Effective Occlusion Handling for Fast Correlation Filter-based Trackers
This work addresses occlusion handling for fast correlation filter-based trackers, which is an incremental improvement in computer vision tracking.
The paper tackled the problem of occlusion-induced multiple peaks and drift in correlation filter-based trackers by proposing a scheme to select filter models based on scenario, using a measurement function and strategy to detect occlusions and update models, along with scale estimation methods. The result showed promising performance on VOT2018 and OTB100 datasets compared to state-of-the-art trackers.
Correlation filter-based trackers heavily suffer from the problem of multiple peaks in their response maps incurred by occlusions. Moreover, the whole tracking pipeline may break down due to the uncertainties brought by shifting among peaks, which will further lead to the degraded correlation filter model. To alleviate the drift problem caused by occlusions, we propose a novel scheme to choose the specific filter model according to different scenarios. Specifically, an effective measurement function is designed to evaluate the quality of filter response. A sophisticated strategy is employed to judge whether occlusions occur, and then decide how to update the filter models. In addition, we take advantage of both log-polar method and pyramid-like approach to estimate the best scale of the target. We evaluate our proposed approach on VOT2018 challenge and OTB100 dataset, whose experimental result shows that the proposed tracker achieves the promising performance compared against the state-of-the-art trackers.