Bayesian Reconstruction of 3D Human Motion from Single-Camera Video
Abstract
The three-dimensional motion of humans is underdetermined when the observation is limited to a single camera, due to the inherent 3D ambi(cid:173) guity of 2D video. We present a system that reconstructs the 3D motion of human subjects from single-camera video, relying on prior knowledge about human motion, learned from training data, to resolve those am(cid:173) biguities. After initialization in 2D, the tracking and 3D reconstruction is automatic; we show results for several video sequences. The results show the power of treating 3D body tracking as an inference problem.
Cite
Text
Howe et al. "Bayesian Reconstruction of 3D Human Motion from Single-Camera Video." Neural Information Processing Systems, 1999.Markdown
[Howe et al. "Bayesian Reconstruction of 3D Human Motion from Single-Camera Video." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/howe1999neurips-bayesian/)BibTeX
@inproceedings{howe1999neurips-bayesian,
title = {{Bayesian Reconstruction of 3D Human Motion from Single-Camera Video}},
author = {Howe, Nicholas R. and Leventon, Michael E. and Freeman, William T.},
booktitle = {Neural Information Processing Systems},
year = {1999},
pages = {820-826},
url = {https://mlanthology.org/neurips/1999/howe1999neurips-bayesian/}
}