Effective Occlusion Handling for Fast Correlation Filter-based Trackers

TL;DR

This paper introduces a novel occlusion handling scheme for correlation filter-based trackers, improving their robustness by evaluating response quality and adaptively updating models, with promising results on standard benchmarks.

Contribution

It proposes a new measurement and decision strategy for occlusion detection and filter update, enhancing tracker stability under occlusions.

Findings

Achieves improved performance on VOT2018 and OTB100 datasets.

Effectively detects occlusions and adapts filter updates.

Outperforms several state-of-the-art trackers.

Abstract

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.