BMVC09_H-GPLVM.pdf (1.05 MB)
Backing off: hierarchical decomposition of activity for 3D novel pose recovery
conference contribution
posted on 2016-02-10, 11:44 authored by John Darby, Baihua LiBaihua Li, Nicholas Costen, David Fleet, Neil LawrenceFor model-based 3D human pose estimation, even simple models of the human body lead to high-dimensional state spaces. Where the class of activity is known a priori, low-dimensional activity models learned from training data make possible a thorough and efficient search for the best pose. Conversely, searching for solutions in the full state space places no restriction on the class of motion to be recovered, but is both difficult and expensive. This paper explores a potential middle ground between these approaches, using the hierarchical Gaussian process latent variable model to learn activity at different hierarchical scales within the human skeleton. We show that by training on full-body activity data then descending through the hierarchy in stages and exploring subtrees independently of one another, novel poses may be recovered. Experimental results on motion capture data and monocular video sequences demonstrate the utility of the approach, and comparisons are drawn with existing low-dimensional activity models. © 2009. The copyright of this document resides with its authors.
History
School
- Science
Department
- Computer Science
Published in
British Machine Vision Conference, BMVC 2009 - ProceedingsCitation
DARBY, J. ... et al, 2009. Backing off: hierarchical decomposition of activity for 3D novel pose recovery. British Machine Vision Conference, BMVC 2009 - Proceedings, 7th-10th September 2009, London, pp.11.1-11.11Publisher
BMVC 2009 (© the authors)Version
- VoR (Version of Record)
Publisher statement
This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/Publication date
2009Notes
The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.ISBN
1901725391;9781901725391Publisher version
Language
- en