3D People Tracking with Gaussian Process Dynamical Models
Top Cited Papers
- 10 July 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 238-245
- https://doi.org/10.1109/cvpr.2006.15
Abstract
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of human motion data, with a density function that gives higher probability to poses and motions close to the training data. With Bayesian model averaging a GPDM can be learned from relatively small amounts of data, and it generalizes gracefully to motions outside the training set. Here we modify the GPDM to permit learning from motions with significant stylistic variation. The resulting priors are effective for tracking a range of human walking styles, despite weak and noisy image measurements and significant occlusions.Keywords
This publication has 14 references indexed in Scilit:
- Gaussian Process Dynamical Models for Human MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Recovering 3D human pose from monocular imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Learning Appearance Manifolds from VideoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Modeling and Learning Contact Dynamics in Human MotionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Priors for people tracking from small training setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Style-based inverse kinematicsACM Transactions on Graphics, 2004
- Generative modeling for continuous non-linearly embedded visual inferencePublished by Association for Computing Machinery (ACM) ,2004
- Interactive control of avatars animated with human motion dataACM Transactions on Graphics, 2002
- Learning and classification of complex dynamicsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Bayesian Learning for Neural NetworksPublished by Springer Science and Business Media LLC ,1996