Output Constraint Transfer for Kernelized Correlation Filter in Tracking

Baochang Zhang, Zhigang Li, Xianbin Cao, Qixiang Ye, Chen Chen, Linlin Shen, Alessandro Perina, Rongrong Jill

Research output: Journal PublicationArticlepeer-review

75 Citations (Scopus)


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.

Original languageEnglish
Article number7776867
Pages (from-to)693-703
Number of pages11
JournalIEEE Transactions on Systems, Man, and Cybernetics: Systems
Issue number4
Publication statusPublished - Apr 2017
Externally publishedYes


  • Correlation filter
  • online learning
  • tracking

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Output Constraint Transfer for Kernelized Correlation Filter in Tracking'. Together they form a unique fingerprint.

Cite this