Correlation Particle Filter for Visual Tracking

Tianzhu Zhang, Si Liu, Changsheng Xu, Bin Liu, Ming Hsuan Yang

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

In this paper, we propose a novel correlation particle filter (CPF) for robust visual tracking. Instead of a simple combination of a correlation filter and a particle filter, we exploit and complement the strength of each one. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has four major advantages: 1) it is robust to partial and total occlusions, and can recover from lost tracks by maintaining multiple hypotheses; 2) it can effectively handle large-scale variation via a particle sampling strategy; 3) it can efficiently maintain multiple modes in the posterior density using fewer particles than conventional particle filters, resulting in low computational cost; and 4) it can shepherd the sampled particles toward the modes of the target state distribution using a mixture of correlation filters, resulting in robust tracking performance. Extensive experimental results on challenging benchmark data sets demonstrate that the proposed CPF tracking algorithm performs favorably against the state-of-the-art methods.

Original languageEnglish
Pages (from-to)2676-2687
Number of pages12
JournalIEEE Transactions on Image Processing
Volume27
Issue number6
DOIs
Publication statusPublished - 2018 Jun

Fingerprint

Sampling
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Zhang, Tianzhu ; Liu, Si ; Xu, Changsheng ; Liu, Bin ; Yang, Ming Hsuan. / Correlation Particle Filter for Visual Tracking. In: IEEE Transactions on Image Processing. 2018 ; Vol. 27, No. 6. pp. 2676-2687.
@article{b47829abdeb4463b9969b9ad9094fc19,
title = "Correlation Particle Filter for Visual Tracking",
abstract = "In this paper, we propose a novel correlation particle filter (CPF) for robust visual tracking. Instead of a simple combination of a correlation filter and a particle filter, we exploit and complement the strength of each one. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has four major advantages: 1) it is robust to partial and total occlusions, and can recover from lost tracks by maintaining multiple hypotheses; 2) it can effectively handle large-scale variation via a particle sampling strategy; 3) it can efficiently maintain multiple modes in the posterior density using fewer particles than conventional particle filters, resulting in low computational cost; and 4) it can shepherd the sampled particles toward the modes of the target state distribution using a mixture of correlation filters, resulting in robust tracking performance. Extensive experimental results on challenging benchmark data sets demonstrate that the proposed CPF tracking algorithm performs favorably against the state-of-the-art methods.",
author = "Tianzhu Zhang and Si Liu and Changsheng Xu and Bin Liu and Yang, {Ming Hsuan}",
year = "2018",
month = "6",
doi = "10.1109/TIP.2017.2781304",
language = "English",
volume = "27",
pages = "2676--2687",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

Correlation Particle Filter for Visual Tracking. / Zhang, Tianzhu; Liu, Si; Xu, Changsheng; Liu, Bin; Yang, Ming Hsuan.

In: IEEE Transactions on Image Processing, Vol. 27, No. 6, 06.2018, p. 2676-2687.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Correlation Particle Filter for Visual Tracking

AU - Zhang, Tianzhu

AU - Liu, Si

AU - Xu, Changsheng

AU - Liu, Bin

AU - Yang, Ming Hsuan

PY - 2018/6

Y1 - 2018/6

N2 - In this paper, we propose a novel correlation particle filter (CPF) for robust visual tracking. Instead of a simple combination of a correlation filter and a particle filter, we exploit and complement the strength of each one. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has four major advantages: 1) it is robust to partial and total occlusions, and can recover from lost tracks by maintaining multiple hypotheses; 2) it can effectively handle large-scale variation via a particle sampling strategy; 3) it can efficiently maintain multiple modes in the posterior density using fewer particles than conventional particle filters, resulting in low computational cost; and 4) it can shepherd the sampled particles toward the modes of the target state distribution using a mixture of correlation filters, resulting in robust tracking performance. Extensive experimental results on challenging benchmark data sets demonstrate that the proposed CPF tracking algorithm performs favorably against the state-of-the-art methods.

AB - In this paper, we propose a novel correlation particle filter (CPF) for robust visual tracking. Instead of a simple combination of a correlation filter and a particle filter, we exploit and complement the strength of each one. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has four major advantages: 1) it is robust to partial and total occlusions, and can recover from lost tracks by maintaining multiple hypotheses; 2) it can effectively handle large-scale variation via a particle sampling strategy; 3) it can efficiently maintain multiple modes in the posterior density using fewer particles than conventional particle filters, resulting in low computational cost; and 4) it can shepherd the sampled particles toward the modes of the target state distribution using a mixture of correlation filters, resulting in robust tracking performance. Extensive experimental results on challenging benchmark data sets demonstrate that the proposed CPF tracking algorithm performs favorably against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85038389912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038389912&partnerID=8YFLogxK

U2 - 10.1109/TIP.2017.2781304

DO - 10.1109/TIP.2017.2781304

M3 - Article

AN - SCOPUS:85038389912

VL - 27

SP - 2676

EP - 2687

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 6

ER -