Robust visual tracking using structurally random projection and weighted least squares

Shengping Zhang, Huiyu Zhou, Feng Jiang, Xuelong Li

Research output: Contribution to journalArticle

89 Citations (Scopus)
203 Downloads (Pure)

Abstract

Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.
Original languageEnglish
Pages (from-to)1749-1760
Number of pages12
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume25
Issue number11
Early online date20 Feb 2015
DOIs
Publication statusPublished - Nov 2015

Fingerprint

Computational complexity

Cite this

Zhang, Shengping ; Zhou, Huiyu ; Jiang, Feng ; Li, Xuelong . / Robust visual tracking using structurally random projection and weighted least squares. In: IEEE Transactions on Circuits and Systems for Video Technology. 2015 ; Vol. 25, No. 11. pp. 1749-1760.
@article{d53bc6daeb064ece939de9dcfa1e9f1e,
title = "Robust visual tracking using structurally random projection and weighted least squares",
abstract = "Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.",
author = "Shengping Zhang and Huiyu Zhou and Feng Jiang and Xuelong Li",
year = "2015",
month = "11",
doi = "10.1109/TCSVT.2015.2406194",
language = "English",
volume = "25",
pages = "1749--1760",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

Robust visual tracking using structurally random projection and weighted least squares. / Zhang, Shengping; Zhou, Huiyu; Jiang, Feng; Li, Xuelong .

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 25, No. 11, 11.2015, p. 1749-1760.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust visual tracking using structurally random projection and weighted least squares

AU - Zhang, Shengping

AU - Zhou, Huiyu

AU - Jiang, Feng

AU - Li, Xuelong

PY - 2015/11

Y1 - 2015/11

N2 - Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.

AB - Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.

U2 - 10.1109/TCSVT.2015.2406194

DO - 10.1109/TCSVT.2015.2406194

M3 - Article

VL - 25

SP - 1749

EP - 1760

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 11

ER -