ML Anthology

Support Vector Tracking

Shai Avidan
CVPR 2001 pp. I:184-191
doi:10.1109/CVPR.2001.990474 /cvpr/2001/avidan2001cvpr-support/

Abstract

Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.

CVPR Semantic Scholar

Cite

Text

Avidan. "Support Vector Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990474

Markdown

[Avidan. "Support Vector Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/avidan2001cvpr-support/) doi:10.1109/CVPR.2001.990474

BibTeX

@inproceedings{avidan2001cvpr-support,
  title     = {{Support Vector Tracking}},
  author    = {Avidan, Shai},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:184-191},
  doi       = {10.1109/CVPR.2001.990474},
  url       = {https://mlanthology.org/cvpr/2001/avidan2001cvpr-support/}
}