A comparative home activity monitoring study using visual and inertial sensors

Lili Tao; Tilo Burghardt; Sion L Hannuna; Massimo Camplani; Adeline T M Paiement; Dima Aldamen; Majid Mirmehdi; Ian J Craddock

doi:10.1109/HealthCom.2015.7454583

A comparative home activity monitoring study using visual and inertial sensors

Lili Tao, Tilo Burghardt, Sion L Hannuna, Massimo Camplani, Adeline T M Paiement, Dima Aldamen, Majid Mirmehdi, Ian J Craddock

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

472 Downloads (Pure)

Abstract

Monitoring actions at home can provide essential information for rehabilitation management. This paper presents a comparative study and a dataset for the fully automated, sample-accurate recognition of common home actions in the living room environment using commercial-grade, inexpensive inertial and visual sensors. We investigate the practical home-use of body-worn mobile phone inertial sensors together with an Asus Xmotion RGB-Depth camera to achieve monitoring of daily living scenarios. To test this setup against realistic data, we introduce the challenging SPHERE-H130 action dataset containing 130 sequences of 13 household actions recorded in a home environment. We report automatic recognition results at maximal temporal resolution, which indicate that a vision-based approach outperforms accelerometer provided by two phone-based inertial sensors by an average of 14.85% accuracy for home actions. Further, we report improved accuracy of a vision-based approach over accelerometry on particularly challenging actions as well as when generalising across subjects.

Original language	English
Title of host publication	2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015)
Subtitle of host publication	Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	644-647
Number of pages	4
ISBN (Electronic)	9781467383257
ISBN (Print)	9781467383264
DOIs	https://doi.org/10.1109/HealthCom.2015.7454583
Publication status	Published - Apr 2016
Event	2015 17th International Conference on E-health Networking, Application & Services (HealthCom) - Boston, MA, United States Duration: 14 Oct 2015 → 17 Oct 2015 Conference number: 17

Conference

Conference	2015 17th International Conference on E-health Networking, Application & Services (HealthCom)
Abbreviated title	HealthCom 2015
Country/Territory	United States
City	Boston, MA
Period	14/10/15 → 17/10/15

Structured keywords

Digital Health
SPHERE

Access to Document

10.1109/HealthCom.2015.7454583

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/document/7454583/. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 2.21 MB

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

Tao, L., Burghardt, T., Hannuna, S. L., Camplani, M., Paiement, A. T. M., Aldamen, D., Mirmehdi, M., & Craddock, I. J. (2016). A comparative home activity monitoring study using visual and inertial sensors. In 2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015): Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA (pp. 644-647). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/HealthCom.2015.7454583

Tao, Lili ; Burghardt, Tilo ; Hannuna, Sion L et al. / A comparative home activity monitoring study using visual and inertial sensors. 2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015): Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA. Institute of Electrical and Electronics Engineers (IEEE), 2016. pp. 644-647

@inproceedings{4da18c90057442ffb387c73d33538d43,

title = "A comparative home activity monitoring study using visual and inertial sensors",

abstract = "Monitoring actions at home can provide essential information for rehabilitation management. This paper presents a comparative study and a dataset for the fully automated, sample-accurate recognition of common home actions in the living room environment using commercial-grade, inexpensive inertial and visual sensors. We investigate the practical home-use of body-worn mobile phone inertial sensors together with an Asus Xmotion RGB-Depth camera to achieve monitoring of daily living scenarios. To test this setup against realistic data, we introduce the challenging SPHERE-H130 action dataset containing 130 sequences of 13 household actions recorded in a home environment. We report automatic recognition results at maximal temporal resolution, which indicate that a vision-based approach outperforms accelerometer provided by two phone-based inertial sensors by an average of 14.85% accuracy for home actions. Further, we report improved accuracy of a vision-based approach over accelerometry on particularly challenging actions as well as when generalising across subjects.",

author = "Lili Tao and Tilo Burghardt and Hannuna, {Sion L} and Massimo Camplani and Paiement, {Adeline T M} and Dima Aldamen and Majid Mirmehdi and Craddock, {Ian J}",

year = "2016",

month = apr,

doi = "10.1109/HealthCom.2015.7454583",

language = "English",

isbn = "9781467383264",

pages = "644--647",

booktitle = "2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2015 17th International Conference on E-health Networking, Application & Services (HealthCom), HealthCom 2015 ; Conference date: 14-10-2015 Through 17-10-2015",

}

Tao, L, Burghardt, T , Hannuna, SL, Camplani, M, Paiement, ATM, Aldamen, D , Mirmehdi, M & Craddock, IJ 2016, A comparative home activity monitoring study using visual and inertial sensors. in 2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015): Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA. Institute of Electrical and Electronics Engineers (IEEE), pp. 644-647, 2015 17th International Conference on E-health Networking, Application & Services (HealthCom), Boston, MA, United States, 14/10/15. https://doi.org/10.1109/HealthCom.2015.7454583

A comparative home activity monitoring study using visual and inertial sensors. / Tao, Lili; Burghardt, Tilo ; Hannuna, Sion L et al.
2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015): Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA. Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 644-647.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - A comparative home activity monitoring study using visual and inertial sensors

AU - Tao, Lili

AU - Burghardt, Tilo

AU - Hannuna, Sion L

AU - Camplani, Massimo

AU - Paiement, Adeline T M

AU - Aldamen, Dima

AU - Mirmehdi, Majid

AU - Craddock, Ian J

N1 - Conference code: 17

PY - 2016/4

Y1 - 2016/4

N2 - Monitoring actions at home can provide essential information for rehabilitation management. This paper presents a comparative study and a dataset for the fully automated, sample-accurate recognition of common home actions in the living room environment using commercial-grade, inexpensive inertial and visual sensors. We investigate the practical home-use of body-worn mobile phone inertial sensors together with an Asus Xmotion RGB-Depth camera to achieve monitoring of daily living scenarios. To test this setup against realistic data, we introduce the challenging SPHERE-H130 action dataset containing 130 sequences of 13 household actions recorded in a home environment. We report automatic recognition results at maximal temporal resolution, which indicate that a vision-based approach outperforms accelerometer provided by two phone-based inertial sensors by an average of 14.85% accuracy for home actions. Further, we report improved accuracy of a vision-based approach over accelerometry on particularly challenging actions as well as when generalising across subjects.

AB - Monitoring actions at home can provide essential information for rehabilitation management. This paper presents a comparative study and a dataset for the fully automated, sample-accurate recognition of common home actions in the living room environment using commercial-grade, inexpensive inertial and visual sensors. We investigate the practical home-use of body-worn mobile phone inertial sensors together with an Asus Xmotion RGB-Depth camera to achieve monitoring of daily living scenarios. To test this setup against realistic data, we introduce the challenging SPHERE-H130 action dataset containing 130 sequences of 13 household actions recorded in a home environment. We report automatic recognition results at maximal temporal resolution, which indicate that a vision-based approach outperforms accelerometer provided by two phone-based inertial sensors by an average of 14.85% accuracy for home actions. Further, we report improved accuracy of a vision-based approach over accelerometry on particularly challenging actions as well as when generalising across subjects.

U2 - 10.1109/HealthCom.2015.7454583

DO - 10.1109/HealthCom.2015.7454583

M3 - Conference Contribution (Conference Proceeding)

SN - 9781467383264

SP - 644

EP - 647

BT - 2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2015 17th International Conference on E-health Networking, Application & Services (HealthCom)

Y2 - 14 October 2015 through 17 October 2015

ER -

Tao L, Burghardt T , Hannuna SL, Camplani M, Paiement ATM, Aldamen D et al. A comparative home activity monitoring study using visual and inertial sensors. In 2015 17th International Conference on E-health Networking, Application & Services (HealthCom 2015): Proceedings of a meeting held 14-17 October 2015, Boston, MA, USA. Institute of Electrical and Electronics Engineers (IEEE). 2016. p. 644-647 Epub 2016 Apr 19. doi: 10.1109/HealthCom.2015.7454583

A comparative home activity monitoring study using visual and inertial sensors

Abstract

Conference

Structured keywords

Access to Document

Handle.net

Fingerprint

Projects

SPHERE (EPSRC IRC)

Cite this