Robust Correlation Tracking via Multi-channel Fused Features and Reliable Response Map

TL;DR

This paper introduces a robust correlation tracking method that fuses multi-channel features and employs a strategy to reduce noise in the response map, enhancing tracking accuracy and stability.

Contribution

It proposes a novel feature fusion technique combined with a background-aware correlation filter and a noise reduction strategy for improved online visual tracking.

Findings

Outperforms existing trackers on multiple benchmarks.

Effectively reduces model drift through noise suppression.

Enhances feature representation with gradient and color information.

Abstract

Benefiting from its ability to efficiently learn how an object is changing, correlation filters have recently demonstrated excellent performance for rapidly tracking objects. Designing effective features and handling model drifts are two important aspects for online visual tracking. This paper tackles these challenges by proposing a robust correlation tracking algorithm (RCT) based on two ideas: First, we propose a method to fuse features in order to more naturally describe the gradient and color information of the tracked object, and introduce the fused features into a background aware correlation filter to obtain the response map. Second, we present a novel strategy to significantly reduce noise in the response map and therefore ease the problem of model drift. Systematic comparative evaluations performed over multiple tracking benchmarks demonstrate the efficacy of the proposed approach.