Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/20286

Title: Backing off: hierarchical decomposition of activity for 3D novel pose recovery
Authors: Darby, John
Li, Baihua
Costen, Nicholas
Fleet, David
Lawrence, Neil
Issue Date: 2009
Publisher: BMVC 2009 (© the authors)
Citation: 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.11.1-11.11
Abstract: For 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.
Description: The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Version: Published
DOI: 10.5244/C.23.11
URI: https://dspace.lboro.ac.uk/2134/20286
Publisher Link: http://dx.doi.org/10.5244/C.23.11
ISBN: 1901725391
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
BMVC09_H-GPLVM.pdfPublished version1.08 MBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.