Learning Support Correlation Filters for Visual Tracking

TL;DR

This paper introduces support correlation filters (SCFs) for visual tracking, combining SVM principles with correlation filters to achieve real-time performance and high accuracy by leveraging Fourier transforms and efficient optimization.

Contribution

It derives an equivalent SVM formulation with circulant matrices and proposes an efficient alternating optimization method for real-time visual tracking.

Findings

SCF-based algorithms outperform state-of-the-art methods in accuracy.

The proposed method achieves real-time tracking with O(n^2*logn) complexity.

Extensions with multi-channel features and scale adaptation improve performance.

Abstract

Sampling and budgeting training examples are two essential factors in tracking algorithms based on support vector machines (SVMs) as a trade-off between accuracy and efficiency. Recently, the circulant matrix formed by dense sampling of translated image patches has been utilized in correlation filters for fast tracking. In this paper, we derive an equivalent formulation of a SVM model with circulant matrix expression and present an efficient alternating optimization method for visual tracking. We incorporate the discrete Fourier transform with the proposed alternating optimization process, and pose the tracking problem as an iterative learning of support correlation filters (SCFs) which find the global optimal solution with real-time performance. For a given circulant data matrix with n^2 samples of size n*n, the computational complexity of the proposed algorithm is O(n^2*logn) whereas that of the standard SVM-based approaches is at least O(n^4). In addition, we extend the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance. Experimental results on a large benchmark dataset show that the proposed SCF-based algorithms perform favorably against the state-of-the-art tracking methods in terms of accuracy and speed.