The University of Southampton
University of Southampton Institutional Repository

Performance Analysis on New Biometric Gait Motion Model

Performance Analysis on New Biometric Gait Motion Model
Performance Analysis on New Biometric Gait Motion Model
Recognising people by the way they walk and/or run is new. A novel analytical model which is invariant to human gait of walking and running is developed based on the concept of dynamically coupled oscillators and the biomechanics of human walking and running. It serves as the foundation of this automatic person recognition system. The effects of noise and low resolution have been evaluated on the largest data set of its kind. This is useful as security camera footage is usually prone to noise and of poor resolution. The gait signature is formed from the Fourier description of the thigh and lower leg rotation. Angles of rotation are extracted via temporal template matching across the whole image sequence. Classification is done via the k-nearest neighbour and cross-validated with the leave-one-out rule. The promising recognition rates for both walking and running suggest the high potential of this technique and using gait as the cue for person identification in practical applications. Future work will focus on understanding the features used to create the gait signature in order to further improve the recognition rate and will determine the invariance attributes for walking and running.
Yam, ChewYean
79143266-5774-4a7f-be45-0f3ff669acca
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da
Yam, ChewYean
79143266-5774-4a7f-be45-0f3ff669acca
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da

Yam, ChewYean, Nixon, Mark S. and Carter, John N. (2002) Performance Analysis on New Biometric Gait Motion Model. Proceedings of Southwest Symposium on Image Analysis and Interpretation.

Record type: Conference or Workshop Item (Other)

Abstract

Recognising people by the way they walk and/or run is new. A novel analytical model which is invariant to human gait of walking and running is developed based on the concept of dynamically coupled oscillators and the biomechanics of human walking and running. It serves as the foundation of this automatic person recognition system. The effects of noise and low resolution have been evaluated on the largest data set of its kind. This is useful as security camera footage is usually prone to noise and of poor resolution. The gait signature is formed from the Fourier description of the thigh and lower leg rotation. Angles of rotation are extracted via temporal template matching across the whole image sequence. Classification is done via the k-nearest neighbour and cross-validated with the leave-one-out rule. The promising recognition rates for both walking and running suggest the high potential of this technique and using gait as the cue for person identification in practical applications. Future work will focus on understanding the features used to create the gait signature in order to further improve the recognition rate and will determine the invariance attributes for walking and running.

Text
Yam_Gait.ps - Other
Download (1MB)

More information

Published date: April 2002
Additional Information: Organisation: IEEE
Venue - Dates: Proceedings of Southwest Symposium on Image Analysis and Interpretation, 2002-04-01
Organisations: Southampton Wireless Group

Identifiers

Local EPrints ID: 256411
URI: http://eprints.soton.ac.uk/id/eprint/256411
PURE UUID: c709e9a0-fbbf-4dc5-97d8-1a286138e137
ORCID for Mark S. Nixon: ORCID iD orcid.org/0000-0002-9174-5934

Catalogue record

Date deposited: 04 Apr 2002
Last modified: 03 Dec 2019 02:07

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×