On-Line Selection of Discriminative Tracking Features
Abstract
We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. We develop an online feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. This feature selection mechanism is embedded in a tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented to illustrate how the method adapts to changing appearances of both tracked object and scene background.
Cite
Text
Collins and Liu. "On-Line Selection of Discriminative Tracking Features." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238365Markdown
[Collins and Liu. "On-Line Selection of Discriminative Tracking Features." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/collins2003iccv-line/) doi:10.1109/ICCV.2003.1238365BibTeX
@inproceedings{collins2003iccv-line,
title = {{On-Line Selection of Discriminative Tracking Features}},
author = {Collins, Robert T. and Liu, Yanxi},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2003},
pages = {346-352},
doi = {10.1109/ICCV.2003.1238365},
url = {https://mlanthology.org/iccv/2003/collins2003iccv-line/}
}