Output Constraint Transfer For Kernelized Correlation Filter In Tracking

Keywords

Correlation filter; online learning; tracking

Abstract

The 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.

Publication Date

4-1-2017

Publication Title

IEEE Transactions on Systems, Man, and Cybernetics: Systems

Volume

47

Issue

4

Number of Pages

693-703

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TSMC.2016.2629509

Socpus ID

85017579931 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85017579931

This document is currently not available here.

Share

COinS