are used to compute a reliability indicator and to update a high level model through the third algorithm using Kalman filtering. Searching areas of the road sides for the next image are also updated in the third stage. The authors conduct experiments and report results that show the reliability and the robustness of this system. They include various road situations, such as roads with high curvature and multi-lane roads.

  • Availability:
  • Authors:
    • Labayrade, Raphael
    • Douret, Jerome
    • Laneurit, Jean
    • Chapuis, Roland
  • Publication Date: 2006-7

Language

  • English

Media Info

  • Media Type: Print
  • Features: Figures; Photos; References; Tables;
  • Pagination: pp 2092-2100
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 01083174
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Dec 31 2007 7:37AM