28572 articles – 22062 references  [version française]

hal-00671212, version 1

A Three Resolution Framework for Reliable Road Obstacle Detection using Stereovision

Mathias Perrollaz () 1, Raphaël Labayrade 2, Romain Gallen 34, Didier Aubert 3

Machine Vision and Applications (2007)

Abstract: Many approaches have been proposed for in-vehicle obstacle detection using stereovision. Unfortunately, computation cost is generally a limiting factor for all these methods, especially for systems using large base-lines, as they need to explore a wide range of disparities. Considering this point, we propose a reliable three resolution framework, designed for real time operation, even with high resolution images and a large baseline.

  • 1:  E-MOTION (INRIA Grenoble Rhône-Alpes / LIG Laboratoire d'Informatique de Grenoble)
  • INRIA – Université Joseph Fourier - Grenoble I – Université Pierre-Mendès-France - Grenoble II – CNRS : UMR5217 – Institut polytechnique de Grenoble (Grenoble INP)
  • 2:  Département génie civil et batiment (DGCB)
  • ENTP
  • 3:  Laboratoire Exploitation, Perception, Simulateurs et Simulations (IFSTTAR/LEPSIS)
  • IFSTTAR – Université Paris-Est Marne-la-Vallée (UPEMLV)
  • 4:  Laboratoire sur les Interactions Véhicules-Infrastructure-Conducteurs (IFSTTAR/LIVIC)
  • IFSTTAR
  • Domain : Computer Science/Computer Vision and Pattern Recognition
 
  • hal-00671212, version 1
  • oai:hal.inria.fr:hal-00671212
  • From: 
  • Submitted on: Thursday, 16 February 2012 19:54:25
  • Updated on: Friday, 17 February 2012 10:50:29