Tracking with the EM Contour Algorithm
Abstract
A novel active-contour method is presented and applied to pose refinement and tracking. The main innovation is that no ”features” are detected at any stage: contours are simply assumed to remove statistical dependencies between pixels on opposite sides of the contour. This assumption, together with a simple model of shape variability of the geometric models, leads to the application of an EM method for maximizing the likelihood of pose parameters. In addition, a dynamical model of the system leads to the application of a Kalman filter. The method is demonstrated by tracking motor vehicles with 3-D models.
Cite
Text
Pece and Worrall. "Tracking with the EM Contour Algorithm." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47969-4_1Markdown
[Pece and Worrall. "Tracking with the EM Contour Algorithm." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/pece2002eccv-tracking/) doi:10.1007/3-540-47969-4_1BibTeX
@inproceedings{pece2002eccv-tracking,
title = {{Tracking with the EM Contour Algorithm}},
author = {Pece, Arthur E. C. and Worrall, Anthony D.},
booktitle = {European Conference on Computer Vision},
year = {2002},
pages = {3-17},
doi = {10.1007/3-540-47969-4_1},
url = {https://mlanthology.org/eccv/2002/pece2002eccv-tracking/}
}