Largest Silhouette-Equivalent Volume for 3D Shapes Modeling without Ghost Object

Brice Michoud 1 Saïda Bouakaz 1 Erwan Guillou 1 Hector Briceño 1
1 SAARA - Simulation, Analyse et Animation pour la Réalité Augmentée
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : In this paper, we investigate a practical framework to compute a 3D shape estimation of multiple objects in real-time from silhouettes in multi-view environments. A popular method called Shape From Silhouette (SFS), computes a 3D shape estimation from binary silhouette masks. This method has several limitations: The acquisition space is limited to the intersection of the camera viewing frusta ; SFS methods reconstruct some ghost objects which do not contain real objects, especially when there are multiple real objects in the scene. In this paper we propose two contributions to overcome these limitations. First, using a new formulation of SFS approach, our system reconstructs objects with no constraints on camera placement and their visibility. Second, a new theoretical approach identifies and removes ghost objects. The reconstructed shapes are more accurate than current silhouette-based approaches. Reconstructed parts are guaranteed to contain real objects. Finally, we present a real-time system that captures multiple and complex objects moving through many camera frusta to demonstrate the application and robustness of our method.
Type de document :
Communication dans un congrès
Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications - M2SFA2 2008, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326774
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 14:50:28
Dernière modification le : jeudi 19 avril 2018 - 14:38:06
Document(s) archivé(s) le : lundi 8 octobre 2012 - 14:00:28

Fichier

1569139892.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326774, version 1

Citation

Brice Michoud, Saïda Bouakaz, Erwan Guillou, Hector Briceño. Largest Silhouette-Equivalent Volume for 3D Shapes Modeling without Ghost Object. Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications - M2SFA2 2008, Oct 2008, Marseille, France. 2008. 〈inria-00326774〉

Partager

Métriques

Consultations de la notice

284

Téléchargements de fichiers

133