Understanding Everyday Hands in Action from RGB-D Images

Gregory Rogez 1 James Supancic 2 Deva Ramanan 3
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We analyze functional manipulations of handheld objects, formalizing the problem as one of fine-grained grasp classification. To do so, we make use of a recently developed fine-grained taxonomy of human-object grasps. We introduce a large dataset of 12000 RGB-D images covering 71 everyday grasps in natural interactions. Our dataset is different from past work (typically addressed from a robotics perspective) in terms of its scale, diversity, and combination of RGB and depth data. From a computer-vision perspective , our dataset allows for exploration of contact and force prediction (crucial concepts in functional grasp analysis) from perceptual cues. We present extensive experimental results with state-of-the-art baselines, illustrating the role of segmentation, object context, and 3D-understanding in functional grasp analysis. We demonstrate a near 2X improvement over prior work and a naive deep baseline, while pointing out important directions for improvement.
Type de document :
Communication dans un congrès
ICCV 2015 - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. IEEE, pp.3889-3897, <http://pamitc.org/iccv15/>. <10.1109/ICCV.2015.443>
Liste complète des métadonnées



https://hal.inria.fr/hal-01237011
Contributeur : Gregory Rogez <>
Soumis le : mercredi 2 décembre 2015 - 15:17:58
Dernière modification le : mardi 11 avril 2017 - 13:40:55
Document(s) archivé(s) le : vendredi 28 avril 2017 - 23:22:47

Fichiers

1803.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Gregory Rogez, James Supancic, Deva Ramanan. Understanding Everyday Hands in Action from RGB-D Images. ICCV 2015 - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. IEEE, pp.3889-3897, <http://pamitc.org/iccv15/>. <10.1109/ICCV.2015.443>. <hal-01237011>

Partager

Métriques

Consultations de
la notice

269

Téléchargements du document

212