ML Anthology

Global 3D Motion Estimation

Cornelia Fermüller
CVPR 1993 pp. 415-421
doi:10.1109/CVPR.1993.341097 /cvpr/1993/fermuller1993cvpr-global/

Abstract

It is shown how a monocular observer can estimate its 3D motion relative to the scene by using normal flow measurements in a global and qualitative way. It is proved that local normal flow measurements form global patterns in the image plane. The position of these patterns is related to the 3D motion parameters. By locating some of these patterns, which depend only on subsets of the motion parameters, through a simple search technique, the 3D motion parameters can be found. The proposed algorithmic procedure is very robust, since it is not affected by small perturbations in the normal flow measurements. The direction of translation and the axis of rotation can be estimated with up to 100% error in the image measurements.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Fermüller. "Global 3D Motion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341097

Markdown

[Fermüller. "Global 3D Motion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/fermuller1993cvpr-global/) doi:10.1109/CVPR.1993.341097

BibTeX

@inproceedings{fermuller1993cvpr-global,
  title     = {{Global 3D Motion Estimation}},
  author    = {Fermüller, Cornelia},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {415-421},
  doi       = {10.1109/CVPR.1993.341097},
  url       = {https://mlanthology.org/cvpr/1993/fermuller1993cvpr-global/}
}