Gait based human identity recognition from multi-view surveillance videos

Emdad Hossain, Girija Chetty

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

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 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 languageEnglish
Title of host publicationInternational Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012)
Subtitle of host publicationLecture Notes in Computer Science
EditorsY Xiang, I Stojmenovic, B.O. Apduhan, G Wang, K Nakano, A Zomaya
Place of PublicationGermany
PublisherSpringer
Pages319-328
Number of pages10
Volume7440
ISBN (Electronic)9783642330650
ISBN (Print)9783642330643
DOIs
Publication statusPublished - 2012
Event12th International Conference on Algorithms and Architectures for Parallel Processing ICA3PP 2012: ICA3PP 2012 - Fukuoka, Fukuoka, Japan
Duration: 4 Sep 20127 Sep 2012
http://nsclab.org/ica3pp12/

Conference

Conference12th International Conference on Algorithms and Architectures for Parallel Processing ICA3PP 2012
Abbreviated titleICA3PP 2012
CountryJapan
CityFukuoka
Period4/09/127/09/12
OtherICA3PP 2012 is the 12th in this series of conferences started in 1995 that are devoted to algorithms and architectures for parallel processing. ICA3PP is now recognized as the main regular event of the world that is covering the many dimensions of parallel algorithms and architectures, encompassing fundamental theoretical approaches, practical experimental projects, and commercial components and systems. As applications of computing systems have permeated in every aspects of daily life, the power of computing system has become increasingly critical. This conference provides a forum for countries around the world to exchange ideas for improving the computation power of computing systems.
Following the traditions of the previous successful ICA3PP conferences held in Hangzhou, Brisbane, Singapore, Melbourne, Hong Kong, Beijing, Cyprus, Taipei, Busan, and Melbourne, ICA3PP 2012 will be held in Fukuoka, Japan. The objective of ICA3PP 2012 is to bring together researchers and practitioners from academia, industry and governments to advance the theories and technologies in parallel and distributed computing. ICA3PP 2012 will focus on two broad areas of parallel and distributed computing, i.e., architectures, algorithms and networks, and systems and applications. The conference of ICA3PP 2012 will be organized by Kyushu Sangyo University, Japan
Internet address

Fingerprint

Fusion reactions
Biometrics
Cameras

Cite this

Hossain, E., & Chetty, G. (2012). Gait based human identity recognition from multi-view surveillance videos. In Y. Xiang, I. Stojmenovic, B. O. Apduhan, G. Wang, K. Nakano, & A. Zomaya (Eds.), International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012): Lecture Notes in Computer Science (Vol. 7440, pp. 319-328). Germany: Springer. https://doi.org/10.1007/978-3-642-33065-0_34
Hossain, Emdad ; Chetty, Girija. / Gait based human identity recognition from multi-view surveillance videos. International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012): Lecture Notes in Computer Science. editor / Y Xiang ; I Stojmenovic ; B.O. Apduhan ; G Wang ; K Nakano ; A Zomaya. Vol. 7440 Germany : Springer, 2012. pp. 319-328
@inproceedings{a628dac043fa4ab98cbcf750f8c5dff2,
title = "Gait based human identity recognition from multi-view 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 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 = "Multimodal, Gait, Biometric",
author = "Emdad Hossain and Girija Chetty",
year = "2012",
doi = "10.1007/978-3-642-33065-0_34",
language = "English",
isbn = "9783642330643",
volume = "7440",
pages = "319--328",
editor = "Y Xiang and I Stojmenovic and B.O. Apduhan and G Wang and K Nakano and A Zomaya",
booktitle = "International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012)",
publisher = "Springer",
address = "Netherlands",

}

Hossain, E & Chetty, G 2012, Gait based human identity recognition from multi-view surveillance videos. in Y Xiang, I Stojmenovic, BO Apduhan, G Wang, K Nakano & A Zomaya (eds), International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012): Lecture Notes in Computer Science. vol. 7440, Springer, Germany, pp. 319-328, 12th International Conference on Algorithms and Architectures for Parallel Processing ICA3PP 2012, Fukuoka, Japan, 4/09/12. https://doi.org/10.1007/978-3-642-33065-0_34

Gait based human identity recognition from multi-view surveillance videos. / Hossain, Emdad; Chetty, Girija.

International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012): Lecture Notes in Computer Science. ed. / Y Xiang; I Stojmenovic; B.O. Apduhan; G Wang; K Nakano; A Zomaya. Vol. 7440 Germany : Springer, 2012. p. 319-328.

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

TY - GEN

T1 - Gait based human identity recognition from multi-view 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 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 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 - Multimodal

KW - Gait

KW - Biometric

UR - https://link.springer.com/chapter/10.1007%2F978-3-642-33065-0_34#citeas

U2 - 10.1007/978-3-642-33065-0_34

DO - 10.1007/978-3-642-33065-0_34

M3 - Conference contribution

SN - 9783642330643

VL - 7440

SP - 319

EP - 328

BT - International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012)

A2 - Xiang, Y

A2 - Stojmenovic, I

A2 - Apduhan, B.O.

A2 - Wang, G

A2 - Nakano, K

A2 - Zomaya, A

PB - Springer

CY - Germany

ER -

Hossain E, Chetty G. Gait based human identity recognition from multi-view surveillance videos. In Xiang Y, Stojmenovic I, Apduhan BO, Wang G, Nakano K, Zomaya A, editors, International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2012): Lecture Notes in Computer Science. Vol. 7440. Germany: Springer. 2012. p. 319-328 https://doi.org/10.1007/978-3-642-33065-0_34