Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 31, Issue 10, Pages 4058-4070Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2020.3045747
Keywords
Drones; Target tracking; Cameras; Object tracking; Visualization; Benchmark testing; Annotations; Single object tracking; UAV; multi-drone; agent sharing network; self-supervised learning
Categories
Funding
- National Key Research and Development Program of China [2018AAA0102402]
- National Natural Science Foundation of China [61732011, 61876127, 61925602]
- Natural Science Foundation of Tianjin [17JCZDJC30800]
- Applied Basic Research Program of Qinghai [2019-ZJ-7017]
Ask authors/readers for more resources
The study introduced a new MDOT dataset and proposed an ASNet to improve the accuracy of multi-drone single object tracking, achieving significant results compared to single-drone tracking in experiments.
Drones equipped with cameras (UAVs) can dynamically track the target in the air from a broader view compared with static cameras or moving sensors over the ground. However, it is still challenging to accurately track the target using a single drone due to several factors such as appearance variations and severe occlusions. To this end, we collect a new Multi-Drone single Object Tracking (MDOT) dataset that consists of 92 groups of video clips with 113, 918 high resolution frames taken by two drones and 63 groups of video clips with 145, 875 high resolution frames taken by three drones. Besides, two evaluation metrics are specially designed for multi-drone single object tracking, i.e., automatic fusion score (AFS) and ideal fusion score (IFS). Moreover, the agent sharing network (ASNet) is proposed by integrating self-supervised template sharing, target re-detection, and view-aware fusion of the target from multiple drones into a unified framework, which can improve the tracking accuracy significantly compared with single drone tracking. Extensive experiments on MDOT show that our ASNet significantly outperforms recent state-of-the-art trackers. The dataset can be found in https://github.com/VisDrone/MultiDrone.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available