Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 3630-3638 |
Number of pages | 9 |
Volume | 2017-October |
ISBN (Electronic) | 9781538610329 |
DOIs | |
Publication status | Published - 2017 Dec 22 |
Event | 16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy Duration: 2017 Oct 22 → 2017 Oct 29 |
Other
Other | 16th IEEE International Conference on Computer Vision, ICCV 2017 |
---|---|
Country | Italy |
City | Venice |
Period | 17/10/22 → 17/10/29 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
Temporal Superpixels Based on Proximity-Weighted Patch Matching. / Lee, Se Ho; Jang, Won Dong; Kim, Chang-Su.
Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Vol. 2017-October Institute of Electrical and Electronics Engineers Inc., 2017. p. 3630-3638 8237652.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Temporal Superpixels Based on Proximity-Weighted Patch Matching
AU - Lee, Se Ho
AU - Jang, Won Dong
AU - Kim, Chang-Su
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
UR - http://www.scopus.com/inward/citedby.url?scp=85041902596&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.390
DO - 10.1109/ICCV.2017.390
M3 - Conference contribution
AN - SCOPUS:85041902596
VL - 2017-October
SP - 3630
EP - 3638
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -