Joint Sparsity-Based Robust Visual Tracking

Seyed Bozorgtabar, Roland GOECKE

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Downloads (Pure)

Abstract

In this paper, a new object tracking in a particle filter framework utilising a joint sparsity-based model is proposed. Based on the observation that a target can be reconstructed from several templates that are updated dynamically, we jointly analyse the representation of the particles under a single regression framework and with the shared underlying structure. Two convex regularisations are combined and used in our model to enable sparsity as well as facilitate coupling information between particles. Unlike the previous methods that consider a model commonality between particles or regard them as independent tasks, we simultaneously take into account a structure inducing norm and an outlier detecting norm. Such a formulation is shown to be more flexible in terms of handling various types of challenges including occlusion and cluttered background. To derive the optimal solution efficiently, we propose to use a Preconditioned Conjugate Gradient method, which is computationally affordable for high-dimensional data. Furthermore, an online updating procedure scheme is included in the dictionary learning, which makes the proposed tracker less vulnerable to outliers. Experiments on challenging video sequences demonstrate the robustness of the proposed approach to handling occlusion, pose and illumination variation and outperform state-of-the-art trackers in tracking accuracy.
Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing (ICIP)
Editors Pesquet-Popescu, Fowler
Place of PublicationParis, France
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4927-4931
Number of pages5
ISBN (Electronic)9781479957514
ISBN (Print)9781479957514
DOIs
Publication statusPublished - 2014
Event2014 IEEE International Conference on Image Processing - Paris, Paris, France
Duration: 27 Oct 201430 Oct 2014

Publication series

Name2014 IEEE International Conference on Image Processing, ICIP 2014

Conference

Conference2014 IEEE International Conference on Image Processing
CountryFrance
CityParis
Period27/10/1430/10/14

Fingerprint

Conjugate gradient method
Glossaries
Lighting
Experiments

Cite this

Bozorgtabar, S., & GOECKE, R. (2014). Joint Sparsity-Based Robust Visual Tracking. In Pesquet-Popescu, & Fowler (Eds.), 2014 IEEE International Conference on Image Processing (ICIP) (pp. 4927-4931). [7025998] (2014 IEEE International Conference on Image Processing, ICIP 2014). Paris, France: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2014.7025998
Bozorgtabar, Seyed ; GOECKE, Roland. / Joint Sparsity-Based Robust Visual Tracking. 2014 IEEE International Conference on Image Processing (ICIP). editor / Pesquet-Popescu ; Fowler. Paris, France : IEEE, Institute of Electrical and Electronics Engineers, 2014. pp. 4927-4931 (2014 IEEE International Conference on Image Processing, ICIP 2014).
@inproceedings{db760d087a6745ad8888a7795e57210f,
title = "Joint Sparsity-Based Robust Visual Tracking",
abstract = "In this paper, a new object tracking in a particle filter framework utilising a joint sparsity-based model is proposed. Based on the observation that a target can be reconstructed from several templates that are updated dynamically, we jointly analyse the representation of the particles under a single regression framework and with the shared underlying structure. Two convex regularisations are combined and used in our model to enable sparsity as well as facilitate coupling information between particles. Unlike the previous methods that consider a model commonality between particles or regard them as independent tasks, we simultaneously take into account a structure inducing norm and an outlier detecting norm. Such a formulation is shown to be more flexible in terms of handling various types of challenges including occlusion and cluttered background. To derive the optimal solution efficiently, we propose to use a Preconditioned Conjugate Gradient method, which is computationally affordable for high-dimensional data. Furthermore, an online updating procedure scheme is included in the dictionary learning, which makes the proposed tracker less vulnerable to outliers. Experiments on challenging video sequences demonstrate the robustness of the proposed approach to handling occlusion, pose and illumination variation and outperform state-of-the-art trackers in tracking accuracy.",
keywords = "Visual Tracking, Sparsity, Preconditioned Conjugate Gradient",
author = "Seyed Bozorgtabar and Roland GOECKE",
year = "2014",
doi = "10.1109/ICIP.2014.7025998",
language = "English",
isbn = "9781479957514",
series = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "4927--4931",
editor = "Pesquet-Popescu and Fowler",
booktitle = "2014 IEEE International Conference on Image Processing (ICIP)",
address = "United States",

