Efficient Siamese Network for UAV Tracking

Abstract

In this work, we propose an efficient Siamese-based tracker (ESTrack) for aerial visual object tracking using dual global correlation and accurate center localization. The dual correlation module embeds task-specific global similarity information for target classification and state estimation. The center localization highlights the classification score where the target exists, which improves the accuracy of the classification and reduces complex hyperparameter tuning. Extensive experiments on five UAV benchmarks show that our ESTrack-50 performs favorably against many state-of-the-art Siamese- based trackers with a speed of 110 fps. Meanwhile, ESTrack-18 and ESTrack-AO achieve 180 fps with comparable performance to most UAV-based trackers.