Semi-supervised video object segmentation using multiple random walkers

Won Dong Jang, Chang-Su Kim

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

A semi-supervised video object segmentation algorithm using multiple random walkers (MRW) is proposed in this work. We develop an initial probability estimation scheme that minimizes an objective function to roughly separate the foreground from the background. Then, we simulate MRW by employing the foreground and background agents. During the MRW process, we update restart distributions using a hybrid of inference restart rule and interactive restart rule. By performing these processes from the second to the last frames, we obtain a segment track of the target object. Furthermore, we optionally refine the segment track by performing Markov random field optimization. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the SegTrack v2 dataset.

Original languageEnglish
Pages57.1-57.13
DOIs
Publication statusPublished - 2016 Jan 1
Event27th British Machine Vision Conference, BMVC 2016 - York, United Kingdom
Duration: 2016 Sep 192016 Sep 22

Other

Other27th British Machine Vision Conference, BMVC 2016
CountryUnited Kingdom
CityYork
Period16/9/1916/9/22

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Jang, W. D., & Kim, C-S. (2016). Semi-supervised video object segmentation using multiple random walkers. 57.1-57.13. Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom. https://doi.org/10.5244/C.30.57

Semi-supervised video object segmentation using multiple random walkers. / Jang, Won Dong; Kim, Chang-Su.

2016. 57.1-57.13 Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom.

Research output: Contribution to conferencePaper

Jang, WD & Kim, C-S 2016, 'Semi-supervised video object segmentation using multiple random walkers', Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom, 16/9/19 - 16/9/22 pp. 57.1-57.13. https://doi.org/10.5244/C.30.57
Jang WD, Kim C-S. Semi-supervised video object segmentation using multiple random walkers. 2016. Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom. https://doi.org/10.5244/C.30.57
Jang, Won Dong ; Kim, Chang-Su. / Semi-supervised video object segmentation using multiple random walkers. Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom.
@conference{e960d8e9c9274dbdbe579f794e48e97f,
title = "Semi-supervised video object segmentation using multiple random walkers",
abstract = "A semi-supervised video object segmentation algorithm using multiple random walkers (MRW) is proposed in this work. We develop an initial probability estimation scheme that minimizes an objective function to roughly separate the foreground from the background. Then, we simulate MRW by employing the foreground and background agents. During the MRW process, we update restart distributions using a hybrid of inference restart rule and interactive restart rule. By performing these processes from the second to the last frames, we obtain a segment track of the target object. Furthermore, we optionally refine the segment track by performing Markov random field optimization. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the SegTrack v2 dataset.",
author = "Jang, {Won Dong} and Chang-Su Kim",
year = "2016",
month = "1",
day = "1",
doi = "10.5244/C.30.57",
language = "English",
pages = "57.1--57.13",
note = "27th British Machine Vision Conference, BMVC 2016 ; Conference date: 19-09-2016 Through 22-09-2016",

}

TY - CONF

T1 - Semi-supervised video object segmentation using multiple random walkers

AU - Jang, Won Dong

AU - Kim, Chang-Su

PY - 2016/1/1

Y1 - 2016/1/1

N2 - A semi-supervised video object segmentation algorithm using multiple random walkers (MRW) is proposed in this work. We develop an initial probability estimation scheme that minimizes an objective function to roughly separate the foreground from the background. Then, we simulate MRW by employing the foreground and background agents. During the MRW process, we update restart distributions using a hybrid of inference restart rule and interactive restart rule. By performing these processes from the second to the last frames, we obtain a segment track of the target object. Furthermore, we optionally refine the segment track by performing Markov random field optimization. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the SegTrack v2 dataset.

AB - A semi-supervised video object segmentation algorithm using multiple random walkers (MRW) is proposed in this work. We develop an initial probability estimation scheme that minimizes an objective function to roughly separate the foreground from the background. Then, we simulate MRW by employing the foreground and background agents. During the MRW process, we update restart distributions using a hybrid of inference restart rule and interactive restart rule. By performing these processes from the second to the last frames, we obtain a segment track of the target object. Furthermore, we optionally refine the segment track by performing Markov random field optimization. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the SegTrack v2 dataset.

UR - http://www.scopus.com/inward/record.url?scp=85041901830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041901830&partnerID=8YFLogxK

U2 - 10.5244/C.30.57

DO - 10.5244/C.30.57

M3 - Paper

AN - SCOPUS:85041901830

SP - 57.1-57.13

ER -