Human Postural Sway Estimation from Noisy Observations

Hafsa ISMAIL, Ibrahim Hamed Ismail RADWAN, Hanna SUOMINEN, Gordon WADDINGTON, Roland GOECKE

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

Postural sway is a reflection of brain signals that are generated to control a person’s balance. During the process of ageing, the postural sway changes, which increases the likelihood of a fall. Thus far, expensive specialist equipment is required, such as a force plate, in order to detect such changes over time, which makes the process costly and impractical. Our long-term goal is to investigate the use of inexpensive, everyday video technology as an alternative. This paper describes a study that establishes a 3-way correlation between the clinical gold standard (force plate), a highly accurate multi-camera 3D video tracking system (Vicon) and a standard RGB video camera. To this end, a dataset of 18 subjects performing the BESS balance test on the force plate was recorded, while simultaneously recording the 3D Vicon data, and the RGB video camera data. Then, using Gaussian process regression and a recurrent neural network, models were built to predict the lateral postural sway in the force plate data from the RGB video data. The predicted results show high correlation with the actual force plate signals, which supports the hypothesis that lateral postural sway can be accurately predicted from video data alone. Detecting changes to a person’s postural sway can be used to improve elderly people’s life by monitoring the likelihood of a fall and detecting its increase well before a fall occurs, so that countermeasures (e.g. exercises) can be put in place to prevent falls occurring.
Original languageEnglish
Title of host publicationProceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017)
EditorsKevin Bowyer, Rama Chellappa, Jeff Cohn
Place of PublicationWashington DC
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages454-461
Number of pages8
ISBN (Electronic)9781509040230
ISBN (Print)9781509040247
DOIs
Publication statusPublished - 30 May 2017

Publication series

Name2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)
ISSN (Print)2326-5396

Fingerprint

Video cameras
Recurrent neural networks
Brain
Aging of materials
Cameras
Monitoring

Cite this

ISMAIL, H., RADWAN, I. H. I., SUOMINEN, H., WADDINGTON, G., & GOECKE, R. (2017). Human Postural Sway Estimation from Noisy Observations. In K. Bowyer, R. Chellappa, & J. Cohn (Eds.), Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017) (pp. 454-461). [7961776] (2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)). Washington DC: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FG.2017.62
ISMAIL, Hafsa ; RADWAN, Ibrahim Hamed Ismail ; SUOMINEN, Hanna ; WADDINGTON, Gordon ; GOECKE, Roland. / Human Postural Sway Estimation from Noisy Observations. Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017). editor / Kevin Bowyer ; Rama Chellappa ; Jeff Cohn. Washington DC : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 454-461 (2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)).
@inproceedings{6934cf5d180940618728818955d34726,
title = "Human Postural Sway Estimation from Noisy Observations",
abstract = "Postural sway is a reflection of brain signals that are generated to control a person’s balance. During the process of ageing, the postural sway changes, which increases the likelihood of a fall. Thus far, expensive specialist equipment is required, such as a force plate, in order to detect such changes over time, which makes the process costly and impractical. Our long-term goal is to investigate the use of inexpensive, everyday video technology as an alternative. This paper describes a study that establishes a 3-way correlation between the clinical gold standard (force plate), a highly accurate multi-camera 3D video tracking system (Vicon) and a standard RGB video camera. To this end, a dataset of 18 subjects performing the BESS balance test on the force plate was recorded, while simultaneously recording the 3D Vicon data, and the RGB video camera data. Then, using Gaussian process regression and a recurrent neural network, models were built to predict the lateral postural sway in the force plate data from the RGB video data. The predicted results show high correlation with the actual force plate signals, which supports the hypothesis that lateral postural sway can be accurately predicted from video data alone. Detecting changes to a person’s postural sway can be used to improve elderly people’s life by monitoring the likelihood of a fall and detecting its increase well before a fall occurs, so that countermeasures (e.g. exercises) can be put in place to prevent falls occurring.",
author = "Hafsa ISMAIL and RADWAN, {Ibrahim Hamed Ismail} and Hanna SUOMINEN and Gordon WADDINGTON and Roland GOECKE",
year = "2017",
month = "5",
day = "30",
doi = "10.1109/FG.2017.62",
language = "English",
isbn = "9781509040247",
series = "2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "454--461",
editor = "Kevin Bowyer and Rama Chellappa and Jeff Cohn",
booktitle = "Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017)",
address = "United States",

