Regression-Based Human Motion Capture From Voxel Data

Abstract

A regression based method is proposed to recover human body pose from 3D voxel data. In order to do this we need to convert the voxel data into a feature vector. This is done using a Bayesian approach based on Mixture of Probabilistic PCA that transforms a collection of 3D shape context descriptors, extracted from the voxels, to a compact feature vector. For the regression, the newly-proposed Multi-Variate Relevance Vector Machine is explored to learn a single mapping from this feature vector to a low-dimensional representation of full body pose. We demonstrate the effectiveness and robustness of our method with experiments on both synthetic data and real sequences.

DOI: 10.5244/C.20.29

Extracted Key Phrases

8 Figures and Tables

Cite this paper

@inproceedings{Sun2006RegressionBasedHM, title={Regression-Based Human Motion Capture From Voxel Data}, author={Yunda Sun and Matthieu Bray and Arasanathan Thayananthan and B. Yuan and Philip H. S. Torr}, booktitle={BMVC}, year={2006} }