Robust object segmentation using graph cut with object and background seed estimation

Jung Ho Ahn, Kil Cheon Kim, Hyeran Byun

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

9 Citations (Scopus)

Abstract

In this paper we propose a new robust way of extracting accurate human silhouettes indoors with an active stereo camera. We first infer the parts of object and background areas of high confidence by fusing color, stereo matching information and image segmentation methods. Then the inferred areas(seeds) are incorporated in a graph cut. The experimental results were presented with image sequences taken with pan-tilt stereo camera. Our proposed algorithms were evaluated with respect to the ground truth data. We proved that our algorithms can outperform other methods that are based on either color/contrast or stereo/contrast principles alone.

Original languageEnglish
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages361-364
Number of pages4
DOIs
Publication statusPublished - 2006 Dec 1
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: 2006 Aug 202006 Aug 24

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2
ISSN (Print)1051-4651

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period06/8/2006/8/24

Fingerprint

Seed
Cameras
Color
Image segmentation

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Ahn, J. H., Kim, K. C., & Byun, H. (2006). Robust object segmentation using graph cut with object and background seed estimation. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006 (pp. 361-364). [1699220] (Proceedings - International Conference on Pattern Recognition; Vol. 2). https://doi.org/10.1109/ICPR.2006.1012
Ahn, Jung Ho ; Kim, Kil Cheon ; Byun, Hyeran. / Robust object segmentation using graph cut with object and background seed estimation. Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. pp. 361-364 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{94abd9df3d8f463ab05ebd7b4401fe8e,
title = "Robust object segmentation using graph cut with object and background seed estimation",
abstract = "In this paper we propose a new robust way of extracting accurate human silhouettes indoors with an active stereo camera. We first infer the parts of object and background areas of high confidence by fusing color, stereo matching information and image segmentation methods. Then the inferred areas(seeds) are incorporated in a graph cut. The experimental results were presented with image sequences taken with pan-tilt stereo camera. Our proposed algorithms were evaluated with respect to the ground truth data. We proved that our algorithms can outperform other methods that are based on either color/contrast or stereo/contrast principles alone.",
author = "Ahn, {Jung Ho} and Kim, {Kil Cheon} and Hyeran Byun",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICPR.2006.1012",
language = "English",
isbn = "0769525210",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "361--364",
booktitle = "Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006",

}

Ahn, JH, Kim, KC & Byun, H 2006, Robust object segmentation using graph cut with object and background seed estimation. in Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006., 1699220, Proceedings - International Conference on Pattern Recognition, vol. 2, pp. 361-364, 18th International Conference on Pattern Recognition, ICPR 2006, Hong Kong, China, 06/8/20. https://doi.org/10.1109/ICPR.2006.1012

Robust object segmentation using graph cut with object and background seed estimation. / Ahn, Jung Ho; Kim, Kil Cheon; Byun, Hyeran.

Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. p. 361-364 1699220 (Proceedings - International Conference on Pattern Recognition; Vol. 2).

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

TY - GEN

T1 - Robust object segmentation using graph cut with object and background seed estimation

AU - Ahn, Jung Ho

AU - Kim, Kil Cheon

AU - Byun, Hyeran

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this paper we propose a new robust way of extracting accurate human silhouettes indoors with an active stereo camera. We first infer the parts of object and background areas of high confidence by fusing color, stereo matching information and image segmentation methods. Then the inferred areas(seeds) are incorporated in a graph cut. The experimental results were presented with image sequences taken with pan-tilt stereo camera. Our proposed algorithms were evaluated with respect to the ground truth data. We proved that our algorithms can outperform other methods that are based on either color/contrast or stereo/contrast principles alone.

AB - In this paper we propose a new robust way of extracting accurate human silhouettes indoors with an active stereo camera. We first infer the parts of object and background areas of high confidence by fusing color, stereo matching information and image segmentation methods. Then the inferred areas(seeds) are incorporated in a graph cut. The experimental results were presented with image sequences taken with pan-tilt stereo camera. Our proposed algorithms were evaluated with respect to the ground truth data. We proved that our algorithms can outperform other methods that are based on either color/contrast or stereo/contrast principles alone.

UR - http://www.scopus.com/inward/record.url?scp=34047223135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047223135&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.1012

DO - 10.1109/ICPR.2006.1012

M3 - Conference contribution

AN - SCOPUS:34047223135

SN - 0769525210

SN - 9780769525211

T3 - Proceedings - International Conference on Pattern Recognition

SP - 361

EP - 364

BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006

ER -

Ahn JH, Kim KC, Byun H. Robust object segmentation using graph cut with object and background seed estimation. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. p. 361-364. 1699220. (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2006.1012