POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models

Yeong Jun Koh; Won Dong Jang; Chang-Su Kim

doi:10.1109/CVPR.2016.121

POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models

Yeong Jun Koh, Won Dong Jang, Chang-Su Kim

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

21 Citations (Scopus)

Abstract

A primary object discovery (POD) algorithm for a video sequence is proposed in this work, which is capable of discovering a primary object, as well as identifying noisy frames that do not contain the object. First, we generate object proposals for each frame. Then, we bisect each proposal into foreground and background regions, and extract features from each region. By superposing the foreground and background features, we build the object recurrence model, the background model, and the primary object model. We develop an iterative scheme to refine each model evolutionarily using the information in the other models. Finally, using the evolved primary object model, we select candidate proposals and locate the bounding box of a primary object by merging the proposals selectively. Experimental results on a challenging dataset demonstrate that the proposed POD algorithm extracts primary objects accurately and robustly.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	1068-1076
Number of pages	9
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.121
Publication status	Published - 2016 Dec 9
Event	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: 2016 Jun 26 → 2016 Jul 1

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2016-December
ISSN (Print)	1063-6919

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/Territory	United States
City	Las Vegas
Period	16/6/26 → 16/7/1

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2015R1A2A1A10055037).

Publisher Copyright:
© 2016 IEEE.

Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2016.121

Cite this

Koh, Y. J., Jang, W. D., & Kim, C.-S. (2016). POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 1068-1076). Article 7780490 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.121

POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models. / Koh, Yeong Jun; Jang, Won Dong; Kim, Chang-Su.
Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1068-1076 7780490 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

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

Koh, YJ, Jang, WD & Kim, C-S 2016, POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780490, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 1068-1076, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.121

Koh YJ, Jang WD, Kim CS. POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 1068-1076. 7780490. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2016.121

Koh, Yeong Jun ; Jang, Won Dong ; Kim, Chang-Su. / POD : Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. pp. 1068-1076 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

@inproceedings{9a4a4b8dbecc42159f4f2409d7a68ed5,

title = "POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models",

abstract = "A primary object discovery (POD) algorithm for a video sequence is proposed in this work, which is capable of discovering a primary object, as well as identifying noisy frames that do not contain the object. First, we generate object proposals for each frame. Then, we bisect each proposal into foreground and background regions, and extract features from each region. By superposing the foreground and background features, we build the object recurrence model, the background model, and the primary object model. We develop an iterative scheme to refine each model evolutionarily using the information in the other models. Finally, using the evolved primary object model, we select candidate proposals and locate the bounding box of a primary object by merging the proposals selectively. Experimental results on a challenging dataset demonstrate that the proposed POD algorithm extracts primary objects accurately and robustly.",

author = "Koh, {Yeong Jun} and Jang, {Won Dong} and Chang-Su Kim",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2015R1A2A1A10055037). Publisher Copyright: {\textcopyright} 2016 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/CVPR.2016.121",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "1068--1076",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",

}

TY - GEN

T1 - POD

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

AU - Koh, Yeong Jun

AU - Jang, Won Dong

AU - Kim, Chang-Su

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2015R1A2A1A10055037). Publisher Copyright: © 2016 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.

PY - 2016/12/9

Y1 - 2016/12/9

N2 - A primary object discovery (POD) algorithm for a video sequence is proposed in this work, which is capable of discovering a primary object, as well as identifying noisy frames that do not contain the object. First, we generate object proposals for each frame. Then, we bisect each proposal into foreground and background regions, and extract features from each region. By superposing the foreground and background features, we build the object recurrence model, the background model, and the primary object model. We develop an iterative scheme to refine each model evolutionarily using the information in the other models. Finally, using the evolved primary object model, we select candidate proposals and locate the bounding box of a primary object by merging the proposals selectively. Experimental results on a challenging dataset demonstrate that the proposed POD algorithm extracts primary objects accurately and robustly.

AB - A primary object discovery (POD) algorithm for a video sequence is proposed in this work, which is capable of discovering a primary object, as well as identifying noisy frames that do not contain the object. First, we generate object proposals for each frame. Then, we bisect each proposal into foreground and background regions, and extract features from each region. By superposing the foreground and background features, we build the object recurrence model, the background model, and the primary object model. We develop an iterative scheme to refine each model evolutionarily using the information in the other models. Finally, using the evolved primary object model, we select candidate proposals and locate the bounding box of a primary object by merging the proposals selectively. Experimental results on a challenging dataset demonstrate that the proposed POD algorithm extracts primary objects accurately and robustly.

UR - http://www.scopus.com/inward/record.url?scp=84986269237&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986269237&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.121

DO - 10.1109/CVPR.2016.121

M3 - Conference contribution

AN - SCOPUS:84986269237

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1068

EP - 1076

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

Y2 - 26 June 2016 through 1 July 2016

ER -

POD: Discovering primary objects in videos based on evolutionary refinement of object recurrence, background, and primary object models

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this