Graph-based Particle Filter for Human Tracking with Stylistic Variations

When?

Wednesday 27 March 2013, 14:30 to 15:30

Where?

CVSSP Seminar Room (40bAB05)

Open to:

Public, Staff, Students

Speaker:

Dr Dimitrios Makris, Kingston University

Abstract:

In this paper, we propose an integrated particle filter-based pose tracking framework which combines priors able to model human motions keeping stylistic variations, reducing the probability of divergence and facilitating the recovering after failure. A novel unsupervised dimensionality reduction technique, Generalised Laplacian Eigenmaps (GLE), generates compact and coherent continuous spaces which explicitly express style. The proposed particle filter embeds the GLE manifold to take advantage of its geometry into the propagation and hypothesis generation stage. The method is validated using standard HumanEva 2 dataset.

 

Biography:

Dr Dimitrios Makris is a Reader at the Digital Imaging Research Centre at Kingston University. His research interests are Computer Vision, Machine Learning and in particular Motion Analysis and Dimensionality Reduction. Dr Makris has been awarded a number of research project as principal investigator and has been financially supported by EPSRC, TSB as well as national (Ipsotek Ltd, Legion Ltd) and international companies (BARCO Ltd/Belgium, LG Electronics/Korea). He is currently the coordinator of the EPSRC Network on Vision and Language (VL-Net). He was the invited speaker in Second IEEE International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS2009). He was one of the only two UK academics that have been interviewed by ZDF/Discovery Channel for their documentary: "2057 – The World in 50 years".