Online quality assessment of human movement from skeleton data

Adeline T M Paiement; Lili Tao; Sion L Hannuna; Massimo Camplani; Dima Damen; Majid Mirmehdi

Online quality assessment of human movement from skeleton data

Adeline T M Paiement, Lili Tao, Sion L Hannuna, Massimo Camplani, Dima Damen, Majid Mirmehdi

Research output: Contribution to conference › Conference Paper › peer-review

51 Citations (Scopus)

398 Downloads (Pure)

Abstract

We propose a general method for online estimation of the quality of movements from Kinect skeleton data. A robust non-linear manifold learning technique is used to reduce the dimensionality of the noisy skeleton data. Then, a statistical model of normal movement is built from observations of healthy subjects, and the level of matching of new observations with this model is computed on a frame-by-frame basis following Markovian assumptions. The proposed method is validated on the assessment of gait on stairs.

Original language	English
Publication status	Published - Sept 2014
Event	British Machine Vision Conference - University of Nottingham, Nottingham, United Kingdom Duration: 1 Sept 2014 → 5 Sept 2014

Conference

Conference	British Machine Vision Conference
Country/Territory	United Kingdom
City	Nottingham
Period	1/09/14 → 5/09/14

Structured keywords

Digital Health
SPHERE

Keywords

Digital Health

Access to Document

Full-text PDF (final published version)
This is the final published version of the article (version of record). It first appeared online via BMVC at http://www.bmva.org/bmvc/2014/. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.17 MB

http://dx.doi.org/10.5244/C.28.79

Handle.net

Persistent link

SPHERE (EPSRC IRC)
Craddock, I. J., Coyle, D. T., Flach, P. A., Kaleshi, D., Mirmehdi, M., Piechocki, R. J., Stark, B. H., Ascione, R., Ashburn, A. M., Burnett, M. E., Damen, D., Gooberman-Hill, R., Harwin, W. S., Hilton, G., Holderbaum, W., Holley, A. P., Manchester, V. A., Meller, B. J., Stack, E. & Gilchrist, I. D.
1/10/13 → 30/09/18
Project: Research, Parent

Cite this

@conference{06a1943a1ba54a23abd4ec14a4d75dfb,

title = "Online quality assessment of human movement from skeleton data",

abstract = "We propose a general method for online estimation of the quality of movements from Kinect skeleton data. A robust non-linear manifold learning technique is used to reduce the dimensionality of the noisy skeleton data. Then, a statistical model of normal movement is built from observations of healthy subjects, and the level of matching of new observations with this model is computed on a frame-by-frame basis following Markovian assumptions. The proposed method is validated on the assessment of gait on stairs.",

keywords = "Digital Health",

author = "Paiement, {Adeline T M} and Lili Tao and Hannuna, {Sion L} and Massimo Camplani and Dima Damen and Majid Mirmehdi",

year = "2014",

month = sep,

language = "English",

note = "British Machine Vision Conference ; Conference date: 01-09-2014 Through 05-09-2014",

}

TY - CONF

T1 - Online quality assessment of human movement from skeleton data

AU - Paiement, Adeline T M

AU - Tao, Lili

AU - Hannuna, Sion L

AU - Camplani, Massimo

AU - Damen, Dima

AU - Mirmehdi, Majid

PY - 2014/9

Y1 - 2014/9

N2 - We propose a general method for online estimation of the quality of movements from Kinect skeleton data. A robust non-linear manifold learning technique is used to reduce the dimensionality of the noisy skeleton data. Then, a statistical model of normal movement is built from observations of healthy subjects, and the level of matching of new observations with this model is computed on a frame-by-frame basis following Markovian assumptions. The proposed method is validated on the assessment of gait on stairs.

AB - We propose a general method for online estimation of the quality of movements from Kinect skeleton data. A robust non-linear manifold learning technique is used to reduce the dimensionality of the noisy skeleton data. Then, a statistical model of normal movement is built from observations of healthy subjects, and the level of matching of new observations with this model is computed on a frame-by-frame basis following Markovian assumptions. The proposed method is validated on the assessment of gait on stairs.

KW - Digital Health

M3 - Conference Paper

T2 - British Machine Vision Conference

Y2 - 1 September 2014 through 5 September 2014

ER -

Online quality assessment of human movement from skeleton data

Abstract

Conference

Structured keywords

Keywords

Access to Document

Handle.net

Fingerprint

Projects

SPHERE (EPSRC IRC)

Cite this