Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles
| Autor: | Hyung Jin Chang, Byeongho Heo, Ales Leonardis, Jin-Young Choi, Kyuewang Lee, Jongwon Choi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
010504 meteorology & atmospheric sciences
business.industry Computer science BitTorrent tracker ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Mode (statistics) 02 engineering and technology Object (computer science) Tracking (particle physics) 01 natural sciences Motion (physics) Computer Science Applications Hardware and Architecture Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Computer vision Computer Vision and Pattern Recognition Artificial intelligence business Software 0105 earth and related environmental sciences Homography (computer vision) |
| Zdroj: | Machine Vision and Applications. 32 |
| ISSN: | 1432-1769 0932-8092 |
| DOI: | 10.1007/s00138-021-01181-x |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink