Self-calibrating view-invariant gait biometrics
Self-calibrating view-invariant gait biometrics
We present a new method for view-point independent gait biometrics. The system relies on a single camera, does not require camera calibration and works with a wide range of camera-views. This is achieved by a formulation where the gait is self-calibrating. These properties make the proposed method particularly suitable for identification by gait, where the advantages of completely unobtrusiveness, remoteness and covertness of the biometric system preclude the availability of camera information and specific walking directions. The approach has been assessed for feature extraction and recognition capabilities on the SOTON Gait Database and then evaluated on a multi-view database to establish recognition capability with respect to view invariance. Moreover, tests on the multi-view CASIA-B database, composed of more than 2270 video sequences with 65 different subjects walking freely along different walking directions have been performed. The obtained results show that human identification by gait can be achieved without any knowledge of internal or external camera parameters with a mean CCR of 73.6% across all views using purely dynamic gait features. The performance of the proposed method is particularly encouraging for application in surveillance scenarios.
997 -1008
Goffredo, Michela
21a346d2-8ce6-46b7-883f-89a2c584afc7
Bouchrika, Imed
584a502f-829f-4acc-9200-e42f60e42bf0
Carter, John
e05be2f9-991d-4476-bb50-ae91606389da
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
August 2010
Goffredo, Michela
21a346d2-8ce6-46b7-883f-89a2c584afc7
Bouchrika, Imed
584a502f-829f-4acc-9200-e42f60e42bf0
Carter, John
e05be2f9-991d-4476-bb50-ae91606389da
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Goffredo, Michela, Bouchrika, Imed, Carter, John and Nixon, Mark
(2010)
Self-calibrating view-invariant gait biometrics.
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 40 (4), .
(doi:10.1109/TSMCB.2009.2031091).
(PMID:19884085)
Abstract
We present a new method for view-point independent gait biometrics. The system relies on a single camera, does not require camera calibration and works with a wide range of camera-views. This is achieved by a formulation where the gait is self-calibrating. These properties make the proposed method particularly suitable for identification by gait, where the advantages of completely unobtrusiveness, remoteness and covertness of the biometric system preclude the availability of camera information and specific walking directions. The approach has been assessed for feature extraction and recognition capabilities on the SOTON Gait Database and then evaluated on a multi-view database to establish recognition capability with respect to view invariance. Moreover, tests on the multi-view CASIA-B database, composed of more than 2270 video sequences with 65 different subjects walking freely along different walking directions have been performed. The obtained results show that human identification by gait can be achieved without any knowledge of internal or external camera parameters with a mean CCR of 73.6% across all views using purely dynamic gait features. The performance of the proposed method is particularly encouraging for application in surveillance scenarios.
Text
final_copy.pdf
- Other
Text
__userfiles.soton.ac.uk_Users_nsc_mydesktop_cartergait.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
More information
e-pub ahead of print date: 30 October 2009
Published date: August 2010
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 268180
URI: http://eprints.soton.ac.uk/id/eprint/268180
ISSN: 1083-4419
PURE UUID: b1c614bd-224b-4933-a6e0-b563f18bf715
Catalogue record
Date deposited: 06 Nov 2009 10:04
Last modified: 15 Mar 2024 02:35
Export record
Altmetrics
Contributors
Author:
Michela Goffredo
Author:
Imed Bouchrika
Author:
John Carter
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
