Motion Segmentation via Synchronization
Abstract
In this paper we consider the problem of segmenting points in a collection of images that contain multiple moving objects. Our contribution is three-fold: (i) we propose a matrix representation of segmentation that permits to formulate the problem in terms of "synchronization" of binary matrices; (ii) we derive a spectral solution to solve such a problem, which is inspired by previous works on synchronization of rotations, homographies, rigid motions and permutations; (iii) we explain how our solution can be interpreted in terms of spectral clustering. The proposed approach is validated on both synthetic and real scenarios, in addition to the Hopkins benchmark.
Cite
Text
Arrigoni and Pajdla. "Motion Segmentation via Synchronization." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00527Markdown
[Arrigoni and Pajdla. "Motion Segmentation via Synchronization." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/arrigoni2019iccvw-motion/) doi:10.1109/ICCVW.2019.00527BibTeX
@inproceedings{arrigoni2019iccvw-motion,
title = {{Motion Segmentation via Synchronization}},
author = {Arrigoni, Federica and Pajdla, Tomás},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {4280-4290},
doi = {10.1109/ICCVW.2019.00527},
url = {https://mlanthology.org/iccvw/2019/arrigoni2019iccvw-motion/}
}