Automatic configuration of spectral dimensionality reduction methods for 3D human pose estimation

Lewandowski, M., Makris, D. and Nebel, J.-C. (2009) Automatic configuration of spectral dimensionality reduction methods for 3D human pose estimation. In: IEEE International Conference on Computer Vision 2009; 03 Oct 2009, Kyoto, Japan. (Unpublished)

Full text not available from this archive.

Abstract

In this paper, our main contribution is a framework for the automatic configuration of any spectral dimensionality reduction methods. This is achieved, first, by introducing the mutual information measure to assess the quality of discovered embedded spaces. Secondly, we overcome the deficiency of mapping function in spectral dimensionality reduction approaches by proposing data projection between spaces based on fully automatic and dynamically adjustable Radial Basis Function network. Finally, this automatic framework is evaluated in the context of 3D human pose estimation. We demonstrate mutual information measure outperforms all current space assessment metrics. Moreover, experiments show the mapping associated to the induced embedded space displays good generalization properties. In particular, it allows improvement of accuracy by around 30% when refining 3D pose estimates of a walking sequence produced by an activity independent method.

Item Type: Conference or Workshop Item (Poster)
Event Title: IEEE International Conference on Computer Vision 2009
Organising Body: Institute of Electrical and Electronics Engineers
Uncontrolled Keywords: spectral dimension
Research Area: Computer science and informatics
Faculty, School or Research Centre: Faculty of Science, Engineering and Computing > School of Computing and Information Systems
Depositing User: Maren Schroeder
Date Deposited: 12 Oct 2012 13:21
Last Modified: 12 Oct 2012 13:21
URI: http://eprints.kingston.ac.uk/id/eprint/23719

Actions (Repository Editors)

Item Control Page Item Control Page