Primary object segmentation in videos based on region augmentation and reduction

Yeong Jun Koh; Chang-Su Kim

doi:10.1109/CVPR.2017.784

Primary object segmentation in videos based on region augmentation and reduction

Yeong Jun Koh
, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

147 Citations (Scopus)

Abstract

A novel algorithm to segment a primary object in a video sequence is proposed in this work. First, we generate candidate regions for the primary object using both color and motion edges. Second, we estimate initial primary object regions, by exploiting the recurrence property of the primary object. Third, we augment the initial regions with missing parts or reducing them by excluding noisy parts repeatedly. This augmentation and reduction process (ARP) identifies the primary object region in each frame. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-Art conventional algorithms on recent benchmark datasets.

Original language	English
Title of host publication	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7417-7425
Number of pages	9
ISBN (Electronic)	9781538604571
DOIs	https://doi.org/10.1109/CVPR.2017.784
Publication status	Published - 2017 Nov 6
Event	30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States Duration: 2017 Jul 21 → 2017 Jul 26

Publication series

Name	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Volume	2017-January

Other

Other	30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Country/Territory	United States
City	Honolulu
Period	17/7/21 → 17/7/26

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2017.784

Cite this

Koh, Y. J., & Kim, C.-S. (2017). Primary object segmentation in videos based on region augmentation and reduction. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 7417-7425). (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.784

Primary object segmentation in videos based on region augmentation and reduction. / Koh, Yeong Jun; Kim, Chang-Su.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 7417-7425 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Koh, YJ & Kim, C-S 2017, Primary object segmentation in videos based on region augmentation and reduction. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 7417-7425, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPR.2017.784

Koh YJ, Kim CS. Primary object segmentation in videos based on region augmentation and reduction. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 7417-7425. (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017). doi: 10.1109/CVPR.2017.784

Koh, Yeong Jun ; Kim, Chang-Su. / Primary object segmentation in videos based on region augmentation and reduction. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 7417-7425 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017).

@inproceedings{afe0f61160fe4418965efaddddc2f40e,

title = "Primary object segmentation in videos based on region augmentation and reduction",

abstract = "A novel algorithm to segment a primary object in a video sequence is proposed in this work. First, we generate candidate regions for the primary object using both color and motion edges. Second, we estimate initial primary object regions, by exploiting the recurrence property of the primary object. Third, we augment the initial regions with missing parts or reducing them by excluding noisy parts repeatedly. This augmentation and reduction process (ARP) identifies the primary object region in each frame. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-Art conventional algorithms on recent benchmark datasets.",

author = "Koh, \{Yeong Jun\} and Chang-Su Kim",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 ; Conference date: 21-07-2017 Through 26-07-2017",

year = "2017",

month = nov,

day = "6",

doi = "10.1109/CVPR.2017.784",

language = "English",

series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7417--7425",

booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",

}

TY - GEN

T1 - Primary object segmentation in videos based on region augmentation and reduction

AU - Koh, Yeong Jun

AU - Kim, Chang-Su

PY - 2017/11/6

Y1 - 2017/11/6

N2 - A novel algorithm to segment a primary object in a video sequence is proposed in this work. First, we generate candidate regions for the primary object using both color and motion edges. Second, we estimate initial primary object regions, by exploiting the recurrence property of the primary object. Third, we augment the initial regions with missing parts or reducing them by excluding noisy parts repeatedly. This augmentation and reduction process (ARP) identifies the primary object region in each frame. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-Art conventional algorithms on recent benchmark datasets.

AB - A novel algorithm to segment a primary object in a video sequence is proposed in this work. First, we generate candidate regions for the primary object using both color and motion edges. Second, we estimate initial primary object regions, by exploiting the recurrence property of the primary object. Third, we augment the initial regions with missing parts or reducing them by excluding noisy parts repeatedly. This augmentation and reduction process (ARP) identifies the primary object region in each frame. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-Art conventional algorithms on recent benchmark datasets.

UR - https://www.scopus.com/pages/publications/85041895818

U2 - 10.1109/CVPR.2017.784

DO - 10.1109/CVPR.2017.784

M3 - Conference contribution

AN - SCOPUS:85041895818

T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

SP - 7417

EP - 7425

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

Y2 - 21 July 2017 through 26 July 2017

ER -

Primary object segmentation in videos based on region augmentation and reduction

Abstract

Publication series

Other

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this