Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions
Abstract
An unsupervised video object segmentation algorithm, which discovers a primary object in a video sequence automatically, is proposed in this work. We introduce three energies in terms of foreground and background probability distributions: Markov, spatiotemporal, and antagonistic energies. Then, we minimize a hybrid of the three energies to separate a primary object from its background. However, the hybrid energy is nonconvex. Therefore, we develop the alternate convex optimization (ACO) scheme, which decomposes the nonconvex optimization into two quadratic programs. Moreover, we propose the forward-backward strategy, which performs the segmentation sequentially from the first to the last frames and then vice versa, to exploit temporal correlations. Experimental results on extensive datasets demonstrate that the proposed ACO algorithm outperforms the state-of-the-art techniques significantly.
Cite
Text
Jang et al. "Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.82Markdown
[Jang et al. "Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/jang2016cvpr-primary/) doi:10.1109/CVPR.2016.82BibTeX
@inproceedings{jang2016cvpr-primary,
title = {{Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions}},
author = {Jang, Won-Dong and Lee, Chulwoo and Kim, Chang-Su},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2016},
doi = {10.1109/CVPR.2016.82},
url = {https://mlanthology.org/cvpr/2016/jang2016cvpr-primary/}
}