Motion Segmentation Using an Occlusion Detector
Abstract
We present a novel method for the detection of motion boundaries in a video sequence based on differential properties of the spatio-temporal domain. Regarding the video sequence as a 3D spatio-temporal function, we consider the second moment matrix of its gradients (averaged over a local window), and show that the eigenvalues of this matrix can be used to detect occlusions and motion discontinuities. Since these cannot always be determined locally (due to false corners and the aperture problem), a scale-space approach is used for extracting the location of motion boundaries. A closed contour is then constructed from the most salient boundary fragments, to provide the final segmentation. The method is shown to give good results on pairs of real images taken in general motion. We use synthetic data to show its robustness to high levels of noise and illumination changes; we also include cases where no intensity edge exists at the location of the motion boundary, or when no parametric motion model can describe the data.
Cite
Text
Feldman and Weinshall. "Motion Segmentation Using an Occlusion Detector." European Conference on Computer Vision, 2006. doi:10.1007/978-3-540-70932-9_3Markdown
[Feldman and Weinshall. "Motion Segmentation Using an Occlusion Detector." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/feldman2006eccv-motion/) doi:10.1007/978-3-540-70932-9_3BibTeX
@inproceedings{feldman2006eccv-motion,
title = {{Motion Segmentation Using an Occlusion Detector}},
author = {Feldman, Doron and Weinshall, Daphna},
booktitle = {European Conference on Computer Vision},
year = {2006},
pages = {34-47},
doi = {10.1007/978-3-540-70932-9_3},
url = {https://mlanthology.org/eccv/2006/feldman2006eccv-motion/}
}