ML Anthology

Matching and Interpretation of Planar Motion Using Tensor Voting

Changki Min, Gérard G. Medioni
CVPR 2004 pp. 57
doi:10.1109/CVPR.2004.392 /cvpr/2004/min2004cvpr-matching/

Abstract

An ellipse that is rotating within an image can be interpreted in different ways under different conditions. We are interested in the 'thin vs. fat ellipse' phenomenon; a thin rotating ellipse is perceived as undergoing rigid rotation, while a fat one is perceived as undergoing nonrigid deformation. Our computational model tries to emulate human perception using the tensor voting framework. The original 4-D tensor voting formalism is found not sufficient to solve this problem, and we augment it here to explicitly handle rotation and deformation.

CVPR Semantic Scholar

Cite

Text

Min and Medioni. "Matching and Interpretation of Planar Motion Using Tensor Voting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.392

Markdown

[Min and Medioni. "Matching and Interpretation of Planar Motion Using Tensor Voting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/min2004cvpr-matching/) doi:10.1109/CVPR.2004.392

BibTeX

@inproceedings{min2004cvpr-matching,
  title     = {{Matching and Interpretation of Planar Motion Using Tensor Voting}},
  author    = {Min, Changki and Medioni, Gérard G.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {57},
  doi       = {10.1109/CVPR.2004.392},
  url       = {https://mlanthology.org/cvpr/2004/min2004cvpr-matching/}
}