Dense Spatio-Temporal Motion Segmentation for Tracking Multiple Self-Occluding People
Abstract
In this paper, we describe a new dense spatio-temporal motion segmentation algorithm with application to tracking of people in crowded environments. The algorithm is based on state-of-the-art motion and image segmentation algorithms. We specifically make use of a mean shift image segmentation algorithm and two graph based motion segmentation algorithms. The resulting motion segmentation is on the one hand accurate and on the other hand computationally efficient. In addition our method is capable of handling mutual occlusions. This shows that motion segmentation can efficiently be used to simultaneously detect, track and segment moving objects. We apply this to tracking people in surveillance videos, but the algorithm is not limited to this class of scenes.
Cite
Text
Hofmann et al. "Dense Spatio-Temporal Motion Segmentation for Tracking Multiple Self-Occluding People." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543167Markdown
[Hofmann et al. "Dense Spatio-Temporal Motion Segmentation for Tracking Multiple Self-Occluding People." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/hofmann2010cvprw-dense/) doi:10.1109/CVPRW.2010.5543167BibTeX
@inproceedings{hofmann2010cvprw-dense,
title = {{Dense Spatio-Temporal Motion Segmentation for Tracking Multiple Self-Occluding People}},
author = {Hofmann, Martin and Rigoll, Gerhard and Huang, Thomas S.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2010},
pages = {9-14},
doi = {10.1109/CVPRW.2010.5543167},
url = {https://mlanthology.org/cvprw/2010/hofmann2010cvprw-dense/}
}