Marker-less Real Time 3D Modeling for Virtual Reality

Today, immersive environments mainly use a few 3D positions given by trackers to align the real and virtual worlds. In this paper we present an alternative approach using commodity components to achieve real time marker-less 3D modeling in virtual reality environments. The goal is to compute in real time a 3D shape of the objects and users present in the interaction space without having to equip them with markers. Having full 3D shapes opens new possibilities for full-body interactions and a tight virtual/real world integration. Data acquisition is performed through cameras surrounding the interaction space. A visual hull reconstruction algorithm is parallelized on a PC cluster to compute in real time the 3D shapes of the scene observed. Experimental results using 4 cameras and 20 processors lead to a precise 3D human model built in real time.

Domaines

Vision par ordinateur et reconnaissance de formes [cs.CV]

Fichier principal

Ipt04.pdf (340.49 Ko)

inria-00349066.png (128.73 Ko)

1distributed-demo.png (26.73 Ko)

2cone_inter.png (45.55 Ko)

3exact_final.png (32.72 Ko)

4hand.jpg (128.94 Ko)

Origine : Fichiers produits par l'(les) auteur(s)

Format : Figure, Image

Jean-Sébastien Franco : Connectez-vous pour contacter le contributeur

https://inria.hal.science/inria-00349066

Soumis le : mardi 23 décembre 2008-11:47:43

Dernière modification le : jeudi 4 avril 2024-20:50:16

Archivage à long terme le : jeudi 11 octobre 2012-14:51:11

Dates et versions

inria-00349066 , version 1 (23-12-2008)

Identifiants

HAL Id : inria-00349066 , version 1

Citer

Jérémie Allard, Edmond Boyer, Jean-Sébastien Franco, Clément Ménier, Bruno Raffin. Marker-less Real Time 3D Modeling for Virtual Reality. Immersive Projection Technology, May 2004, Ames, United States. ⟨inria-00349066⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

UGA IMAG CNRS INRIA LIG LIG_SRCPR INRIA2

1199 Consultations

1688 Téléchargements