Temporal Context and Environment-Aware Correlation Filter for UAV Object Tracking
Bing He, Fasheng Wang, Xing Wang, Haojie Li, Fuming Sun, Hui Zhou
Abstract
In this article, we propose a temporal context and environment-aware correlation filter (CF) for unmanned aerial vehicle (UAV) object tracking. First, we exploit environmental residuals between two adjacent frames to enhance the discrimination ability and insensitivity of the tracker in complex tracking environments. Second, the historical filter model is utilized to build a temporal regularization term to prevent the filter degradation induced by the severe object appearance variations that affect the tracking performance while suppressing the boundary effect. Finally, we propose to use the predicted object position in the next frame to efficiently sample a predicted context patch for constructing the prediction context-aware regularization term, improving the ability of the tracker to cope with interference from unknown environment changes. Extensive experimental results on four challenging benchmarks show that our tracker achieves state-of-the-art (SOTA) performance compared with other advanced CF-based UAV trackers with real-time tracking speed (47 frames/s) on a single CPU.