A 2D/3D Vision Based Approach Applied to Road Detection in Urban Environments - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

A 2D/3D Vision Based Approach Applied to Road Detection in Urban Environments

Résumé

This paper presents an approach for road detection based on image segmentation. This segmentation is resulted from merging 2D and 3D image processing data from a stereo vision system. The 2D layer returns a matrix containing pixel's clusters based on the Watershed transform. Whereas the 3D layer return labels, that are classified by the V-Disparity technique, to free spaces, obstacles and non-classified area. Thus, a feature's descriptor for each cluster is composed with features from both layers. The road pattern recognition was performed by an artificial neural network, trained to obtain a final result from this feature's descriptor. The proposed work reports real experiments carried out in a challenging urban environment to illustrate the validity and application of this approach.
Fichier principal
Vignette du fichier
root.pdf (289.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00936028 , version 1 (24-01-2014)

Identifiants

  • HAL Id : hal-00936028 , version 1

Citer

Giovani Bernardes Vitor, Danilo Alves de Lima, Alessandro Corrêa Victorino, Janito Vaqueiro Ferreira. A 2D/3D Vision Based Approach Applied to Road Detection in Urban Environments. IEEE Intelligent Vehicles Symposium (IV 2013), Jun 2013, australie, Australia. pp.952-957. ⟨hal-00936028⟩
448 Consultations
912 Téléchargements

Partager

Gmail Facebook X LinkedIn More