Learning Background-Aware Correlation Filters for Visual Tracking
This work improves visual tracking accuracy for applications like surveillance and robotics by addressing a known bottleneck in CFs, though it is incremental as it builds on existing CF methods.
The paper tackled the problem of visual tracking by addressing the limitation of Correlation Filters (CFs) in not modeling background variations, which leads to suboptimal results. They proposed a Background-Aware CF that models both foreground and background changes, achieving superior accuracy and real-time performance compared to state-of-the-art trackers, including deep learning methods, as demonstrated in extensive experiments on multiple benchmarks.
Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn - "on the fly" - how the object is changing over time. A fundamental drawback to CFs, however, is that the background of the object is not be modelled over time which can result in suboptimal results. In this paper we propose a Background-Aware CF that can model how both the foreground and background of the object varies over time. Our approach, like conventional CFs, is extremely computationally efficient - and extensive experiments over multiple tracking benchmarks demonstrate the superior accuracy and real-time performance of our method compared to the state-of-the-art trackers including those based on a deep learning paradigm.