ML Anthology

Affine Invariant Detection of Periodic Motion

Steven M. Seitz, Charles R. Dyer
CVPR 1994 pp. 970-975
doi:10.1109/CVPR.1994.323936 /cvpr/1994/seitz1994cvpr-affine/

Abstract

Current approaches for detecting periodic motion assume a stationary camera and place limits on an object's motion. These approaches rely on the assumption that a periodic motion projects to a set of periodic image curves, an assumption that fails in general. Using affine-invariance, we derive necessary and sufficient conditions for an image sequence to be the projection of a periodic motion. No restrictions are placed on either the motion of the camera or the object. Our algorithm is shown to be provably-correct for noise-free data and is easily extended to be robust with respect to occlusions and noise. The extended algorithm is evaluated with real and synthetic image sequences.< <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

Seitz and Dyer. "Affine Invariant Detection of Periodic Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323936

Markdown

[Seitz and Dyer. "Affine Invariant Detection of Periodic Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/seitz1994cvpr-affine/) doi:10.1109/CVPR.1994.323936

BibTeX

@inproceedings{seitz1994cvpr-affine,
  title     = {{Affine Invariant Detection of Periodic Motion}},
  author    = {Seitz, Steven M. and Dyer, Charles R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {970-975},
  doi       = {10.1109/CVPR.1994.323936},
  url       = {https://mlanthology.org/cvpr/1994/seitz1994cvpr-affine/}
}