Correlation Filters for UAV Online Tracking Based on Complementary Appearance Model and Reversibility Reasoning

Correlation filter (CF)-based approaches have been widely applied in online object tracking tasks for unmanned aerial vehicles (UAVs) due to their high computational efficiency and low memory consumption. One of the key steps is to perform correlation operations between the appearance model (AM) and the filter. However, as the difficulty in controlling the learning rate of the AM, most existing trackers are prone to causing degradation. In this paper, we propose a novel complementary AM (CAM) consisting of a primary model (PM) and a secondary model (SM). Specifically, the learning rates of the PM and SM are approximately complementary, allowing the CAM to consider both past and current information. Moreover, in order to take full advantage of historical information, a CAM-based reversibility reasoning approach is proposed for CF training. It can robustly handle the variations in object appearance. Then we further create a deep tracker by fusing convolutional features which demonstrates more outstanding performance. We also embed the CAM into two advanced trackers to validate the scalability of the CAM. Comprehensive experiments on six challenging UAV tracking benchmarks have indicated the superiority of our method compared to other 36 state-of-the-art CPU- and GPU-based trackers, with a speed of 45 FPS running on a cheap CPU.