An Accelerated Correlation Filter Tracker

TL;DR

This paper introduces an accelerated correlation filter tracking method that improves convergence speed and robustness, reducing computational complexity while maintaining high tracking accuracy.

Contribution

It proposes a novel accelerated ADMM optimization with momentum and adaptive initialization for correlation filter tracking, enhancing speed and robustness.

Findings

Achieves faster convergence of the DCF filter.

Maintains tracking accuracy comparable to state-of-the-art methods.

Demonstrates robustness across multiple benchmark datasets.

Abstract

Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features. Despite the outstanding performance achieved by the above combination, existing advanced trackers suffer from the burden of high computational complexity of the deep feature extraction and online model learning. We propose an accelerated ADMM optimisation method obtained by adding a momentum to the optimisation sequence iterates, and by relaxing the impact of the error between DCF parameters and their norm. The proposed optimisation method is applied to an innovative formulation of the DCF design, which seeks the most discriminative spatially regularised feature channels. A further speed up is achieved by an adaptive initialisation of the filter optimisation process. The significantly increased convergence of the DCF filter is demonstrated by establishing the optimisation process equivalence with a continuous dynamical system for which the convergence properties can readily be derived. The experimental results obtained on several well-known benchmarking datasets demonstrate the efficiency and robustness of the proposed ACFT method, with a tracking accuracy comparable to the start-of-the-art trackers.