Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking

Chenghuan Liu, Du Huynh, Mark Reynolds

Research output: Chapter in Book/Conference paperConference paper

Abstract

Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable features and kernel functions incorporated, can give very promising tracking results. In this paper, we propose to learn discriminative correlation filters that incorporate information from the variances of the target's appearance features. We have evaluated our filters against several recent tracking methods on the OTB benchmark dataset. Our results show that the additional feature variances help to improve the robustness of the correlation filters in complex scenes.
Original languageEnglish
Title of host publication2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781538628393
DOIs
Publication statusPublished - 2017
Event2017 International Conference on Digital Image Computing: Techniques and Applications - Sydney, Australia
Duration: 29 Nov 20171 Dec 2017

Conference

Conference2017 International Conference on Digital Image Computing: Techniques and Applications
Abbreviated titleDICTA
CountryAustralia
CitySydney
Period29/11/171/12/17

Fingerprint

Computer vision
Lighting

Cite this

Liu, C., Huynh, D., & Reynolds, M. (2017). Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking. In 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) United States: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2017.8227458
Liu, Chenghuan ; Huynh, Du ; Reynolds, Mark. / Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking. 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA). United States : IEEE, Institute of Electrical and Electronics Engineers, 2017.
@inproceedings{1ba2f211e979437cb1d56ace923ef6fc,
title = "Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking",
abstract = "Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable features and kernel functions incorporated, can give very promising tracking results. In this paper, we propose to learn discriminative correlation filters that incorporate information from the variances of the target's appearance features. We have evaluated our filters against several recent tracking methods on the OTB benchmark dataset. Our results show that the additional feature variances help to improve the robustness of the correlation filters in complex scenes.",
author = "Chenghuan Liu and Du Huynh and Mark Reynolds",
year = "2017",
doi = "10.1109/DICTA.2017.8227458",
language = "English",
booktitle = "2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Liu, C, Huynh, D & Reynolds, M 2017, Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking. in 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA). IEEE, Institute of Electrical and Electronics Engineers, United States, 2017 International Conference on Digital Image Computing: Techniques and Applications, Sydney, Australia, 29/11/17. https://doi.org/10.1109/DICTA.2017.8227458

Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking. / Liu, Chenghuan; Huynh, Du; Reynolds, Mark.

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA). United States : IEEE, Institute of Electrical and Electronics Engineers, 2017.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking

AU - Liu, Chenghuan

AU - Huynh, Du

AU - Reynolds, Mark

PY - 2017

Y1 - 2017

N2 - Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable features and kernel functions incorporated, can give very promising tracking results. In this paper, we propose to learn discriminative correlation filters that incorporate information from the variances of the target's appearance features. We have evaluated our filters against several recent tracking methods on the OTB benchmark dataset. Our results show that the additional feature variances help to improve the robustness of the correlation filters in complex scenes.

AB - Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable features and kernel functions incorporated, can give very promising tracking results. In this paper, we propose to learn discriminative correlation filters that incorporate information from the variances of the target's appearance features. We have evaluated our filters against several recent tracking methods on the OTB benchmark dataset. Our results show that the additional feature variances help to improve the robustness of the correlation filters in complex scenes.

U2 - 10.1109/DICTA.2017.8227458

DO - 10.1109/DICTA.2017.8227458

M3 - Conference paper

BT - 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

ER -

Liu C, Huynh D, Reynolds M. Learning Variance Kernelized Correlation Filters for Robust Visual Object Tracking. In 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA). United States: IEEE, Institute of Electrical and Electronics Engineers. 2017 https://doi.org/10.1109/DICTA.2017.8227458