Output Constraint Transfer for Kernelized Correlation Filter in Tracking

TL;DR

This paper introduces Output Constraint Transfer (OCT), a Bayesian optimization-based method that models correlation response distribution to improve Kernelized Correlation Filter (KCF) tracking accuracy and reduce drifting, especially during appearance changes.

Contribution

The paper proposes a novel OCT method that models correlation response distribution and transfers data distribution constraints to enhance KCF tracking performance.

Findings

OCT significantly improves KCF accuracy on benchmark datasets.

The method outperforms existing state-of-the-art trackers.

Source code is publicly available for further research.

Abstract

Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers. However, it does not reasonably model the distribution of correlation response during tracking process, which might cause the drifting problem, especially when targets undergo significant appearance changes due to occlusion, camera shaking, and/or deformation. In this paper, we propose an Output Constraint Transfer (OCT) method that by modeling the distribution of correlation response in a Bayesian optimization framework is able to mitigate the drifting problem. OCT builds upon the reasonable assumption that the correlation response to the target image follows a Gaussian distribution, which we exploit to select training samples and reduce model uncertainty. OCT is rooted in a new theory which transfers data distribution to a constraint of the optimized variable, leading to an efficient framework to calculate correlation filters. Extensive experiments on a commonly used tracking benchmark show that the proposed method significantly improves KCF, and achieves better performance than other state-of-the-art trackers. To encourage further developments, the source code is made available https://github.com/bczhangbczhang/OCT-KCF.