Visual Tracking by Integrating Fast Ensemble Proposal and Sparse Verification

Sparse representation has been exploited for visual object tracking to yield impressive performance in recent years. However, sparse models in tracking are commonly limited by two intrinsic challenges, i.e., the high computational cost that makes it impractical in real-world applications and few reliable target observations available in dictionary initialization that renders it hard to handle great target dynamics in complicated scenarios. In this paper, we propose a novel object tracking method to address these problems. Our method integrates fast ensemble proposal and sparse verification, and the two complementarily work in the following way: The target proposals are fast generated and filtered to reduce computational load and provide evidence reference for later sparse verification, and the spare model updates its dictionary dynamically with the target observations verified by fused evidences. Extensive experimental results demonstrate that the proposed method handles the aforementioned problems with impressive success and that it outperforms state-of-the-art methods in various challenging scenarios.