State-aware Anti-drift Robust Correlation Tracking

TL;DR

This paper introduces a state-aware anti-drift correlation tracker that jointly models discrimination and reliability, incorporating global context and reliable masks to improve robustness against target appearance variations and distractions.

Contribution

The paper proposes a novel tracker that combines discrimination and reliability modeling with global context and color-based masks, enhancing anti-drift capabilities in visual tracking.

Findings

Outperforms state-of-the-art methods on OTB-100 dataset

Effective in handling external distractions and appearance changes

Demonstrates robustness with both hand-crafted and CNN features

Abstract

Correlation filter (CF) based trackers have aroused increasing attentions in visual tracking field due to the superior performance on several datasets while maintaining high running speed. For each frame, an ideal filter is trained in order to discriminate the target from its surrounding background. Considering that the target always undergoes external and internal interference during tracking procedure, the trained filter should take consideration of not only the external distractions but also the target appearance variation synchronously. To this end, we present a State-aware Anti-drift Tracker (SAT) in this paper, which jointly model the discrimination and reliability information in filter learning. Specifically, global context patches are incorporated into filter training stage to better distinguish the target from backgrounds. Meanwhile, a color-based reliable mask is learned to encourage the filter to focus on more reliable regions suitable for tracking. We show that the proposed optimization problem could be efficiently solved using Alternative Direction Method of Multipliers and fully carried out in Fourier domain. Extensive experiments are conducted on OTB-100 datasets to compare the SAT tracker (both hand-crafted feature and CNN feature) with other relevant state-of-the-art methods. Both quantitative and qualitative evaluations further demonstrate the effectiveness and robustness of the proposed work.