Visual Tracking via Reliable Memories

TL;DR

This paper introduces a real-time visual tracking framework that leverages reliable pattern memories to improve long-term tracking accuracy and robustness against drift errors in challenging videos.

Contribution

It presents a novel combination of a DFT-based tracker with a clustering method for memorizing consistent patterns, enhancing long-term tracking performance.

Findings

Performs favorably against state-of-the-art methods on benchmarks.

Handles long videos over 4000 frames without losing track.

Effectively mitigates drift errors in challenging scenarios.

Abstract

In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks. First, we design a Discrete Fourier Transform (DFT) based tracker which is able to exploit a large number of tracked samples while still ensures real-time performance. Second, we propose a clustering method with temporal constraints to explore and memorize consistent patterns from previous frames, named as reliable memories. By virtue of this method, our tracker can utilize uncontaminated information to alleviate drifting issues. Experimental results show that our tracker performs favorably against other state of-the-art methods on benchmark datasets. Furthermore, it is significantly competent in handling drifts and able to robustly track challenging long videos over 4000 frames, while most of others lose track at early frames.