In-vehicle obstacles detection and characterization by stereovision
LABAYRADE ; AUBERT
Type de document
COMMUNICATION AVEC ACTES INTERNATIONAL (ACTI)
Langue
anglais
Auteur
LABAYRADE ; AUBERT
Résumé / Abstract
In this paper, the authors propose a fast and robust stereo algorithm to perform in-vehicle obstacles detection and characterization. The stereo algorithm is called the 'v-disparity' algorithm which provides a suitable representation of the geometric content of the road scene. The stereo algorithm principle is described, and then the in-vehicle embedded system is presented. This system can be divided into two main stages. The first one deals with onboard detection (the focus is put on obstacle areas and free road surface extraction), whereas the second one is about obstacles characterization (car/truck discrimination). For each stage, the authors present first the way in which the 'v-disparity' algorithm is used and then report representative experiments on real situations which show that their solution is accurate, reliable and efficient. In particular, both processes are fast, generic, robust to noise and bad conditions, and work even in the case partial occlusions.
