Publication

Lie algebra-based kinematic prior for 3D human pose tracking

Conference Article

Conference

IAPR International Conference on Machine Vision Applications (MVA)

Edition

14th

Pages

394-397

Doc link

http://www.mva-org.jp/Proceedings/2015USB/papers/11-03.pdf

File

Download the digital copy of the doc pdf document

Abstract

We propose a novel kinematic prior for 3D human pose tracking that allows predicting the position in subsequent frames given the current position. We first define a Riemannian manifold that models the pose and extend it with its Lie algebra to also be able to represent the kinematics. We then learn a joint Gaussian mixture model of both the human pose and the kinematics on this manifold. Finally by conditioning the kinematics on the pose we are able to obtain a distribution of poses for subsequent frames that which can be used as a reliable prior in 3D human pose tracking. Our model scales well to large amounts of data and can be sampled at over 100,000 samples/second. We show it outperforms the widely used Gaussian diffusion model on the challenging Human3.6M dataset.

Categories

computer vision.

Author keywords

Lie algebra, 3D human pose tracking, mixture models

Scientific reference

E. Simo-Serra, C. Torras and F. Moreno-Noguer. Lie algebra-based kinematic prior for 3D human pose tracking, 14th IAPR International Conference on Machine Vision Applications, 2015, Tokyo, Japan, pp. 394-397.