On Detecting and Handling target occlusions in Correlation-filter-based 2D tracking

This paper focuses on the application of 2D visual object tracking in Unmanned Aerial Vehicles (UAV) for the coverage of live outdoor events, by filming moving targets (e.g., athletes, boats, cars etc.). In this application scenario, a 2D target tracker visually assists the UAV pilot (or cameraman) to maintain proper target framing, or it is employed for autonomous UAV operation. It should be expected that in such scenarios, the 2D tracker may fail due to target occlusions, illumination variations, fast 3D target motion, etc., thus, the 2D tracker should be able to recover from such situations. The proposed long-term 2D tracking algorithm solves exactly this problem, by detecting occlusions from the 2D tracker responses. Moreover, according to the immensity of the occlusion, the tracker may stop updating the tracker model or try to re-detect the target in a broader frame region. Experimental results indicate that our proposed tracking algorithm outperforms state-of-the art correlation filter trackers in UAV orientated visual tracking benchmarks, as well as in realistic UAV cinematography applications.