Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals

Yeong Jun Koh, Chang-Su Kim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms.

Original languageEnglish
Article number8002643
Pages (from-to)5203-5216
Number of pages14
JournalIEEE Transactions on Image Processing
Volume26
Issue number11
DOIs
Publication statusPublished - 2017 Nov 1

Fingerprint

Recurrence
Merging
Color

Keywords

  • object proposal
  • Primary object discovery
  • recurrence property
  • video object segmentation

ASJC Scopus subject areas

  • Software
  • Medicine(all)
  • Computer Graphics and Computer-Aided Design

Cite this

Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals. / Koh, Yeong Jun; Kim, Chang-Su.

In: IEEE Transactions on Image Processing, Vol. 26, No. 11, 8002643, 01.11.2017, p. 5203-5216.

Research output: Contribution to journalArticle

@article{8fb3a4ec19954620b20696a7b4f226e7,
title = "Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals",
abstract = "A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms.",
keywords = "object proposal, Primary object discovery, recurrence property, video object segmentation",
author = "Koh, {Yeong Jun} and Chang-Su Kim",
year = "2017",
month = "11",
day = "1",
doi = "10.1109/TIP.2017.2736418",
language = "English",
volume = "26",
pages = "5203--5216",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals

AU - Koh, Yeong Jun

AU - Kim, Chang-Su

PY - 2017/11/1

Y1 - 2017/11/1

N2 - A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms.

AB - A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms.

KW - object proposal

KW - Primary object discovery

KW - recurrence property

KW - video object segmentation

UR - http://www.scopus.com/inward/record.url?scp=85029009755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029009755&partnerID=8YFLogxK

U2 - 10.1109/TIP.2017.2736418

DO - 10.1109/TIP.2017.2736418

M3 - Article

C2 - 28792896

AN - SCOPUS:85029009755

VL - 26

SP - 5203

EP - 5216

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 11

M1 - 8002643

ER -