Abstract
Correlation filter (CF) is widely used in unmanned aerial vehicle (UAV) tracking because of its efficient performance. However, due to the existence of edge effects, CF will be confused so that the peak of the response is no longer obvious, resulting in tracking drift and template degradation, thereby degrading CF performance. To handle the problem, we propose a new CF for this problem. First, we introduce a response-weighted background residual term to make CF learn the background in a targeted manner according to the strength of the response. Secondly, a history filter model is constructed and a spatio-temporal regularization term is introduced to improve the robustness of CF. Finally, we conduct experiments on two challenging UAV benchmarks, DTB70 and UAV123_10fps. The results show that our tracker achieves state-of-the-art performance compared with 15 other SOTA trackers, and can run at 58 FPS on a single CPU, meeting the needs of UAV real-time tracking.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have