PGT: Proposal-guided object tracking

Han Ul Kim, Chang-Su Kim

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

Abstract

We propose a robust visual tracking system, which refines initial estimates of a base tracker by employing object proposal techniques. First, we decompose the base tracker into three building blocks: Representation method, appearance model, and model update strategy. We then design each building block by adopting and improving ideas from recent successful trackers. Second, we propose the proposal-guided tracking (PGT) algorithm. Given proposals generated by an edge-based object proposal technique, we select only the proposals that can improve the result of the base tracker using several cues. Then, we discriminate target proposals from non-target ones, based on the nearest neighbor classification using the target and background models. Finally, we replace the result of the base tracker with the best target proposal. Experimental results demonstrate that proposed PGT algorithm provides excellent results on a visual tracking benchmark.

Original languageEnglish
Title of host publicationProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1762-1767
Number of pages6
Volume2018-February
ISBN (Electronic)9781538615423
DOIs
Publication statusPublished - 2018 Feb 5
Event9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
Duration: 2017 Dec 122017 Dec 15

Other

Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
CountryMalaysia
CityKuala Lumpur
Period17/12/1217/12/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Information Systems
  • Signal Processing

Cite this

Kim, H. U., & Kim, C-S. (2018). PGT: Proposal-guided object tracking. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 (Vol. 2018-February, pp. 1762-1767). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2017.8282318

PGT : Proposal-guided object tracking. / Kim, Han Ul; Kim, Chang-Su.

Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February Institute of Electrical and Electronics Engineers Inc., 2018. p. 1762-1767.

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

Kim, HU & Kim, C-S 2018, PGT: Proposal-guided object tracking. in Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. vol. 2018-February, Institute of Electrical and Electronics Engineers Inc., pp. 1762-1767, 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, 17/12/12. https://doi.org/10.1109/APSIPA.2017.8282318
Kim HU, Kim C-S. PGT: Proposal-guided object tracking. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1762-1767 https://doi.org/10.1109/APSIPA.2017.8282318
Kim, Han Ul ; Kim, Chang-Su. / PGT : Proposal-guided object tracking. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Vol. 2018-February Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1762-1767
@inproceedings{42f68bed27c44ef1a364223508148a56,
title = "PGT: Proposal-guided object tracking",
abstract = "We propose a robust visual tracking system, which refines initial estimates of a base tracker by employing object proposal techniques. First, we decompose the base tracker into three building blocks: Representation method, appearance model, and model update strategy. We then design each building block by adopting and improving ideas from recent successful trackers. Second, we propose the proposal-guided tracking (PGT) algorithm. Given proposals generated by an edge-based object proposal technique, we select only the proposals that can improve the result of the base tracker using several cues. Then, we discriminate target proposals from non-target ones, based on the nearest neighbor classification using the target and background models. Finally, we replace the result of the base tracker with the best target proposal. Experimental results demonstrate that proposed PGT algorithm provides excellent results on a visual tracking benchmark.",
author = "Kim, {Han Ul} and Chang-Su Kim",
year = "2018",
month = "2",
day = "5",
doi = "10.1109/APSIPA.2017.8282318",
language = "English",
volume = "2018-February",
pages = "1762--1767",
booktitle = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - PGT

T2 - Proposal-guided object tracking

AU - Kim, Han Ul

AU - Kim, Chang-Su

PY - 2018/2/5

Y1 - 2018/2/5

N2 - We propose a robust visual tracking system, which refines initial estimates of a base tracker by employing object proposal techniques. First, we decompose the base tracker into three building blocks: Representation method, appearance model, and model update strategy. We then design each building block by adopting and improving ideas from recent successful trackers. Second, we propose the proposal-guided tracking (PGT) algorithm. Given proposals generated by an edge-based object proposal technique, we select only the proposals that can improve the result of the base tracker using several cues. Then, we discriminate target proposals from non-target ones, based on the nearest neighbor classification using the target and background models. Finally, we replace the result of the base tracker with the best target proposal. Experimental results demonstrate that proposed PGT algorithm provides excellent results on a visual tracking benchmark.

AB - We propose a robust visual tracking system, which refines initial estimates of a base tracker by employing object proposal techniques. First, we decompose the base tracker into three building blocks: Representation method, appearance model, and model update strategy. We then design each building block by adopting and improving ideas from recent successful trackers. Second, we propose the proposal-guided tracking (PGT) algorithm. Given proposals generated by an edge-based object proposal technique, we select only the proposals that can improve the result of the base tracker using several cues. Then, we discriminate target proposals from non-target ones, based on the nearest neighbor classification using the target and background models. Finally, we replace the result of the base tracker with the best target proposal. Experimental results demonstrate that proposed PGT algorithm provides excellent results on a visual tracking benchmark.

UR - http://www.scopus.com/inward/record.url?scp=85050464181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050464181&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2017.8282318

DO - 10.1109/APSIPA.2017.8282318

M3 - Conference contribution

AN - SCOPUS:85050464181

VL - 2018-February

SP - 1762

EP - 1767

BT - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -