TY - GEN
T1 - Temporal Superpixels Based on Proximity-Weighted Patch Matching
AU - Lee, Se Ho
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. NRF2015R1A2A1A10055037), and partly by the Ministry of Science and ICT (MSIT), Korea, under the Information Technology Research Center (ITRC) support program (IITP-2017-2016-0-00464) supervised by the Institute for Information and communications Technology Promotion (IITP).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - A temporal superpixel algorithm based on proximity-weighted patch matching (TS-PPM) is proposed in this work. We develop the proximity-weighted patch matching (PPM), which estimates the motion vector of a superpixel robustly, by considering the patch matching distances of neighboring superpixels as well as the target superpixel. In each frame, we initialize superpixels by transferring the superpixel labels of the previous frame using PPM motion vectors. Then, we update the superpixel labels of boundary pixels, based on a cost function, composed of color, spatial, contour, and temporal consistency terms. Finally, we execute superpixel splitting, merging, and relabeling to regularize superpixel sizes and reduce incorrect labels. Experiments show that the proposed algorithm outperforms the state-of-the-art conventional algorithms significantly.
AB - A temporal superpixel algorithm based on proximity-weighted patch matching (TS-PPM) is proposed in this work. We develop the proximity-weighted patch matching (PPM), which estimates the motion vector of a superpixel robustly, by considering the patch matching distances of neighboring superpixels as well as the target superpixel. In each frame, we initialize superpixels by transferring the superpixel labels of the previous frame using PPM motion vectors. Then, we update the superpixel labels of boundary pixels, based on a cost function, composed of color, spatial, contour, and temporal consistency terms. Finally, we execute superpixel splitting, merging, and relabeling to regularize superpixel sizes and reduce incorrect labels. Experiments show that the proposed algorithm outperforms the state-of-the-art conventional algorithms significantly.
UR - http://www.scopus.com/inward/record.url?scp=85041902596&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.390
DO - 10.1109/ICCV.2017.390
M3 - Conference contribution
AN - SCOPUS:85041902596
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3630
EP - 3638
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017
Y2 - 22 October 2017 through 29 October 2017
ER -