On Laboratory Gait Analysis via Computer Vision
On Laboratory Gait Analysis via Computer Vision
We describe a marker-less system for analysing and classifying human gait motion by combining a statistical approach and motion tracking with topological analysis guided by anatomical knowledge. The marker-less gait analysis system consists of three stages: detection and extraction of the moving human body and its contour from image sequences; extraction of human gait motion by the joint angles and body points; and kinematic analysis and feature extraction for classifying the gait pattern. The periodic motion of human gait is described by symmetry, and a 2D stick figure is used to rep-resent the human gait model. The usefulness of proposed method is demonstrated in marker-less gait analysis with comparison to biomechanical data.
Gait Analysis, Biometrics
1 902956 31 5
109-113
Yoo, Jang-Hee
cbfc2f5d-2a17-4f6d-a94c-788b5747fa7b
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
2003
Yoo, Jang-Hee
cbfc2f5d-2a17-4f6d-a94c-788b5747fa7b
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Yoo, Jang-Hee and Nixon, Mark S.
(2003)
On Laboratory Gait Analysis via Computer Vision.
AISB ’03 Symposium on Biologically-Inspired Machine Vision, Theory and Application, University of , Aberystwyth, UK, United Kingdom.
07 - 11 Apr 2003.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
We describe a marker-less system for analysing and classifying human gait motion by combining a statistical approach and motion tracking with topological analysis guided by anatomical knowledge. The marker-less gait analysis system consists of three stages: detection and extraction of the moving human body and its contour from image sequences; extraction of human gait motion by the joint angles and body points; and kinematic analysis and feature extraction for classifying the gait pattern. The periodic motion of human gait is described by symmetry, and a 2D stick figure is used to rep-resent the human gait model. The usefulness of proposed method is demonstrated in marker-less gait analysis with comparison to biomechanical data.
Text
aisb03jhy.ps
- Other
More information
Published date: 2003
Additional Information:
Event Dates: April 7-11, 2003
Venue - Dates:
AISB ’03 Symposium on Biologically-Inspired Machine Vision, Theory and Application, University of , Aberystwyth, UK, United Kingdom, 2003-04-07 - 2003-04-11
Keywords:
Gait Analysis, Biometrics
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 258199
URI: http://eprints.soton.ac.uk/id/eprint/258199
ISBN: 1 902956 31 5
PURE UUID: 1ae3172f-ac27-4720-ae00-518c3a81a44b
Catalogue record
Date deposited: 20 Nov 2003
Last modified: 15 Mar 2024 02:34
Export record
Contributors
Author:
Jang-Hee Yoo
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
