Occam Algorithms for Computing Visual Motion

Schweitzer, Haim

doi:10.1109/ICCV.1993.378163

Occam Algorithms for Computing Visual Motion

Haim Schweitzer

ICCV 1993 pp. 551-555

doi:10.1109/ICCV.1993.378163 /iccv/1993/schweitzer1993iccv-occam/

Abstract

By drawing an analogy with machine learning, the author proposes to define visual motion as a predictor that can accurately predict future frames. Under this new definition, visual motion can be specified by a collection of image patches, each moving in a simple motion. An implementation with rectangular patches determined recursively by a binary decision tree is described. Experimental results on real video sequences verify the algorithm assumptions and show that motion in typical sequences can be accurately described in terms of a few parameters.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

ICCV Semantic Scholar

Cite

Text

Schweitzer. "Occam Algorithms for Computing Visual Motion." IEEE/CVF International Conference on Computer Vision, 1993. doi:10.1109/ICCV.1993.378163

Markdown

[Schweitzer. "Occam Algorithms for Computing Visual Motion." IEEE/CVF International Conference on Computer Vision, 1993.](https://mlanthology.org/iccv/1993/schweitzer1993iccv-occam/) doi:10.1109/ICCV.1993.378163

BibTeX

@inproceedings{schweitzer1993iccv-occam,
  title     = {{Occam Algorithms for Computing Visual Motion}},
  author    = {Schweitzer, Haim},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1993},
  pages     = {551-555},
  doi       = {10.1109/ICCV.1993.378163},
  url       = {https://mlanthology.org/iccv/1993/schweitzer1993iccv-occam/}
}