Publications
Detailed Information
Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Kyuewang | - |
dc.contributor.author | Chang, Hyung Jin | - |
dc.contributor.author | Choi, Jongwon | - |
dc.contributor.author | Heo, Byeongho | - |
dc.contributor.author | Leonardis, Ales | - |
dc.contributor.author | Choi, Jin Young | - |
dc.date.accessioned | 2023-11-24T04:39:10Z | - |
dc.date.available | 2023-11-24T04:39:10Z | - |
dc.date.created | 2021-05-21 | - |
dc.date.created | 2021-05-21 | - |
dc.date.issued | 2021-05 | - |
dc.identifier.citation | Machine Vision and Applications, Vol.32 No.3, p. 54 | - |
dc.identifier.issn | 0932-8092 | - |
dc.identifier.uri | https://hdl.handle.net/10371/197511 | - |
dc.description.abstract | To 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.language | 영어 | - |
dc.publisher | Springer Verlag | - |
dc.title | Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s00138-021-01181-x | - |
dc.citation.journaltitle | Machine Vision and Applications | - |
dc.identifier.wosid | 000625832500001 | - |
dc.identifier.scopusid | 2-s2.0-85102116558 | - |
dc.citation.number | 3 | - |
dc.citation.startpage | 54 | - |
dc.citation.volume | 32 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Choi, Jin Young | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordPlus | TRACKING | - |
dc.subject.keywordAuthor | Visual tracking | - |
dc.subject.keywordAuthor | Correlation filter tracking | - |
dc.subject.keywordAuthor | Motion-aware ensemble method | - |
dc.subject.keywordAuthor | Unmanned surveillance vehicles | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.