Vision-based lane-vehicle detection and tracking

Abstract

This chapter presents a vision-based lane-vehicle detection and tracking system comprising of (i) enhanced lane boundary detection, (ii) linear-parabolic lane region tracking, and (iii) vehicle detection with a proposed possible vehicle region verification. First, a road image is partitioned into sky and road region. Lane boundaries are then extracted from the road region using line model estimation without applying Hough Transform. These detected boundaries are tracked in consecutive video frames with possible edges scanning and linear-parabolic modeling. An approximate lane region is subsequently constructed with the predicted model parameters. By integrating the knowledge of lane region with vehicle detection, vehicle searching region is restricted to the road area so as to detect the shadow underneath a vehicle continuously with less interference to the road environment and non-vehicle structures. A self-adjusting bounding box is used to extract likely vehicle region for further verification. Besides horizontal symmetry detection, a vertical asymmetry measurement is presented to validate the extracted region and to obtain the center of frontal vehicle. Simulation results have revealed good performance of lane-vehicle detection and tracking system. © 2009 American Institute of Physics.