ML Anthology

Using Spatio-Temporal Patches for Simultaneous Estimation of Edge Strength, Orientation, and Motion

Andrew N. Stein, Martial Hebert
CVPRW 2006 pp. 19
doi:10.1109/CVPRW.2006.209 /cvprw/2006/stein2006cvprw-using/

Abstract

We describe an extension to ordinary patch-based edge detection in images using spatio-temporal volumetric patches from video. The inclusion of temporal information enables us to estimate motion normal to edges in addition to edge strength and spatial orientation. The method can handle complex edges in clutter by comparing distributions of data on either half of an extracted patch, rather than modeling the intensity profile of the edge. An efficient approach is provided for building the necessary histograms which samples candidate edge orientations and motions. Results are compared to classical spatio-temporal filtering techniques.

PDF CVPRW Semantic Scholar

Cite

Text

Stein and Hebert. "Using Spatio-Temporal Patches for Simultaneous Estimation of Edge Strength, Orientation, and Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006. doi:10.1109/CVPRW.2006.209

Markdown

[Stein and Hebert. "Using Spatio-Temporal Patches for Simultaneous Estimation of Edge Strength, Orientation, and Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006.](https://mlanthology.org/cvprw/2006/stein2006cvprw-using/) doi:10.1109/CVPRW.2006.209

BibTeX

@inproceedings{stein2006cvprw-using,
  title     = {{Using Spatio-Temporal Patches for Simultaneous Estimation of Edge Strength, Orientation, and Motion}},
  author    = {Stein, Andrew N. and Hebert, Martial},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2006},
  pages     = {19},
  doi       = {10.1109/CVPRW.2006.209},
  url       = {https://mlanthology.org/cvprw/2006/stein2006cvprw-using/}
}