Semantic labeling of 2D objects with 3D models - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Semantic labeling of 2D objects with 3D models

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 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 databases show recognition rates of up to 89.2%.
Fichier principal
Vignette du fichier
Semantic_labeling_of_2D_objects_with_3D_models.pdf (1.86 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00738236 , version 1 (04-10-2014)

Identifiants

  • HAL Id : hal-00738236 , version 1

Citer

Raluca Diana Petre, Zaharia Titus. Semantic labeling of 2D objects with 3D models. 5th IEEE International Conference on Semantic Computing (ICSC 2011), Sep 2011, United States. pp.419-423. ⟨hal-00738236⟩
84 Consultations
32 Téléchargements

Partager

Gmail Facebook X LinkedIn More