Pose Refinement of Active Models Using Forces in 3D

Abstract

A new algorithm is described for refining the pose of a model of a rigid object, to conform more accurately to the image structure. Elemental 3D forces are considered to act on the model. These are derived from directional derivatives of the image local to the projected model features. The convergence properties of the algorithm is investigated and compared to a previous technique. Its use in a video sequence of a cluttered outdoor traffic scene is also illustrated and assessed.

Cite

Text

Worrall et al. "Pose Refinement of Active Models Using Forces in 3D." European Conference on Computer Vision, 1994. doi:10.1007/3-540-57956-7_38

Markdown

[Worrall et al. "Pose Refinement of Active Models Using Forces in 3D." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/worrall1994eccv-pose/) doi:10.1007/3-540-57956-7_38

BibTeX

@inproceedings{worrall1994eccv-pose,
  title     = {{Pose Refinement of Active Models Using Forces in 3D}},
  author    = {Worrall, Anthony D. and Sullivan, Geoffrey D. and Baker, Keith D.},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {341-350},
  doi       = {10.1007/3-540-57956-7_38},
  url       = {https://mlanthology.org/eccv/1994/worrall1994eccv-pose/}
}