Learning and Tracking Cyclic Human Motion
Abstract
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segmenting these data automatically into "cycles". Then the mean and the princi(cid:173) pal components of the cycles are computed using a new algorithm that accounts for missing information and enforces smooth tran(cid:173) sitions between cycles. The learned temporal model provides a prior probability distribution over human motions that can be used in a Bayesian framework for tracking human subjects in complex monocular video sequences and recovering their 3D motion.
Cite
Text
Ormoneit et al. "Learning and Tracking Cyclic Human Motion." Neural Information Processing Systems, 2000.Markdown
[Ormoneit et al. "Learning and Tracking Cyclic Human Motion." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/ormoneit2000neurips-learning/)BibTeX
@inproceedings{ormoneit2000neurips-learning,
title = {{Learning and Tracking Cyclic Human Motion}},
author = {Ormoneit, Dirk and Sidenbladh, Hedvig and Black, Michael J. and Hastie, Trevor},
booktitle = {Neural Information Processing Systems},
year = {2000},
pages = {894-900},
url = {https://mlanthology.org/neurips/2000/ormoneit2000neurips-learning/}
}