ML Anthology

A Multigrid Approach for Hierarchical Motion Estimation

Étienne Mémin, Patrick Pérez
ICCV 1998 pp. 933-938
doi:10.1109/ICCV.1998.710828 /iccv/1998/memin1998iccv-multigrid/

Abstract

This paper focuses on the estimation of the apparent motion field between two consecutive frames in an image sequence. The approach developed here is a tradeoff between methods based on global parameterized flow models and local dense optic flow estimators. The method relies on an adaptive multigrid minimization approach. In addition to accelerated convergence toward good estimates, it allows to mix different parameterizations of the estimate relative to adaptive partitions of the image. The performances of the resulting algorithms are demonstrated in the difficult context of a non-convex energy. Experimental results on real world Meteosat sequences are presented.

ICCV Semantic Scholar

Cite

Text

Mémin and Pérez. "A Multigrid Approach for Hierarchical Motion Estimation." IEEE/CVF International Conference on Computer Vision, 1998. doi:10.1109/ICCV.1998.710828

Markdown

[Mémin and Pérez. "A Multigrid Approach for Hierarchical Motion Estimation." IEEE/CVF International Conference on Computer Vision, 1998.](https://mlanthology.org/iccv/1998/memin1998iccv-multigrid/) doi:10.1109/ICCV.1998.710828

BibTeX

@inproceedings{memin1998iccv-multigrid,
  title     = {{A Multigrid Approach for Hierarchical Motion Estimation}},
  author    = {Mémin, Étienne and Pérez, Patrick},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1998},
  pages     = {933-938},
  doi       = {10.1109/ICCV.1998.710828},
  url       = {https://mlanthology.org/iccv/1998/memin1998iccv-multigrid/}
}