Learning Multi-Task Correlation Particle Filters for Visual Tracking

Tianzhu Zhang, Changsheng Xu, Ming Hsuan Yang

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different object parts and features into account to learn the correlation filters jointly. Next, the proposed MCPF is introduced to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed MCPF enjoys several merits. First, it exploits the interdependencies among different features to derive the correlation filters jointly, and makes the learned filters complement and enhance each other to obtain consistent responses. Second, it handles partial occlusion via a part-based representation, and exploits the intrinsic relationship among local parts via spatial constraints to preserve object structure and learn the correlation filters jointly. Third, it effectively handles large scale variation via a sampling scheme by drawing particles at different scales for target object state estimation. Fourth, it shepherds the sampled particles toward the modes of the target state distribution via the MCF, and effectively covers object states well using fewer particles than conventional particle filters, thereby resulting in robust tracking performance and low computational cost. Extensive experimental results on four challenging benchmark datasets demonstrate that the proposed MCPF tracking algorithm performs favorably against the state-of-the-art methods.

Original languageEnglish
Article number8267285
Pages (from-to)365-378
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Volume41
Issue number2
DOIs
Publication statusPublished - 2019 Feb 1

Fingerprint

Multi-task Learning
Correlation Filter
Visual Tracking
Particle Filter
State estimation
Sampling
Costs
Interdependencies
Complement
Target
State Estimation
Occlusion
Computational Cost

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

@article{bea3709c69ca45b1acc2494a716816de,
title = "Learning Multi-Task Correlation Particle Filters for Visual Tracking",
abstract = "In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different object parts and features into account to learn the correlation filters jointly. Next, the proposed MCPF is introduced to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed MCPF enjoys several merits. First, it exploits the interdependencies among different features to derive the correlation filters jointly, and makes the learned filters complement and enhance each other to obtain consistent responses. Second, it handles partial occlusion via a part-based representation, and exploits the intrinsic relationship among local parts via spatial constraints to preserve object structure and learn the correlation filters jointly. Third, it effectively handles large scale variation via a sampling scheme by drawing particles at different scales for target object state estimation. Fourth, it shepherds the sampled particles toward the modes of the target state distribution via the MCF, and effectively covers object states well using fewer particles than conventional particle filters, thereby resulting in robust tracking performance and low computational cost. Extensive experimental results on four challenging benchmark datasets demonstrate that the proposed MCPF tracking algorithm performs favorably against the state-of-the-art methods.",
author = "Tianzhu Zhang and Changsheng Xu and Yang, {Ming Hsuan}",
year = "2019",
month = "2",
day = "1",
doi = "10.1109/TPAMI.2018.2797062",
language = "English",
volume = "41",
pages = "365--378",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "2",

}

Learning Multi-Task Correlation Particle Filters for Visual Tracking. / Zhang, Tianzhu; Xu, Changsheng; Yang, Ming Hsuan.

In: IEEE transactions on pattern analysis and machine intelligence, Vol. 41, No. 2, 8267285, 01.02.2019, p. 365-378.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Learning Multi-Task Correlation Particle Filters for Visual Tracking

AU - Zhang, Tianzhu

AU - Xu, Changsheng

AU - Yang, Ming Hsuan

PY - 2019/2/1

Y1 - 2019/2/1

N2 - In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different object parts and features into account to learn the correlation filters jointly. Next, the proposed MCPF is introduced to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed MCPF enjoys several merits. First, it exploits the interdependencies among different features to derive the correlation filters jointly, and makes the learned filters complement and enhance each other to obtain consistent responses. Second, it handles partial occlusion via a part-based representation, and exploits the intrinsic relationship among local parts via spatial constraints to preserve object structure and learn the correlation filters jointly. Third, it effectively handles large scale variation via a sampling scheme by drawing particles at different scales for target object state estimation. Fourth, it shepherds the sampled particles toward the modes of the target state distribution via the MCF, and effectively covers object states well using fewer particles than conventional particle filters, thereby resulting in robust tracking performance and low computational cost. Extensive experimental results on four challenging benchmark datasets demonstrate that the proposed MCPF tracking algorithm performs favorably against the state-of-the-art methods.

AB - In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different object parts and features into account to learn the correlation filters jointly. Next, the proposed MCPF is introduced to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed MCPF enjoys several merits. First, it exploits the interdependencies among different features to derive the correlation filters jointly, and makes the learned filters complement and enhance each other to obtain consistent responses. Second, it handles partial occlusion via a part-based representation, and exploits the intrinsic relationship among local parts via spatial constraints to preserve object structure and learn the correlation filters jointly. Third, it effectively handles large scale variation via a sampling scheme by drawing particles at different scales for target object state estimation. Fourth, it shepherds the sampled particles toward the modes of the target state distribution via the MCF, and effectively covers object states well using fewer particles than conventional particle filters, thereby resulting in robust tracking performance and low computational cost. Extensive experimental results on four challenging benchmark datasets demonstrate that the proposed MCPF tracking algorithm performs favorably against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85041012904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041012904&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2018.2797062

DO - 10.1109/TPAMI.2018.2797062

M3 - Article

C2 - 29994598

AN - SCOPUS:85041012904

VL - 41

SP - 365

EP - 378

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 2

M1 - 8267285

ER -