Successful tracking of articulated hand motion is the first step in many computer vision applications such as gesture recognition. However the nonrigidity of the hand, complex background scenes, and occlusion make tracking a challenging task. We divide and conquer tracking by decomposing complex motion into nonrigid motion and rigid motion. A learning-based algorithm for analyzing nonrigid motion is presented. In this method, appearance-based models are learned from image data, and underlying motion patterns are explored using a generative model. Nonlinear dynamics of the articulation such as fast appearance deformation can thus be analyzed without resorting to a complex kinematic model. We approximate the rigid motion as planar motion, which can be approached by a filtering method. We unify our treatments of nonrigid motion and rigid motion into a single, robust Bayesian framework and demonstrate the efficacy of this method by performing successful tracking in the presence of significant occlusion clutter.
Probabilistic tracking and recognition of nonrigid hand motion
2003-01-01
831456 byte
Conference paper
Electronic Resource
English
Probabilistic Tracking and Recognition of Non-Rigid Hand Motion
British Library Conference Proceedings | 2003
|Detection and Recognition of Periodic, Nonrigid Motion
British Library Online Contents | 1997
|Nonrigid Motion Analysis: Articulated and Elastic Motion
British Library Online Contents | 1998
|Point correspondence in unstructured nonrigid motion
IEEE | 1995
|Point Correspondence in Unstructured Nonrigid Motion
British Library Conference Proceedings | 1995
|