Details

Autor(en) / Beteiligte

• Urtasun, R.
• Fleet, D.J.
• Hertzmann, A.
• Fua, P.

Titel

Priors for people tracking from small training sets

Ist Teil von

• Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005, Vol.1, p.403-410 Vol. 1

Ort / Verlag

IEEE

Erscheinungsjahr

2005

Quelle

IEL

Beschreibungen/Notizen

• 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 low-dimensional 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 straightforward deterministic optimization.