Back to Search Start Over

SVMT: A MATLAB toolbox for stereo-vision motion tracking of motor reactivity

SVMT: A MATLAB toolbox for stereo-vision motion tracking of motor reactivity

Authors :
Vousdoukas, M.I.
Perakakis, P.
Idrissi, S.
Vila, J.
Source :
Computer Methods & Programs in Biomedicine. Oct2012, Vol. 108 Issue 1, p318-329. 12p.
Publication Year :
2012

Abstract

Abstract: This article presents a Matlab-based stereo-vision motion tracking system (SVMT) for the detection of human motor reactivity elicited by sensory stimulation. It is a low-cost, non-intrusive system supported by Graphical User Interface (GUI) software, and has been successfully tested and integrated in a broad array of physiological recording devices at the Human Physiology Laboratory in the University of Granada. The SVMT GUI software handles data in Matlab and ASCII formats. Internal functions perform lens distortion correction, camera geometry definition, feature matching, as well as data clustering and filtering to extract 3D motion paths of specific body areas. System validation showed geo-rectification errors below 0.5mm, while feature matching and motion paths extraction procedures were successfully validated with manual tracking and RMS errors were typically below 2% of the movement range. The application of the system in a psychophysiological experiment designed to elicit a startle motor response by the presentation of intense and unexpected acoustic stimuli, provided reliable data probing dynamical features of motor responses and habituation to repeated stimulus presentations. The stereo-geolocation and motion tracking performance of the SVMT system were successfully validated through comparisons with surface EMG measurements of eyeblink startle, which clearly demonstrate the ability of SVMT to track subtle body movement, such as those induced by the presentation of intense acoustic stimuli. Finally, SVMT provides an efficient solution for the assessment of motor reactivity not only in controlled laboratory settings, but also in more open, ecological environments. [Copyright &y& Elsevier]

Details

Language :
English
ISSN :
01692607
Volume :
108
Issue :
1
Database :
Academic Search Index
Journal :
Computer Methods & Programs in Biomedicine
Publication Type :
Academic Journal
Accession number :
79559612
Full Text :
https://doi.org/10.1016/j.cmpb.2012.01.006