Currently, the correlation filter is widely used in visual tracking because of its effectiveness and efficiency. Toadapt the representation to changing target appearances, a linear interpolation is used to update tracking modelsaccording to a manually designed learning rate. However, The limitation of manually tricks make methods onlyapply to some special scenes because the threshold parameters are sensitive to different response maps in complexscenes. In this paper, to overcome this problem, an adaptive increment correlation filter based tracker is proposed.Different from traditional linear interpolation depending on a manual learning rate, the increment is learned bylinear regression based on the history tracking model and the current training samples. Experimentally, we showthat our algorithm can outperform state-of-the-art keypoint-based trackers.
展开▼
