A novel decentralised system architecture for multi-camera target tracking

Gaetano Di Caterina; Trushali Doshi; John J. Soraghan; Lykourgos Petropoulakis

doi:10.1007/978-3-319-48680-2_9

A novel decentralised system architecture for multi-camera target tracking

Gaetano Di Caterina, Trushali Doshi, John J. Soraghan, Lykourgos Petropoulakis

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

44 Downloads (Pure)

Abstract

Target tracking in a multi-camera system is an active and challenging research that in many systems requires video synchronisation and knowledge of the camera set-up and layout. In this paper a highly flexible, modular and decentralised system architecture is presented for multi-camera target tracking with relaxed synchronisation constraints among camera views. Moreover, the system does not rely on positional information to handle camera hand-off events. As a practical application, the system itself can, at any time, automatically select the best target view available, to implicitly solve occlusion. Further, to validate the proposed architecture, an extension to a multi-camera environment of the colour-based IMS-SWAD tracker is used. The experimental results show that the tracker can successfully track a chosen target in multiple views, in both indoor and outdoor environments, with non-overlapping and overlapping camera views.

Original language	English
Title of host publication	Advanced Concepts for Intelligent Vision Systems (ACIVS2016)
Place of Publication	Berlin
Pages	92-104
Number of pages	13
Volume	10016
DOIs	https://doi.org/10.1007/978-3-319-48680-2_9
Publication status	Published - 21 Oct 2016
Event	Advanced Concepts for Intelligent Vision Systems 2016 - Patria Palace Hotel, Lecce, Italy Duration: 24 Oct 2016 → 27 Oct 2016 http://acivs.org/acivs2016/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743

Conference

Conference	Advanced Concepts for Intelligent Vision Systems 2016
Abbreviated title	Acivs 2016
Country/Territory	Italy
City	Lecce
Period	24/10/16 → 27/10/16
Internet address	http://acivs.org/acivs2016/

Keywords

video analytics
multi-camera
decentralised
tracking
system architecture
synchronisation constraints
camera hand-off events
occlusion

Access to Document

10.1007/978-3-319-48680-2_9

Di-Caterina-etal-Acivs2016-Novel-decentralised-system-architecture-for-multi-camera-target-trackingAccepted author manuscript, 1.44 MB

Cite this

@inproceedings{bf0ca9d421e3441aa342550e6d5d1e97,

title = "A novel decentralised system architecture for multi-camera target tracking",

abstract = "Target tracking in a multi-camera system is an active and challenging research that in many systems requires video synchronisation and knowledge of the camera set-up and layout. In this paper a highly flexible, modular and decentralised system architecture is presented for multi-camera target tracking with relaxed synchronisation constraints among camera views. Moreover, the system does not rely on positional information to handle camera hand-off events. As a practical application, the system itself can, at any time, automatically select the best target view available, to implicitly solve occlusion. Further, to validate the proposed architecture, an extension to a multi-camera environment of the colour-based IMS-SWAD tracker is used. The experimental results show that the tracker can successfully track a chosen target in multiple views, in both indoor and outdoor environments, with non-overlapping and overlapping camera views.",

keywords = "video analytics, multi-camera, decentralised, tracking, system architecture, synchronisation constraints, camera hand-off events, occlusion",

author = "{Di Caterina}, Gaetano and Trushali Doshi and Soraghan, {John J.} and Lykourgos Petropoulakis",

note = "The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-48680-2_9; Advanced Concepts for Intelligent Vision Systems 2016, Acivs 2016 ; Conference date: 24-10-2016 Through 27-10-2016",

year = "2016",

month = oct,

day = "21",

doi = "10.1007/978-3-319-48680-2_9",

language = "English",

isbn = "978-3-319-48679-6",

volume = "10016",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "92--104",

booktitle = "Advanced Concepts for Intelligent Vision Systems (ACIVS2016)",

url = "http://acivs.org/acivs2016/",

}

Di Caterina, G, Doshi, T, Soraghan, JJ & Petropoulakis, L 2016, A novel decentralised system architecture for multi-camera target tracking. in Advanced Concepts for Intelligent Vision Systems (ACIVS2016). vol. 10016, Lecture Notes in Computer Science, Berlin, pp. 92-104, Advanced Concepts for Intelligent Vision Systems 2016, Lecce, Italy, 24/10/16. https://doi.org/10.1007/978-3-319-48680-2_9

TY - GEN

T1 - A novel decentralised system architecture for multi-camera target tracking

AU - Di Caterina, Gaetano

AU - Doshi, Trushali

AU - Soraghan, John J.

AU - Petropoulakis, Lykourgos

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-48680-2_9

PY - 2016/10/21

Y1 - 2016/10/21

N2 - Target tracking in a multi-camera system is an active and challenging research that in many systems requires video synchronisation and knowledge of the camera set-up and layout. In this paper a highly flexible, modular and decentralised system architecture is presented for multi-camera target tracking with relaxed synchronisation constraints among camera views. Moreover, the system does not rely on positional information to handle camera hand-off events. As a practical application, the system itself can, at any time, automatically select the best target view available, to implicitly solve occlusion. Further, to validate the proposed architecture, an extension to a multi-camera environment of the colour-based IMS-SWAD tracker is used. The experimental results show that the tracker can successfully track a chosen target in multiple views, in both indoor and outdoor environments, with non-overlapping and overlapping camera views.

AB - Target tracking in a multi-camera system is an active and challenging research that in many systems requires video synchronisation and knowledge of the camera set-up and layout. In this paper a highly flexible, modular and decentralised system architecture is presented for multi-camera target tracking with relaxed synchronisation constraints among camera views. Moreover, the system does not rely on positional information to handle camera hand-off events. As a practical application, the system itself can, at any time, automatically select the best target view available, to implicitly solve occlusion. Further, to validate the proposed architecture, an extension to a multi-camera environment of the colour-based IMS-SWAD tracker is used. The experimental results show that the tracker can successfully track a chosen target in multiple views, in both indoor and outdoor environments, with non-overlapping and overlapping camera views.

KW - video analytics

KW - multi-camera

KW - decentralised

KW - tracking

KW - system architecture

KW - synchronisation constraints

KW - camera hand-off events

KW - occlusion

UR - http://acivs.org/acivs2016/

UR - http://link.springer.com/book/10.1007/978-3-319-48680-2

U2 - 10.1007/978-3-319-48680-2_9

DO - 10.1007/978-3-319-48680-2_9

M3 - Conference contribution book

SN - 978-3-319-48679-6

VL - 10016

T3 - Lecture Notes in Computer Science

SP - 92

EP - 104

BT - Advanced Concepts for Intelligent Vision Systems (ACIVS2016)

CY - Berlin

T2 - Advanced Concepts for Intelligent Vision Systems 2016

Y2 - 24 October 2016 through 27 October 2016

ER -

A novel decentralised system architecture for multi-camera target tracking

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this