Flexible Object Models for Category-Level 3D Object Recognition

Akash Kushal 1, 2 Cordelia Schmid 3 Jean Ponce 4, 5
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
4 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we propose a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models (PSMs) obeying loose local geometric constraints. The PSMs themselves are formed of dense, locally rigid assemblies of image features. Since our model only enforces local geometric consistency, both at the level of model parts and at the level of individual features within the parts, it is robust to viewpoint changes and intra-class variability. The proposed approach has been implemented, and it outperforms the state-of-the-art algorithms for object detection and localization recently compared in [14] on the Pascal 2005 VOC Challenge Cars Test 1 data.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. IEEE Computer Society, pp.1-8, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270174〉. 〈10.1109/CVPR.2007.383149〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548682
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:28:57
Dernière modification le : jeudi 11 janvier 2018 - 06:23:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:32:46

Fichier

akash_cvpr.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Akash Kushal, Cordelia Schmid, Jean Ponce. Flexible Object Models for Category-Level 3D Object Recognition. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. IEEE Computer Society, pp.1-8, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270174〉. 〈10.1109/CVPR.2007.383149〉. 〈inria-00548682〉

Partager

Métriques

Consultations de la notice

547

Téléchargements de fichiers

256