Real-time 3D motion capture by monocular vision and virtual rendering

GOMEZ, David; HORAIN, Patrick

doi:10.1007/s00138-017-0861-3

ESTIA INSTITUTE OF TECHNOLOGY

HORAIN, Patrick

Langue

Article de revue

Ce document a été publié dans

Machine Vision and Applications. 2017-11, vol. 28, n° 8, p. 839 - 858

Springer Verlag

Résumé en anglais

Networked 3D virtual environments allow multiple users to interact over the Internet by means of avatars and to get some feeling of a virtual telepresence. However, avatar control may be tedious. 3D sensors for motion capture systems based on 3D sensors have reached the consumer market, but webcams remain more widespread and cheaper. This work aims at animating a user's avatar by real-time motion capture using a personal computer and a plain webcam. In a classical model-based approach, we register a 3D articulated upper-body model onto video sequences and propose a number of heuristics to accelerate particle filtering while robustly tracking user motion. Describing the body pose using wrists 3D positions rather than joint angles allows efficient handling of depth ambiguities for probabilistic tracking. We demonstrate experimentally the robustness of our 3D body tracking by real-time monocular vision, even in the case of partial occlusions and motion in the depth direction< Réduire

Mots clés en anglais

Monocular vision

3D/2D registration

3D motion capture

Real-time computer vision

Particle filtering

URI

https://oskar-bordeaux.fr/handle/20.500.12278/180898

DOI

http://dx.doi.org/10.1007/s00138-017-0861-3

Unités de recherche

ESTIA - Recherche

Voir/Ouvrir

Métadonnées

Partager cette publication !

Licence d’utilisation du document