Detection of gait cycles in treadmill walking using a Kinect

Highlights • Heel strikes were detected with the maximum longitudinal distance between the knees. • This distance was estimated with depth images from Kinect without using a skeleton. • The error for heel strike events estimation with Kinect information was 17 ± 24 ms. • The error for step duration...

Full description

Saved in:

Bibliographic Details
Published in:	Gait & posture Vol. 41; no. 2; pp. 722 - 725
Main Authors:	Auvinet, Edouard, Multon, Franck, Aubin, Carl-Eric, Meunier, Jean, Raison, Maxime
Format:	Journal Article
Language:	English
Published:	England Elsevier B.V 01-02-2015 Elsevier
Subjects:	Adult Computer Science Cycles Equipment Design Exercise Test - instrumentation Female Foot - physiology Gait - physiology Gait analysis Heel strike detection Humans Kinect Knee - physiology Male Motion capture Multimedia Orthopedics Treadmill Walking - physiology Young Adult Kinect Heel strike detection Cycles Motion capture Treadmill Gait analysis
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Highlights • Heel strikes were detected with the maximum longitudinal distance between the knees. • This distance was estimated with depth images from Kinect without using a skeleton. • The error for heel strike events estimation with Kinect information was 17 ± 24 ms. • The error for step duration estimation with Kinect information was 0 ± 12 ms.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0966-6362 1879-2219
DOI:	10.1016/j.gaitpost.2014.08.006