Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets
Abstract
We present an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragments are automatically adapted to the image data, being selected by an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. Modeling of target and background are performed in a Chan-Vese manner, using the framework of level sets to preserve accurate boundaries of the target. The extracted target boundaries are used to learn the dynamic shape of the target over time, enabling tracking to continue under total occlusion. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique.
Cite
Text
Chockalingam et al. "Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459276Markdown
[Chockalingam et al. "Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/chockalingam2009iccv-adaptive/) doi:10.1109/ICCV.2009.5459276BibTeX
@inproceedings{chockalingam2009iccv-adaptive,
title = {{Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets}},
author = {Chockalingam, Prakash and Pradeep, S. Nalin and Birchfield, Stan},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2009},
pages = {1530-1537},
doi = {10.1109/ICCV.2009.5459276},
url = {https://mlanthology.org/iccv/2009/chockalingam2009iccv-adaptive/}
}