Multi-view gait fusion for large scale human identification in surveillance videos

Emdad Hossain; Girija Chetty

doi:10.1007/978-3-642-33140-4_46

Multi-view gait fusion for large scale human identification in surveillance videos

Emdad Hossain
, Girija Chetty

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

Abstract

In this paper we propose a novel multi-view feature fusion of gait biometric information in surveillance videos for large scale human identification. The experimental evaluation on low resolution surveillance video images from a publicly available database [1] showed that the combined LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns. The multi-view fusion at feature level allows complementarity of multiple camera views in surveillance scenarios to be exploited for improvement of identity recognition performance.

Original language	English
Title of host publication	International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012)
Subtitle of host publication	Lecture Notes in Computer Science
Editors	Jacques Blanc-Talon, Wilfried Philips, Dan Popescu, Paul Scheunders, Pavel Zemcik
Place of Publication	Czech Republic
Publisher	Springer
Pages	527-538
Number of pages	12
Volume	7517
ISBN (Electronic)	9783642331404
ISBN (Print)	9783642331398
DOIs	https://doi.org/10.1007/978-3-642-33140-4_46
Publication status	Published - 2012
Event	Advances Concepts for Intelligent Vision System - Brno, Brno, Czech Republic Duration: 4 Sept 2012 → …

Conference

Conference	Advances Concepts for Intelligent Vision System
Country/Territory	Czech Republic
City	Brno
Period	4/09/12 → …

Access to Document

10.1007/978-3-642-33140-4_46

Cite this

Hossain, E., & Chetty, G. (2012). Multi-view gait fusion for large scale human identification in surveillance videos. In J. Blanc-Talon, W. Philips, D. Popescu, P. Scheunders, & P. Zemcik (Eds.), International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012): Lecture Notes in Computer Science (Vol. 7517, pp. 527-538). Springer. https://doi.org/10.1007/978-3-642-33140-4_46

Hossain, Emdad ; Chetty, Girija. / Multi-view gait fusion for large scale human identification in surveillance videos. International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012): Lecture Notes in Computer Science. editor / Jacques Blanc-Talon ; Wilfried Philips ; Dan Popescu ; Paul Scheunders ; Pavel Zemcik. Vol. 7517 Czech Republic : Springer, 2012. pp. 527-538

@inproceedings{4c6eda3b8a924e769e940997fa1b78d3,

title = "Multi-view gait fusion for large scale human identification in surveillance videos",

abstract = "In this paper we propose a novel multi-view feature fusion of gait biometric information in surveillance videos for large scale human identification. The experimental evaluation on low resolution surveillance video images from a publicly available database [1] showed that the combined LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns. The multi-view fusion at feature level allows complementarity of multiple camera views in surveillance scenarios to be exploited for improvement of identity recognition performance.",

keywords = "Multi view images, LDA, MLP, Identification, Feature fusion",

author = "Emdad Hossain and Girija Chetty",

year = "2012",

doi = "10.1007/978-3-642-33140-4\_46",

language = "English",

isbn = "9783642331398",

volume = "7517",

pages = "527--538",

editor = "Jacques Blanc-Talon and Wilfried Philips and Dan Popescu and Paul Scheunders and Pavel Zemcik",

booktitle = "International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012)",

publisher = "Springer",

address = "Netherlands",

note = "Advances Concepts for Intelligent Vision System ; Conference date: 04-09-2012",

}

Hossain, E & Chetty, G 2012, Multi-view gait fusion for large scale human identification in surveillance videos. in J Blanc-Talon, W Philips, D Popescu, P Scheunders & P Zemcik (eds), International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012): Lecture Notes in Computer Science. vol. 7517, Springer, Czech Republic, pp. 527-538, Advances Concepts for Intelligent Vision System, Brno, Czech Republic, 4/09/12. https://doi.org/10.1007/978-3-642-33140-4_46

Multi-view gait fusion for large scale human identification in surveillance videos. / Hossain, Emdad; Chetty, Girija.
International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012): Lecture Notes in Computer Science. ed. / Jacques Blanc-Talon; Wilfried Philips; Dan Popescu; Paul Scheunders; Pavel Zemcik. Vol. 7517 Czech Republic: Springer, 2012. p. 527-538.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Multi-view gait fusion for large scale human identification in surveillance videos

AU - Hossain, Emdad

AU - Chetty, Girija

PY - 2012

Y1 - 2012

N2 - In this paper we propose a novel multi-view feature fusion of gait biometric information in surveillance videos for large scale human identification. The experimental evaluation on low resolution surveillance video images from a publicly available database [1] showed that the combined LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns. The multi-view fusion at feature level allows complementarity of multiple camera views in surveillance scenarios to be exploited for improvement of identity recognition performance.

AB - In this paper we propose a novel multi-view feature fusion of gait biometric information in surveillance videos for large scale human identification. The experimental evaluation on low resolution surveillance video images from a publicly available database [1] showed that the combined LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns. The multi-view fusion at feature level allows complementarity of multiple camera views in surveillance scenarios to be exploited for improvement of identity recognition performance.

KW - Multi view images

KW - LDA

KW - MLP

KW - Identification

KW - Feature fusion

U2 - 10.1007/978-3-642-33140-4_46

DO - 10.1007/978-3-642-33140-4_46

M3 - Conference contribution

SN - 9783642331398

VL - 7517

SP - 527

EP - 538

BT - International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012)

A2 - Blanc-Talon, Jacques

A2 - Philips, Wilfried

A2 - Popescu, Dan

A2 - Scheunders, Paul

A2 - Zemcik, Pavel

PB - Springer

CY - Czech Republic

T2 - Advances Concepts for Intelligent Vision System

Y2 - 4 September 2012

ER -

Hossain E, Chetty G. Multi-view gait fusion for large scale human identification in surveillance videos. In Blanc-Talon J, Philips W, Popescu D, Scheunders P, Zemcik P, editors, International Conference on Advanced Concepts in intelligent Vision Systems (ACIVS 2012): Lecture Notes in Computer Science. Vol. 7517. Czech Republic: Springer. 2012. p. 527-538 doi: 10.1007/978-3-642-33140-4_46

Multi-view gait fusion for large scale human identification in surveillance videos

Abstract

Conference

Access to Document

Fingerprint

Cite this