ML Anthology

An EM-like Algorithm for Color-Histogram-Based Object Tracking

Zoran Zivkovic, Ben J. A. Kröse
CVPR 2004 pp. 798-803
doi:10.1109/CVPR.2004.32 /cvpr/2004/zivkovic2004cvpr-em/

Abstract

The iterative procedure called 'mean-shift' is a simple robust method for finding the position of a local mode (local maximum) of a kernel-based estimate of a density function. A new robust algorithm is given here that presents a natural extension of the 'mean-shift' procedure. The new algorithm simultaneously estimates the position of the local mode and the covariance matrix that describes the approximate shape of the local mode. We apply the new method to develop a new 5-degrees of freedom (DOF) color histogram based non-rigid object tracking algorithm.

CVPR Semantic Scholar

Cite

Text

Zivkovic and Kröse. "An EM-like Algorithm for Color-Histogram-Based Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.32

Markdown

[Zivkovic and Kröse. "An EM-like Algorithm for Color-Histogram-Based Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/zivkovic2004cvpr-em/) doi:10.1109/CVPR.2004.32

BibTeX

@inproceedings{zivkovic2004cvpr-em,
  title     = {{An EM-like Algorithm for Color-Histogram-Based Object Tracking}},
  author    = {Zivkovic, Zoran and Kröse, Ben J. A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {798-803},
  doi       = {10.1109/CVPR.2004.32},
  url       = {https://mlanthology.org/cvpr/2004/zivkovic2004cvpr-em/}
}