Sciweavers

Share
NIPS
2004

Joint Tracking of Pose, Expression, and Texture using Conditionally Gaussian Filters

9 years 1 months ago
Joint Tracking of Pose, Expression, and Texture using Conditionally Gaussian Filters
We present a generative model and stochastic filtering algorithm for simultaneous tracking of 3D position and orientation, non-rigid motion, object texture, and background texture using a single camera. We show that the solution to this problem is formally equivalent to stochastic filtering of conditionally Gaussian processes, a problem for which well known approaches exist [3, 8]. We propose an approach based on Monte Carlo sampling of the nonlinear component of the process (object motion) and exact filtering of the object and background textures given the sampled motion. The smoothness of image sequences in time and space is exploited by using Laplace's method to generate proposal distributions for importance sampling [7]. The resulting inference algorithm encompasses both optic flow and template-based tracking as special cases, and elucidates the conditions under which these methods are optimal. We demonstrate an application of the system to 3D non-rigid face tracking. 1 Backg...
Tim K. Marks, John R. Hershey, J. Cooper Roddey, J
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors Tim K. Marks, John R. Hershey, J. Cooper Roddey, Javier R. Movellan
Comments (0)
books