Sciweavers

ICCV
2005
IEEE

Priors for People Tracking from Small Training Sets

14 years 4 months ago
Priors for People Tracking from Small Training Sets
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density function that both gives higher probability to points close to training data and provides a nonlinear probabilistic mapping from the lowdimensional latent space to the full-dimensional pose space. The SGPLVM is a natural choice when only small amounts of training data are available. We demonstrate our approach with two distinct motions, golfing and walking. We show that the SGPLVM sufficiently constrains the problem such that tracking can be accomplished with straighforward deterministic optimization.
Raquel Urtasun, David J. Fleet, Aaron Hertzmann, P
Added 24 Jun 2010
Updated 24 Jun 2010
Type Conference
Year 2005
Where ICCV
Authors Raquel Urtasun, David J. Fleet, Aaron Hertzmann, Pascal Fua
Comments (0)