001 A novel system for robust lane detection and tracking教程.pdfVIP

Signal Processing 92 (2012) 319–334 Contents lists available at ScienceDirect Signal Processing journal homepage: /locate/sigpro A novel system for robust lane detection and tracking Yifei Wang , Naim Dahnoun, Alin Achim1 Visual Information Lab, Merchant Venturers School of Engineering, University of Bristol, Merchant Venturers Building, Woodland Road, BS8 1UB Bristol, UK a r t i c l e i n f o a b s t r a c t Article history: This paper presents a lane detection and tracking system based on a novel lane feature Received 20 December 2010 extraction approach and the Gaussian Sum Particle filter (GSPF). The proposed feature Received in revised form extraction approach is based on the fact that by zooming into the vanishing point of the 15 April 2011 lanes, the lane markings/boundaries will only move on the same straight lines they are Accepted 25 July 2011 on. Objects other than the lanes in the frame do not share this property and can be Available online 4 August 2011 ignored during the model parameter estimation. This algorithm is able to iteratively Keywords: refine various traditional feature maps and to operate with curved roads. The tracking Lane feature extraction part of the system is initialised by a deformable template matching algorithm. Three Lane detection typ