Learning Background-Aware Correlation Filters for Visual Tracking

TL;DR

This paper introduces a background-aware correlation filter for visual tracking that models both foreground and background variations over time, achieving superior accuracy and real-time performance.

Contribution

It proposes a novel background-aware correlation filter that enhances traditional CFs by modeling background changes, improving tracking accuracy.

Findings

Outperforms state-of-the-art trackers on multiple benchmarks.

Maintains real-time processing speeds.

Demonstrates robustness under challenging variations.

Abstract

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.