Learning support correlation filters for visual tracking

Wangmeng Zuo, Xiaohe Wu, Liang Lin, Lei Zhang, Ming Hsuan Yang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

For visual tracking methods based on kernel support vector machines (SVMs), data sampling is usually adopted to reduce the computational cost in training. In addition, budgeting of support vectors is required for computational efficiency. Instead of sampling and budgeting, recently the circulant matrix formed by dense sampling of translated image patches has been utilized in kernel correlation filters for fast tracking. In this paper, we derive an equivalent formulation of a SVM model with the circulant matrix expression and present an efficient alternating optimization method for visual tracking. We incorporate the discrete Fourier transform with the proposed alternating optimization process, and pose the tracking problem as an iterative learning of support correlation filters (SCFs). In the fully-supervision setting, our SCF can find the globally optimal solution with real-time performance. For a given circulant data matrix with n 2 samples of n ×n pixels, the computational complexity of the proposed algorithm is O(n 2 logn) whereas that of the standard SVM-based approaches is at least O(n 4 ). In addition, we extend the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance. Experimental results on a large benchmark dataset show that the proposed SCF-based algorithms perform favorably against the state-of-the-art tracking methods in terms of accuracy and speed.

Original languageEnglish
Article number8344564
Pages (from-to)1158-1172
Number of pages15
JournalIEEE transactions on pattern analysis and machine intelligence
Volume41
Issue number5
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Correlation Filter
Visual Tracking
Support vector machines
Budget control
Sampling
Support Vector Machine
Circulant Matrix
Computational efficiency
Discrete Fourier transforms
Computational complexity
kernel
Pixels
Support Vector
Discrete Fourier transform
Kernel Function
Process Optimization
Computational Efficiency
Patch
Optimization Methods
Computational Cost

All Science Journal Classification (ASJC) codes

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

Cite this

Zuo, Wangmeng ; Wu, Xiaohe ; Lin, Liang ; Zhang, Lei ; Yang, Ming Hsuan. / Learning support correlation filters for visual tracking. In: IEEE transactions on pattern analysis and machine intelligence. 2019 ; Vol. 41, No. 5. pp. 1158-1172.
@article{1f8d4c5619be409e894ff57eccbe6425,
title = "Learning support correlation filters for visual tracking",
abstract = "For visual tracking methods based on kernel support vector machines (SVMs), data sampling is usually adopted to reduce the computational cost in training. In addition, budgeting of support vectors is required for computational efficiency. Instead of sampling and budgeting, recently the circulant matrix formed by dense sampling of translated image patches has been utilized in kernel correlation filters for fast tracking. In this paper, we derive an equivalent formulation of a SVM model with the circulant matrix expression and present an efficient alternating optimization method for visual tracking. We incorporate the discrete Fourier transform with the proposed alternating optimization process, and pose the tracking problem as an iterative learning of support correlation filters (SCFs). In the fully-supervision setting, our SCF can find the globally optimal solution with real-time performance. For a given circulant data matrix with n 2 samples of n ×n pixels, the computational complexity of the proposed algorithm is O(n 2 logn) whereas that of the standard SVM-based approaches is at least O(n 4 ). In addition, we extend the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance. Experimental results on a large benchmark dataset show that the proposed SCF-based algorithms perform favorably against the state-of-the-art tracking methods in terms of accuracy and speed.",
author = "Wangmeng Zuo and Xiaohe Wu and Liang Lin and Lei Zhang and Yang, {Ming Hsuan}",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/TPAMI.2018.2829180",
language = "English",
volume = "41",
pages = "1158--1172",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "5",

}

Learning support correlation filters for visual tracking. / Zuo, Wangmeng; Wu, Xiaohe; Lin, Liang; Zhang, Lei; Yang, Ming Hsuan.

In: IEEE transactions on pattern analysis and machine intelligence, Vol. 41, No. 5, 8344564, 01.05.2019, p. 1158-1172.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Learning support correlation filters for visual tracking

AU - Zuo, Wangmeng

AU - Wu, Xiaohe

AU - Lin, Liang

AU - Zhang, Lei

AU - Yang, Ming Hsuan

PY - 2019/5/1

Y1 - 2019/5/1

N2 - For visual tracking methods based on kernel support vector machines (SVMs), data sampling is usually adopted to reduce the computational cost in training. In addition, budgeting of support vectors is required for computational efficiency. Instead of sampling and budgeting, recently the circulant matrix formed by dense sampling of translated image patches has been utilized in kernel correlation filters for fast tracking. In this paper, we derive an equivalent formulation of a SVM model with the circulant matrix expression and present an efficient alternating optimization method for visual tracking. We incorporate the discrete Fourier transform with the proposed alternating optimization process, and pose the tracking problem as an iterative learning of support correlation filters (SCFs). In the fully-supervision setting, our SCF can find the globally optimal solution with real-time performance. For a given circulant data matrix with n 2 samples of n ×n pixels, the computational complexity of the proposed algorithm is O(n 2 logn) whereas that of the standard SVM-based approaches is at least O(n 4 ). In addition, we extend the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance. Experimental results on a large benchmark dataset show that the proposed SCF-based algorithms perform favorably against the state-of-the-art tracking methods in terms of accuracy and speed.

AB - For visual tracking methods based on kernel support vector machines (SVMs), data sampling is usually adopted to reduce the computational cost in training. In addition, budgeting of support vectors is required for computational efficiency. Instead of sampling and budgeting, recently the circulant matrix formed by dense sampling of translated image patches has been utilized in kernel correlation filters for fast tracking. In this paper, we derive an equivalent formulation of a SVM model with the circulant matrix expression and present an efficient alternating optimization method for visual tracking. We incorporate the discrete Fourier transform with the proposed alternating optimization process, and pose the tracking problem as an iterative learning of support correlation filters (SCFs). In the fully-supervision setting, our SCF can find the globally optimal solution with real-time performance. For a given circulant data matrix with n 2 samples of n ×n pixels, the computational complexity of the proposed algorithm is O(n 2 logn) whereas that of the standard SVM-based approaches is at least O(n 4 ). In addition, we extend the SCF-based tracking algorithm with multi-channel features, kernel functions, and scale-adaptive approaches to further improve the tracking performance. Experimental results on a large benchmark dataset show that the proposed SCF-based algorithms perform favorably against the state-of-the-art tracking methods in terms of accuracy and speed.

UR - http://www.scopus.com/inward/record.url?scp=85045737041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045737041&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2018.2829180

DO - 10.1109/TPAMI.2018.2829180

M3 - Article

C2 - 29993910

AN - SCOPUS:85045737041

VL - 41

SP - 1158

EP - 1172

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

M1 - 8344564

ER -