ML Anthology

Modeling View and Posture Manifolds for Tracking

Chan-Su Lee, Ahmed M. Elgammal
ICCV 2007 pp. 1-8
doi:10.1109/ICCV.2007.4409030 /iccv/2007/lee2007iccv-modeling/

Abstract

In this paper we consider modeling data lying on multiple continuous manifolds. In particular, we model the shape manifold of a person performing a motion observed from different view points along a view circle at fixed camera height. We introduce a model that ties together the body configuration (kinematics) manifold and the visual manifold (observations) in a way that facilitates tracking the 3D configuration with continuous relative view variability. The model exploits the low dimensionality nature of both the body configuration manifold and the view manifold where each of them are represented separately.

PDF ICCV Semantic Scholar

Cite

Text

Lee and Elgammal. "Modeling View and Posture Manifolds for Tracking." IEEE/CVF International Conference on Computer Vision, 2007. doi:10.1109/ICCV.2007.4409030

Markdown

[Lee and Elgammal. "Modeling View and Posture Manifolds for Tracking." IEEE/CVF International Conference on Computer Vision, 2007.](https://mlanthology.org/iccv/2007/lee2007iccv-modeling/) doi:10.1109/ICCV.2007.4409030

BibTeX

@inproceedings{lee2007iccv-modeling,
  title     = {{Modeling View and Posture Manifolds for Tracking}},
  author    = {Lee, Chan-Su and Elgammal, Ahmed M.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2007},
  pages     = {1-8},
  doi       = {10.1109/ICCV.2007.4409030},
  url       = {https://mlanthology.org/iccv/2007/lee2007iccv-modeling/}
}