Statistical Feature Modelling for Active Contours
Abstract
A method is proposed of robust feature-detection for visual tracking. Frequently strong background clutter competes with foreground features and may succeed in pulling a tracker off target. This effect may be avoided by modelling the appearance of the foreground object (the target). The model consists of probability density functions of intensity along curve normals—a form of statistical template. The model can then be located by the use of a dynamic programming algorithm—even in the presence of substantial image distortions. Practical tests with contour tracking show marked improvement over simple feature detection techniques.
Cite
Text
Rowe and Blake. "Statistical Feature Modelling for Active Contours." European Conference on Computer Vision, 1996. doi:10.1007/3-540-61123-1_170Markdown
[Rowe and Blake. "Statistical Feature Modelling for Active Contours." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/rowe1996eccv-statistical/) doi:10.1007/3-540-61123-1_170BibTeX
@inproceedings{rowe1996eccv-statistical,
title = {{Statistical Feature Modelling for Active Contours}},
author = {Rowe, Simon and Blake, Andrew},
booktitle = {European Conference on Computer Vision},
year = {1996},
pages = {560-569},
doi = {10.1007/3-540-61123-1_170},
url = {https://mlanthology.org/eccv/1996/rowe1996eccv-statistical/}
}