ML Anthology

On Analyzing Video with Very Small Motions

Michael Dixon, Austin Abrams, Nathan Jacobs, Robert Pless
CVPR 2011 pp. 425-432
doi:10.1109/CVPR.2011.5995703 /cvpr/2011/dixon2011cvpr-analyzing/

Abstract

We characterize a class of videos consisting of very small but potentially complicated motions. We find that in these scenes, linear appearance variations have a direct relationship to scene motions. We show how to interpret appearance variations captured through a PCA decomposition of the image set as a scene-specific non-parametric motion basis. We propose fast, robust tools for dense flow estimates that are effective in scenes with small motions and potentially large image noise. We show example results in a variety of applications, including motion segmentation and long-term point tracking.

CVPR Semantic Scholar

Cite

Text

Dixon et al. "On Analyzing Video with Very Small Motions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995703

Markdown

[Dixon et al. "On Analyzing Video with Very Small Motions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/dixon2011cvpr-analyzing/) doi:10.1109/CVPR.2011.5995703

BibTeX

@inproceedings{dixon2011cvpr-analyzing,
  title     = {{On Analyzing Video with Very Small Motions}},
  author    = {Dixon, Michael and Abrams, Austin and Jacobs, Nathan and Pless, Robert},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {425-432},
  doi       = {10.1109/CVPR.2011.5995703},
  url       = {https://mlanthology.org/cvpr/2011/dixon2011cvpr-analyzing/}
}