Graph-based Particle Filter for Human Tracking with Stylistic Variations

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.