Contour-constrained superpixels for image and video processing

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

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

2 Citations (Scopus)

Abstract

A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour constraint. Furthermore, we extend the CCS algorithm to generate temporal superpixels for video processing. We initialize superpixel labels in each frame by transferring those in the previous frame and refine the labels to make superpixels temporally consistent as well as compatible with object contours. Experimental results demonstrate that the proposed algorithm provides better performance than the state-of-the-art superpixel methods.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5863-5871
Number of pages9
Volume2017-January
ISBN (Electronic)9781538604571
DOIs
Publication statusPublished - 2017 Nov 6
Event30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Labels
Processing
Pattern matching
Pixels

ASJC Scopus subject areas

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Lee, S. H., Jang, W. D., & Kim, C-S. (2017). Contour-constrained superpixels for image and video processing. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (Vol. 2017-January, pp. 5863-5871). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.621

Contour-constrained superpixels for image and video processing. / Lee, Se Ho; Jang, Won Dong; Kim, Chang-Su.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 5863-5871.

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

Lee, SH, Jang, WD & Kim, C-S 2017, Contour-constrained superpixels for image and video processing. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 5863-5871, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPR.2017.621
Lee SH, Jang WD, Kim C-S. Contour-constrained superpixels for image and video processing. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5863-5871 https://doi.org/10.1109/CVPR.2017.621
Lee, Se Ho ; Jang, Won Dong ; Kim, Chang-Su. / Contour-constrained superpixels for image and video processing. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5863-5871
@inproceedings{4493b35847d94d50a9581c9830d71b68,
title = "Contour-constrained superpixels for image and video processing",
abstract = "A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour constraint. Furthermore, we extend the CCS algorithm to generate temporal superpixels for video processing. We initialize superpixel labels in each frame by transferring those in the previous frame and refine the labels to make superpixels temporally consistent as well as compatible with object contours. Experimental results demonstrate that the proposed algorithm provides better performance than the state-of-the-art superpixel methods.",
author = "Lee, {Se Ho} and Jang, {Won Dong} and Chang-Su Kim",
year = "2017",
month = "11",
day = "6",
doi = "10.1109/CVPR.2017.621",
language = "English",
volume = "2017-January",
pages = "5863--5871",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Contour-constrained superpixels for image and video processing

AU - Lee, Se Ho

AU - Jang, Won Dong

AU - Kim, Chang-Su

PY - 2017/11/6

Y1 - 2017/11/6

N2 - A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour constraint. Furthermore, we extend the CCS algorithm to generate temporal superpixels for video processing. We initialize superpixel labels in each frame by transferring those in the previous frame and refine the labels to make superpixels temporally consistent as well as compatible with object contours. Experimental results demonstrate that the proposed algorithm provides better performance than the state-of-the-art superpixel methods.

AB - A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour constraint. Furthermore, we extend the CCS algorithm to generate temporal superpixels for video processing. We initialize superpixel labels in each frame by transferring those in the previous frame and refine the labels to make superpixels temporally consistent as well as compatible with object contours. Experimental results demonstrate that the proposed algorithm provides better performance than the state-of-the-art superpixel methods.

UR - http://www.scopus.com/inward/record.url?scp=85041894131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041894131&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.621

DO - 10.1109/CVPR.2017.621

M3 - Conference contribution

AN - SCOPUS:85041894131

VL - 2017-January

SP - 5863

EP - 5871

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -