TY - GEN
T1 - Online video object segmentation via convolutional trident network
AU - Jang, Won Dong
AU - Kim, Chang-Su
N1 - Funding Information:
This work was supported partly by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2015R1A2A1A10055037), and partly by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2017-2016-0-00464) supervised by the IITP (Institute for Information & communications Technology Promotion).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/6
Y1 - 2017/11/6
N2 - A semi-supervised online video object segmentation algorithm, which accepts user annotations about a target object at the first frame, is proposed in this work. We propagate the segmentation labels at the previous frame to the current frame using optical flow vectors. However, the propagation is error-prone. Therefore, we develop the convolutional trident network (CTN), which has three decoding branches: separative, definite foreground, and definite background decoders. Then, we perform Markov random field optimization based on outputs of the three decoders. We sequentially carry out these processes from the second to the last frames to extract a segment track of the target object. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the DAVIS benchmark dataset.
AB - A semi-supervised online video object segmentation algorithm, which accepts user annotations about a target object at the first frame, is proposed in this work. We propagate the segmentation labels at the previous frame to the current frame using optical flow vectors. However, the propagation is error-prone. Therefore, we develop the convolutional trident network (CTN), which has three decoding branches: separative, definite foreground, and definite background decoders. Then, we perform Markov random field optimization based on outputs of the three decoders. We sequentially carry out these processes from the second to the last frames to extract a segment track of the target object. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the DAVIS benchmark dataset.
UR - http://www.scopus.com/inward/record.url?scp=85044320174&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2017.790
DO - 10.1109/CVPR.2017.790
M3 - Conference contribution
AN - SCOPUS:85044320174
T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
SP - 7474
EP - 7483
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Y2 - 21 July 2017 through 26 July 2017
ER -