3D models-based semantic labeling of 2D objects - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

3D models-based semantic labeling of 2D objects

Résumé

This paper tackles the issue of still image object categorization. The objective is to infer the semantics of 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D synthetic models in order to identify unknown 2D objects, based on 2D/3D matching techniques. Notably, we use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results carried out on both MPEG-7 and Princeton 3D mesh test sets show recognition rates of up to 89%.
Fichier principal
Vignette du fichier
3D_models-based_sematic_labeling_of_2D_objects.pdf (537.59 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00738224 , version 1 (04-10-2014)

Identifiants

Citer

Raluca Diana Petre, Zaharia Titus. 3D models-based semantic labeling of 2D objects. International Conference on Digital Image Computing: Techniques and Applications (DICTA 2011), Dec 2011, Australia. pp.152-157, ⟨10.1109/DICTA.2011.32⟩. ⟨hal-00738224⟩
75 Consultations
118 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More