Title :
Object-Based Visual 3D Tracking of Articulated Objects via Kinematic Sets
Author :
Comport, Andrew I. ; Marchand, Éric ; Chaumette, Francois
Author_Institution :
IRISA - INRIA Rennes, France
Abstract :
A theoretical framework based on robotics techniques is introduced for visual tracking of parametric non-rigid multi-body objects. It is based on an a-priori model of the object including a general mechanical link description. The objective equation is defined in the object-based coordinate system and non-linear minimization relates to the movement of the object and not the camera. This results in simultaneously estimating all degrees of freedom between the object´s last known position relative to its previous position as well as internal articulated parameters. A new kinematic-set formulation takes into account that articulated degrees of freedom are directly observable from the camera and therefore their estimation does not need to pass via a kinematic-chain back to the root. By doing this the tracking techniques are efficient and precise leading to real-time performance and accurate measurements. The system is locally based upon an accurate modeling of a distance criteria. A general method is derived for defining any type of mechanical link and experimental results show prismatic, rotational and helicoidal type links. A statistical M-estimation technique is applied to improve robustness. A monocular camera system was used as a real-time sensor to verify the theory.
Keywords :
Computer Society; Computer vision; Conferences; Kinematics; Pattern recognition;
Conference_Titel :
Computer Vision and Pattern Recognition Workshop, 2004. CVPRW '04. Conference on
DOI :
10.1109/CVPR.2004.136