Temporal Superpixels Based on Proximity-Weighted Patch Matching

Se Ho Lee, Won Dong Jang, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

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 languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3630-3638
Number of pages9
Volume2017-October
ISBN (Electronic)9781538610329
DOIs
Publication statusPublished - 2017 Dec 22
Event16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
Duration: 2017 Oct 222017 Oct 29

Other

Other16th IEEE International Conference on Computer Vision, ICCV 2017
CountryItaly
CityVenice
Period17/10/2217/10/29

Fingerprint

Labels
Merging
Cost functions
Pixels
Color
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Lee, S. H., Jang, W. D., & Kim, C-S. (2017). Temporal Superpixels Based on Proximity-Weighted Patch Matching. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 (Vol. 2017-October, pp. 3630-3638). [8237652] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2017.390

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 proceedingConference contribution

Lee, SH, Jang, WD & Kim, C-S 2017, Temporal Superpixels Based on Proximity-Weighted Patch Matching. in Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. vol. 2017-October, 8237652, Institute of Electrical and Electronics Engineers Inc., pp. 3630-3638, 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 17/10/22. https://doi.org/10.1109/ICCV.2017.390
Lee SH, Jang WD, Kim C-S. Temporal Superpixels Based on Proximity-Weighted Patch Matching. In 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 https://doi.org/10.1109/ICCV.2017.390
Lee, Se Ho ; Jang, Won Dong ; Kim, Chang-Su. / Temporal Superpixels Based on Proximity-Weighted Patch Matching. Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Vol. 2017-October Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3630-3638
@inproceedings{dc783cd1d831413e93b9dfb97109acd3,
title = "Temporal Superpixels Based on Proximity-Weighted Patch Matching",
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.",
author = "Lee, {Se Ho} and Jang, {Won Dong} and Chang-Su Kim",
year = "2017",
month = "12",
day = "22",
doi = "10.1109/ICCV.2017.390",
language = "English",
volume = "2017-October",
pages = "3630--3638",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

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 -