ML Anthology

Robust Dynamic Motion Estimation over Time

Michael J. Black, P. Anandan
CVPR 1991 pp. 296-302
doi:10.1109/CVPR.1991.139705 /cvpr/1991/black1991cvpr-robust/

Abstract

A novel approach to incrementally estimating visual motion over a sequence of images is presented. The authors start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of a minimization problem. The resulting objective function is non-convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. A highly parallel incremental stochastic minimization algorithm is presented which has a number of advantages over previous approaches. The incremental nature of the scheme makes it dynamic and permits the detection of occlusion and disocclusion boundaries.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

PDF CVPR Semantic Scholar

Cite

Text

Black and Anandan. "Robust Dynamic Motion Estimation over Time." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139705

Markdown

[Black and Anandan. "Robust Dynamic Motion Estimation over Time." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/black1991cvpr-robust/) doi:10.1109/CVPR.1991.139705

BibTeX

@inproceedings{black1991cvpr-robust,
  title     = {{Robust Dynamic Motion Estimation over Time}},
  author    = {Black, Michael J. and Anandan, P.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {296-302},
  doi       = {10.1109/CVPR.1991.139705},
  url       = {https://mlanthology.org/cvpr/1991/black1991cvpr-robust/}
}