Prior-based facade rectification for AR in urban environment - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Prior-based facade rectification for AR in urban environment

Antoine Fond
Marie-Odile Berger
  • Fonction : Auteur
  • PersonId : 773665
  • IdRef : 075878518
Gilles Simon
  • Fonction : Auteur
  • PersonId : 756529
  • IdRef : 059737867

Résumé

We present a method for automatic facade rectification and detection in the Manhattan world scenario. A Bayesian inference approach is proposed to recover the Manhattan directions in camera coordinate system, based on a prior we derived from the analysis of urban datasets. In addition, a SVM-based procedure is used to identify right-angle corners in the rectified images. These corners are clustered in facade regions using a greedy rectangular min-cut technique. Experiments on a standard dataset show that our algorithm performs better or as well as state-of-the-art techniques while being much faster.
Fichier principal
Vignette du fichier
PID3851949.pdf (6.31 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01235842 , version 1 (30-11-2015)

Identifiants

  • HAL Id : hal-01235842 , version 1

Citer

Antoine Fond, Marie-Odile Berger, Gilles Simon. Prior-based facade rectification for AR in urban environment. ISMAR workshop on Urban Augmented Reality, Sep 2015, Fukuoka, Japan. ⟨hal-01235842⟩
201 Consultations
142 Téléchargements

Partager

Gmail Facebook X LinkedIn More