Trains of keypoints for 3d object recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Trains of keypoints for 3d object recognition

Résumé

This paper presents a 3D object recognition method that exploits the spatio-temporal coherence of image sequences to capture the object most relevant features. We start from an image sequence that describes the object's visual appearance from different view points. We extract local features (SIFT) and track them over the sequence. The tracked interest points form trains of features that are used to build a vocabulary for the object. Training images are represented with respect to that vocabulary and an SVM classier is trained to recognize the object. We present very promising results on a dataset of 11 objects. Tests are performed under varying illumination, scale, and scene clutter.
Fichier principal
Vignette du fichier
icpr06.pdf (240.22 Ko) Télécharger le fichier
Vignette du fichier
icpr.jpg (176.57 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

inria-00306707 , version 1 (03-04-2009)

Identifiants

  • HAL Id : inria-00306707 , version 1

Citer

Élise Arnaud, Elisabetta Delponte, Francesca Odone, Alessandro Verri. Trains of keypoints for 3d object recognition. International Conference on Pattern Recognition, 2006, Honk Kong, Hong Kong SAR China. ⟨inria-00306707⟩
212 Consultations
819 Téléchargements

Partager

Gmail Facebook X LinkedIn More