GUAN, Li; FRANCO, Jean-Sébastien; POLLEFEYS, Marc

doi:10.1007/s11263-010-0341-y

Métadonnées

Licence d’utilisation du document

GUAN, Li
University of North Carolina [Chapel Hill] [UNC]

FRANCO, Jean-Sébastien
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Visualization and manipulation of complex data on wireless mobile devices [IPARLA ]
Interpretation and Modelling of Images and Videos [PERCEPTION]

POLLEFEYS, Marc
University of North Carolina [Chapel Hill] [UNC]
Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] [ETH Zürich]

Langue

Article de revue

Ce document a été publié dans

International Journal of Computer Vision. 2010-12, vol. 90, n° 3, p. 283-303

Springer Verlag

Résumé en anglais

In this paper, we present an algorithm to probabilistically estimate object shapes in a 3D dynamic scene using their silhouette information derived from multiple geometrically calibrated video camcorders. The scene is represented by a 3D volume. Every object in the scene is associated with a distinctive label to represent its existence at every voxel location. The label links together automatically-learned view-specific appearance models of the respective object, so as to avoid the photometric calibration of the cameras. Generative probabilistic sensor models can be derived by analyzing the dependencies between the sensor observations and object labels. Bayesian reasoning is then applied to achieve robust reconstruction against real-world environment challenges, such as lighting variations, changing background etc. Our main contribution is to explicitly model the visual occlusion process and show: (1) static objects (such as trees or lamp posts), as parts of the pre-learned background model, can be automatically recovered as a byproduct of the inference; (2) ambiguities due to inter-occlusion between multiple dynamic objects can be alleviated, and the final reconstruction quality is drastically improved. Several indoor and outdoor real-world datasets are evaluated to verify our framework.< Réduire

Mots clés en anglais

multi-view 3D reconstruction

probability

graphical model

Bayes rule

occluder

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Multi-view occlusion reasoning for probabilistic silhouette-based dynamic scene reconstruction

Langue

Ce document a été publié dans

Résumé en anglais

Mots clés en anglais

URI

DOI

Origine

Unités de recherche