}

ISMAIL, H, RADWAN, IHI, SUOMINEN, H, WADDINGTON, G & GOECKE, R 2017, Human Postural Sway Estimation from Noisy Observations. in K Bowyer, R Chellappa & J Cohn (eds), Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017)., 7961776, 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), IEEE, Institute of Electrical and Electronics Engineers, Washington DC, pp. 454-461. https://doi.org/10.1109/FG.2017.62

Human Postural Sway Estimation from Noisy Observations. / ISMAIL, Hafsa; RADWAN, Ibrahim Hamed Ismail; SUOMINEN, Hanna; WADDINGTON, Gordon; GOECKE, Roland.

Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017). ed. / Kevin Bowyer; Rama Chellappa; Jeff Cohn. Washington DC : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 454-461 7961776 (2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Human Postural Sway Estimation from Noisy Observations

AU - ISMAIL, Hafsa

AU - RADWAN, Ibrahim Hamed Ismail

AU - SUOMINEN, Hanna

AU - WADDINGTON, Gordon

AU - GOECKE, Roland

PY - 2017/5/30

Y1 - 2017/5/30

N2 - Postural sway is a reflection of brain signals that are generated to control a person’s balance. During the process of ageing, the postural sway changes, which increases the likelihood of a fall. Thus far, expensive specialist equipment is required, such as a force plate, in order to detect such changes over time, which makes the process costly and impractical. Our long-term goal is to investigate the use of inexpensive, everyday video technology as an alternative. This paper describes a study that establishes a 3-way correlation between the clinical gold standard (force plate), a highly accurate multi-camera 3D video tracking system (Vicon) and a standard RGB video camera. To this end, a dataset of 18 subjects performing the BESS balance test on the force plate was recorded, while simultaneously recording the 3D Vicon data, and the RGB video camera data. Then, using Gaussian process regression and a recurrent neural network, models were built to predict the lateral postural sway in the force plate data from the RGB video data. The predicted results show high correlation with the actual force plate signals, which supports the hypothesis that lateral postural sway can be accurately predicted from video data alone. Detecting changes to a person’s postural sway can be used to improve elderly people’s life by monitoring the likelihood of a fall and detecting its increase well before a fall occurs, so that countermeasures (e.g. exercises) can be put in place to prevent falls occurring.

AB - Postural sway is a reflection of brain signals that are generated to control a person’s balance. During the process of ageing, the postural sway changes, which increases the likelihood of a fall. Thus far, expensive specialist equipment is required, such as a force plate, in order to detect such changes over time, which makes the process costly and impractical. Our long-term goal is to investigate the use of inexpensive, everyday video technology as an alternative. This paper describes a study that establishes a 3-way correlation between the clinical gold standard (force plate), a highly accurate multi-camera 3D video tracking system (Vicon) and a standard RGB video camera. To this end, a dataset of 18 subjects performing the BESS balance test on the force plate was recorded, while simultaneously recording the 3D Vicon data, and the RGB video camera data. Then, using Gaussian process regression and a recurrent neural network, models were built to predict the lateral postural sway in the force plate data from the RGB video data. The predicted results show high correlation with the actual force plate signals, which supports the hypothesis that lateral postural sway can be accurately predicted from video data alone. Detecting changes to a person’s postural sway can be used to improve elderly people’s life by monitoring the likelihood of a fall and detecting its increase well before a fall occurs, so that countermeasures (e.g. exercises) can be put in place to prevent falls occurring.

UR - http://www.scopus.com/inward/record.url?scp=85026285247&partnerID=8YFLogxK

U2 - 10.1109/FG.2017.62

DO - 10.1109/FG.2017.62

M3 - Conference contribution

SN - 9781509040247

T3 - 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)

SP - 454

EP - 461

BT - Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017)

A2 - Bowyer, Kevin

A2 - Chellappa, Rama

A2 - Cohn, Jeff

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Washington DC

ER -

ISMAIL H, RADWAN IHI, SUOMINEN H, WADDINGTON G, GOECKE R. Human Postural Sway Estimation from Noisy Observations. In Bowyer K, Chellappa R, Cohn J, editors, Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017). Washington DC: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 454-461. 7961776. (2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)). https://doi.org/10.1109/FG.2017.62