Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles
- Authors
- Lee, Kyuewang; Chang, Hyung Jin; Choi, Jongwon; Heo, Byeongho; Leonardis, Ales; Choi, Jin Young
- Issue Date
- May-2021
- Publisher
- SPRINGER
- Keywords
- Visual tracking; Correlation filter tracking; Motion-aware ensemble method; Unmanned surveillance vehicles
- Citation
- MACHINE VISION AND APPLICATIONS, v.32, no.3
- Journal Title
- MACHINE VISION AND APPLICATIONS
- Volume
- 32
- Number
- 3
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44120
- DOI
- 10.1007/s00138-021-01181-x
- ISSN
- 0932-8092
1432-1769
- 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.
- 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](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44120)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.