Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles

Full metadata record
DC Field Value Language
dc.contributor.authorLee, Kyuewang-
dc.contributor.authorChang, Hyung Jin-
dc.contributor.authorChoi, Jongwon-
dc.contributor.authorHeo, Byeongho-
dc.contributor.authorLeonardis, Ales-
dc.contributor.authorChoi, Jin Young-
dc.date.accessioned2021-06-18T07:14:15Z-
dc.date.available2021-06-18T07:14:15Z-
dc.date.issued2021-05-
dc.identifier.issn0932-8092-
dc.identifier.issn1432-1769-
dc.identifier.urihttps://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44120-
dc.description.abstractTo tackle problems arising from unexpected camera motions in unmanned aerial vehicles (UAVs), we propose a three-mode ensemble tracker where each mode specializes in distinctive situations. The proposed ensemble tracker is composed of appearance-based tracking mode, homography-based tracking mode, and momentum-based tracking mode. The appearance-based tracking mode tracks a moving object well when the UAV is nearly stopped, whereas the homography-based tracking mode shows good tracking performance under smooth UAV or object motion. The momentum-based tracking mode copes with large or abrupt motion of either the UAV or the object. We evaluate the proposed tracking scheme on a widely-used UAV123 benchmark dataset. The proposed motion-aware ensemble shows a 5.3% improvement in average precision compared to the baseline correlation filter tracker, which effectively employs deep features while achieving a tracking speed of at least 80fps in our experimental settings. In addition, the proposed method outperforms existing real-time correlation filter trackers.-
dc.language영어-
dc.language.isoENG-
dc.publisherSPRINGER-
dc.titleMotion-aware ensemble of three-mode trackers for unmanned aerial vehicles-
dc.typeArticle-
dc.identifier.doi10.1007/s00138-021-01181-x-
dc.identifier.bibliographicCitationMACHINE VISION AND APPLICATIONS, v.32, no.3-
dc.description.isOpenAccessN-
dc.identifier.wosid000625832500001-
dc.identifier.scopusid2-s2.0-85102116558-
dc.citation.number3-
dc.citation.titleMACHINE VISION AND APPLICATIONS-
dc.citation.volume32-
dc.type.docTypeArticle-
dc.publisher.location미국-
dc.subject.keywordAuthorVisual tracking-
dc.subject.keywordAuthorCorrelation filter tracking-
dc.subject.keywordAuthorMotion-aware ensemble method-
dc.subject.keywordAuthorUnmanned surveillance vehicles-
dc.subject.keywordPlusTRACKING-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalWebOfScienceCategoryComputer Science, Cybernetics-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Choi, Jong Won photo

Choi, Jong Won
첨단영상대학원 (영상학과)
Read more

Altmetrics

Total Views & Downloads

BROWSE