3D Occlusion Inference from Silhouette Cues - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

3D Occlusion Inference from Silhouette Cues

Abstract

We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views. While well studied and robust in controlled environments, silhouette-based reconstruction of dynamic objects fails in general environments where uncontrolled occlusions are commonplace, due to inherent silhouette corruption by occluders. We show that occluders in the interaction space of dynamic objects can be detected and their 3D shape fully recovered as a byproduct of shape-from-silhouette analysis. We provide a Bayesian sensor fusion formulation to process all occlusion cues occurring in a multi-view sequence. Results show that the shape of static occluders can be robustly recovered from pure dynamic object motion, and that this information can be used for online self-correction and consolidation of dynamic object shape reconstruction.
Fichier principal
Vignette du fichier
cvpr07.pdf (678.29 Ko) Télécharger le fichier
Vignette du fichier
hal-00348980.png (52.25 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image
Loading...

Dates and versions

hal-00348980 , version 1 (22-12-2008)

Identifiers

  • HAL Id : hal-00348980 , version 1

Cite

Li Guan, Jean-Sébastien Franco, Marc Pollefeys. 3D Occlusion Inference from Silhouette Cues. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2007, United States. pp.1-8. ⟨hal-00348980⟩
132 View
429 Download

Share

Gmail Mastodon Facebook X LinkedIn More