A Multi-modal gait based human identity recognition system based on surveillance videos

Emdad Hossain, Girija Chetty

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

1 Citation (Scopus)

Abstract

In this paper we propose a novel human-identification scheme from long range gait profiles in surveillance videos. We investigate the role of multi view gait images acquired from multiple cameras, importance of infrared and visible range images in ascertaining identity, and role of soft/secondary biometric (walking style) in enhancing the accuracy and robustness of the identification systems, Experimental evaluation of several subspace based gait feature extraction approaches (PCA/LDA) and learning classifier methods (MLP/SMO) on different datasets from a publicly available gait database CASIA, show that it is possible to do large scale human identity recognition from gait information captured in multiple view-points, with multiple cameras and with usage of subtle soft/secondary biometric information
Original languageEnglish
Title of host publicationieee proceedings on 6th international conference on signal processing and communication systems
EditorsTad Wysocki
Place of PublicationNew Jersey, USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-4
Number of pages4
ISBN (Print)9781467323918
DOIs
Publication statusPublished - 2012
Event6th international conference on signal processing and communication systems - Gold Coast , Gold Coast , Australia
Duration: 12 Dec 201214 Dec 2012
https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=20977

Conference

Conference6th international conference on signal processing and communication systems
CountryAustralia
CityGold Coast
Period12/12/1214/12/12
Internet address

Fingerprint

Biometrics
Cameras
Robustness (control systems)
Feature extraction
Identification (control systems)
Classifiers
Infrared radiation

Cite this

Hossain, E., & Chetty, G. (2012). A Multi-modal gait based human identity recognition system based on surveillance videos. In T. Wysocki (Ed.), ieee proceedings on 6th international conference on signal processing and communication systems (pp. 1-4). New Jersey, USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICSPCS.2012.6508011
Hossain, Emdad ; Chetty, Girija. / A Multi-modal gait based human identity recognition system based on surveillance videos. ieee proceedings on 6th international conference on signal processing and communication systems. editor / Tad Wysocki. New Jersey, USA : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 1-4
@inproceedings{31c87436e8f841fb80762d1db517bdab,
title = "A Multi-modal gait based human identity recognition system based on surveillance videos",
abstract = "In this paper we propose a novel human-identification scheme from long range gait profiles in surveillance videos. We investigate the role of multi view gait images acquired from multiple cameras, importance of infrared and visible range images in ascertaining identity, and role of soft/secondary biometric (walking style) in enhancing the accuracy and robustness of the identification systems, Experimental evaluation of several subspace based gait feature extraction approaches (PCA/LDA) and learning classifier methods (MLP/SMO) on different datasets from a publicly available gait database CASIA, show that it is possible to do large scale human identity recognition from gait information captured in multiple view-points, with multiple cameras and with usage of subtle soft/secondary biometric information",
keywords = "Multimodal, Gait, Biometric Identification",
author = "Emdad Hossain and Girija Chetty",
year = "2012",
doi = "10.1109/ICSPCS.2012.6508011",
language = "English",
isbn = "9781467323918",
pages = "1--4",
editor = "Tad Wysocki",
booktitle = "ieee proceedings on 6th international conference on signal processing and communication systems",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Hossain, E & Chetty, G 2012, A Multi-modal gait based human identity recognition system based on surveillance videos. in T Wysocki (ed.), ieee proceedings on 6th international conference on signal processing and communication systems. IEEE, Institute of Electrical and Electronics Engineers, New Jersey, USA, pp. 1-4, 6th international conference on signal processing and communication systems, Gold Coast , Australia, 12/12/12. https://doi.org/10.1109/ICSPCS.2012.6508011

A Multi-modal gait based human identity recognition system based on surveillance videos. / Hossain, Emdad; Chetty, Girija.

ieee proceedings on 6th international conference on signal processing and communication systems. ed. / Tad Wysocki. New Jersey, USA : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 1-4.

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

TY - GEN

T1 - A Multi-modal gait based human identity recognition system based on surveillance videos

AU - Hossain, Emdad

AU - Chetty, Girija

PY - 2012

Y1 - 2012

N2 - In this paper we propose a novel human-identification scheme from long range gait profiles in surveillance videos. We investigate the role of multi view gait images acquired from multiple cameras, importance of infrared and visible range images in ascertaining identity, and role of soft/secondary biometric (walking style) in enhancing the accuracy and robustness of the identification systems, Experimental evaluation of several subspace based gait feature extraction approaches (PCA/LDA) and learning classifier methods (MLP/SMO) on different datasets from a publicly available gait database CASIA, show that it is possible to do large scale human identity recognition from gait information captured in multiple view-points, with multiple cameras and with usage of subtle soft/secondary biometric information

AB - In this paper we propose a novel human-identification scheme from long range gait profiles in surveillance videos. We investigate the role of multi view gait images acquired from multiple cameras, importance of infrared and visible range images in ascertaining identity, and role of soft/secondary biometric (walking style) in enhancing the accuracy and robustness of the identification systems, Experimental evaluation of several subspace based gait feature extraction approaches (PCA/LDA) and learning classifier methods (MLP/SMO) on different datasets from a publicly available gait database CASIA, show that it is possible to do large scale human identity recognition from gait information captured in multiple view-points, with multiple cameras and with usage of subtle soft/secondary biometric information

KW - Multimodal

KW - Gait

KW - Biometric Identification

U2 - 10.1109/ICSPCS.2012.6508011

DO - 10.1109/ICSPCS.2012.6508011

M3 - Conference contribution

SN - 9781467323918

SP - 1

EP - 4

BT - ieee proceedings on 6th international conference on signal processing and communication systems

A2 - Wysocki, Tad

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - New Jersey, USA

ER -

Hossain E, Chetty G. A Multi-modal gait based human identity recognition system based on surveillance videos. In Wysocki T, editor, ieee proceedings on 6th international conference on signal processing and communication systems. New Jersey, USA: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 1-4 https://doi.org/10.1109/ICSPCS.2012.6508011