Title | ||
---|---|---|
Joint Tracking of Pose, Expression, and Texture using Conditionally Gaussian Filters. |
Abstract | ||
---|---|---|
We present a generative model and stochastic filtering algor ithm for si-multaneous 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 fil-tering 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 mo-tion) and exact filtering of the object and background textur es 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 encom-passes both optic flow and template-based tracking as specia l cases, and elucidates the conditions under which these methods are optimal. We demonstrate an application of the system to 3D non-rigid face tracking. |
Year | Venue | Keywords |
---|---|---|
2004 | NIPS | importance sampling,monte carlo sampling,face tracking,gaussian process,optical flow |
Field | DocType | Citations |
Computer vision,Mathematical optimization,Monte Carlo method,Importance sampling,Laplace transform,Computer science,Filter (signal processing),Gaussian,Gaussian process,Artificial intelligence,Facial motion capture,Generative model | Conference | 5 |
PageRank | References | Authors |
0.50 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tim K. Marks | 1 | 281 | 19.41 |
John R. Hershey | 2 | 844 | 65.57 |
J. Cooper Roddey | 3 | 54 | 6.79 |
Javier R. Movellan | 4 | 1853 | 150.44 |