Self-calibrating view-invariant gait biometrics

Goffredo, Michela, Bouchrika, Imed, Carter, John and Nixon, Mark (2010) Self-calibrating view-invariant gait biometrics. IEEE Transactions Systems, Man and Cybernetics B, 40, (4), 997 -1008. (doi:10.1109/TSMCB.2009.2031091). (PMID:19884085).


[img] PDF
Download (1092Kb)
[img] PDF - Publishers print
Restricted to internal admin

Download (1090Kb) | Request a copy


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.

Item Type: Article
ISSNs: 1083-4419 (electronic)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QP Physiology
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Comms, Signal Processing & Control
ePrint ID: 268180
Date Deposited: 06 Nov 2009 10:04
Last Modified: 14 Apr 2014 11:32
Further Information:Google Scholar
ISI Citation Count:7

Actions (login required)

View Item View Item

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