Gaussian-like Spatial Priors for Articulated Tracking
Abstract
We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.
Cite
Text
Hauberg et al. "Gaussian-like Spatial Priors for Articulated Tracking." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15549-9_31Markdown
[Hauberg et al. "Gaussian-like Spatial Priors for Articulated Tracking." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/hauberg2010eccv-gaussian/) doi:10.1007/978-3-642-15549-9_31BibTeX
@inproceedings{hauberg2010eccv-gaussian,
title = {{Gaussian-like Spatial Priors for Articulated Tracking}},
author = {Hauberg, Søren and Sommer, Stefan and Pedersen, Kim Steenstrup},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {425-437},
doi = {10.1007/978-3-642-15549-9_31},
url = {https://mlanthology.org/eccv/2010/hauberg2010eccv-gaussian/}
}