ML Anthology

Real-Time Tracking of Non-Rigid Objects Using Mean Shift

Dorin Comaniciu, Visvanathan Ramesh, Peter Meer
CVPR 2000 pp. 2142-
doi:10.1109/CVPR.2000.854761 /cvpr/2000/comaniciu2000cvpr-real/

Abstract

A new method for real time tracking of non-rigid objects seen from a moving camera is proposed. The central computational module is based on the mean shift iterations and finds the most probable target position in the current frame. The dissimilarity between the target model (its color distribution) and the target candidates is expressed by a metric derived from the Bhattacharyya coefficient. The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution. The capability of the tracker to handle in real time partial occlusions, significant clutter, and target scale variations, is demonstrated for several image sequences.

CVPR Semantic Scholar

Cite

Text

Comaniciu et al. "Real-Time Tracking of Non-Rigid Objects Using Mean Shift." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854761

Markdown

[Comaniciu et al. "Real-Time Tracking of Non-Rigid Objects Using Mean Shift." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/comaniciu2000cvpr-real/) doi:10.1109/CVPR.2000.854761

BibTeX

@inproceedings{comaniciu2000cvpr-real,
  title     = {{Real-Time Tracking of Non-Rigid Objects Using Mean Shift}},
  author    = {Comaniciu, Dorin and Ramesh, Visvanathan and Meer, Peter},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2142-},
  doi       = {10.1109/CVPR.2000.854761},
  url       = {https://mlanthology.org/cvpr/2000/comaniciu2000cvpr-real/}
}