TY - GEN
T1 - Primary object segmentation in videos via alternate convex optimization of foreground and background distributions
AU - Jang, Won Dong
AU - Lee, Chulwoo
AU - Kim, Chang-Su
N1 - Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2015R1A2A1A10055037).
Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/9
Y1 - 2016/12/9
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84986269059&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2016.82
DO - 10.1109/CVPR.2016.82
M3 - Conference contribution
AN - SCOPUS:84986269059
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 696
EP - 704
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PB - IEEE Computer Society
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Y2 - 26 June 2016 through 1 July 2016
ER -