}

Bozorgtabar, S & GOECKE, R 2014, Joint Sparsity-Based Robust Visual Tracking. in Pesquet-Popescu & Fowler (eds), 2014 IEEE International Conference on Image Processing (ICIP)., 7025998, 2014 IEEE International Conference on Image Processing, ICIP 2014, IEEE, Institute of Electrical and Electronics Engineers, Paris, France, pp. 4927-4931, 2014 IEEE International Conference on Image Processing, Paris, France, 27/10/14. https://doi.org/10.1109/ICIP.2014.7025998

Joint Sparsity-Based Robust Visual Tracking. / Bozorgtabar, Seyed; GOECKE, Roland.

2014 IEEE International Conference on Image Processing (ICIP). ed. / Pesquet-Popescu; Fowler. Paris, France : IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 4927-4931 7025998 (2014 IEEE International Conference on Image Processing, ICIP 2014).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Joint Sparsity-Based Robust Visual Tracking

AU - Bozorgtabar, Seyed

AU - GOECKE, Roland

PY - 2014

Y1 - 2014

N2 - In this paper, a new object tracking in a particle filter framework utilising a joint sparsity-based model is proposed. Based on the observation that a target can be reconstructed from several templates that are updated dynamically, we jointly analyse the representation of the particles under a single regression framework and with the shared underlying structure. Two convex regularisations are combined and used in our model to enable sparsity as well as facilitate coupling information between particles. Unlike the previous methods that consider a model commonality between particles or regard them as independent tasks, we simultaneously take into account a structure inducing norm and an outlier detecting norm. Such a formulation is shown to be more flexible in terms of handling various types of challenges including occlusion and cluttered background. To derive the optimal solution efficiently, we propose to use a Preconditioned Conjugate Gradient method, which is computationally affordable for high-dimensional data. Furthermore, an online updating procedure scheme is included in the dictionary learning, which makes the proposed tracker less vulnerable to outliers. Experiments on challenging video sequences demonstrate the robustness of the proposed approach to handling occlusion, pose and illumination variation and outperform state-of-the-art trackers in tracking accuracy.

AB - In this paper, a new object tracking in a particle filter framework utilising a joint sparsity-based model is proposed. Based on the observation that a target can be reconstructed from several templates that are updated dynamically, we jointly analyse the representation of the particles under a single regression framework and with the shared underlying structure. Two convex regularisations are combined and used in our model to enable sparsity as well as facilitate coupling information between particles. Unlike the previous methods that consider a model commonality between particles or regard them as independent tasks, we simultaneously take into account a structure inducing norm and an outlier detecting norm. Such a formulation is shown to be more flexible in terms of handling various types of challenges including occlusion and cluttered background. To derive the optimal solution efficiently, we propose to use a Preconditioned Conjugate Gradient method, which is computationally affordable for high-dimensional data. Furthermore, an online updating procedure scheme is included in the dictionary learning, which makes the proposed tracker less vulnerable to outliers. Experiments on challenging video sequences demonstrate the robustness of the proposed approach to handling occlusion, pose and illumination variation and outperform state-of-the-art trackers in tracking accuracy.

KW - Visual Tracking

KW - Sparsity

KW - Preconditioned Conjugate Gradient

UR - http://www.scopus.com/inward/record.url?scp=84983134682&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/joint-sparsitybased-robust-visual-tracking

U2 - 10.1109/ICIP.2014.7025998

DO - 10.1109/ICIP.2014.7025998

M3 - Conference contribution

SN - 9781479957514

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 4927

EP - 4931

BT - 2014 IEEE International Conference on Image Processing (ICIP)

A2 - Pesquet-Popescu, null

A2 - Fowler, null

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Paris, France

ER -

Bozorgtabar S, GOECKE R. Joint Sparsity-Based Robust Visual Tracking. In Pesquet-Popescu, Fowler, editors, 2014 IEEE International Conference on Image Processing (ICIP). Paris, France: IEEE, Institute of Electrical and Electronics Engineers. 2014. p. 4927-4931. 7025998. (2014 IEEE International Conference on Image Processing, ICIP 2014). https://doi.org/10.1109/ICIP.2014.7025998