TY - GEN
T1 - Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking
AU - Simo-Serra, Edgar
AU - Torras, Carme
AU - Moreno-Noguer, Francesc
N1 - Publisher Copyright:
© 2015 MVA organization.
PY - 2015/7/8
Y1 - 2015/7/8
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84941215720&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84941215720&partnerID=8YFLogxK
U2 - 10.1109/MVA.2015.7153212
DO - 10.1109/MVA.2015.7153212
M3 - Conference contribution
AN - SCOPUS:84941215720
T3 - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
SP - 394
EP - 397
BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Y2 - 18 May 2015 through 22 May 2015
ER -