Fast road detection from color images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Fast road detection from color images

Résumé

In this paper, we present a method for drivable road detection by extracting its specular intrinsic feature from an image. The resulting detection is then used in a stereo vision-based 3D road parameters extraction algorithm. A substantial representation of the road surface, called axis-calibration, is represented as an angle in log- chromaticity space. This feature provides an invariance to road surface under illuminant conditions with shadow or not. We also add a sky removal function in order to eliminate the negative effects of sky light on axis-calibration result. Then, a confidence interval calculation helps the pixels' classification to speed up the detection processing. At last, the approach is combined with a stereo- vision based method to filter out false detected pixels and to obtain precise 3D road parameters. The experimental results show that the proposed approach can be adapted for real-time ADAS system in various driving conditions.
Fichier principal
Vignette du fichier
paper_10.2_final_submission_opt.pdf (242.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00858217 , version 1 (04-09-2013)

Identifiants

  • HAL Id : hal-00858217 , version 1

Citer

Bihao Wang, Vincent Fremont. Fast road detection from color images. IEEE Intelligent Vehicles Symposium 2013, Jun 2013, Australia. pp.1209-1214. ⟨hal-00858217⟩
165 Consultations
1219 Téléchargements

Partager

Gmail Facebook X LinkedIn More