Deep convolutional neural networks for motion instability identification using kinect

Daniel Leightley, Subhas C. Mukhopadhyay, Hemant Ghayvat, Moi Hoon Yap

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Evaluating the execution style of human motion can give insight into the performance and behaviour exhibited by the participant. This could enable support in developing personalised rehabilitation programmes by providing better understanding of motion mechanics and contextual behaviour. However, performing analyses, generating statistical representations and models which are free from external bins, repeatable and robust is a difficult task. In this work, we propose a framework which evaluates clinically valid motions to identify unstable behaviour during performance using Deep Convolutional Neural Networks. The framework is composed of two parts; 1) Instead of using the whole skeleton as input, we divide the human skeleton into five joint groups. For each group, feature encoding is used to represent spatial and temporal domains to permit high-level abstraction and to remove noise these are then represented using distance matrices. 2) The encoded representations are labelled using an automatic labelling method and evaluated using deep learning. Experimental results demonstrates the ability to correctly classify data compared to classical approaches.

LanguageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA)
Place of PublicationPiscataway, NJ, USA
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages310-313
Number of pages4
ISBN (Electronic)9784901122160
ISBN (Print)9781538604953
DOIs
Publication statusPublished - 19 Jul 2017
Externally publishedYes
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: 8 May 201712 May 2017

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
CountryJapan
CityNagoya
Period8/05/1712/05/17

Fingerprint

Bins
Patient rehabilitation
Labeling
Mechanics
Neural networks
Deep learning

Cite this

Leightley, D., Mukhopadhyay, S. C., Ghayvat, H., & Yap, M. H. (2017). Deep convolutional neural networks for motion instability identification using kinect. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA) (pp. 310-313). [7986863] Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.23919/MVA.2017.7986863
Leightley, Daniel ; Mukhopadhyay, Subhas C. ; Ghayvat, Hemant ; Yap, Moi Hoon. / Deep convolutional neural networks for motion instability identification using kinect. Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA). Piscataway, NJ, USA : Institute of Electrical and Electronics Engineers (IEEE), 2017. pp. 310-313
@inproceedings{4cc2d39d02a1400fa5c6cf176bc7327b,
title = "Deep convolutional neural networks for motion instability identification using kinect",
abstract = "Evaluating the execution style of human motion can give insight into the performance and behaviour exhibited by the participant. This could enable support in developing personalised rehabilitation programmes by providing better understanding of motion mechanics and contextual behaviour. However, performing analyses, generating statistical representations and models which are free from external bins, repeatable and robust is a difficult task. In this work, we propose a framework which evaluates clinically valid motions to identify unstable behaviour during performance using Deep Convolutional Neural Networks. The framework is composed of two parts; 1) Instead of using the whole skeleton as input, we divide the human skeleton into five joint groups. For each group, feature encoding is used to represent spatial and temporal domains to permit high-level abstraction and to remove noise these are then represented using distance matrices. 2) The encoded representations are labelled using an automatic labelling method and evaluated using deep learning. Experimental results demonstrates the ability to correctly classify data compared to classical approaches.",
author = "Daniel Leightley and Mukhopadhyay, {Subhas C.} and Hemant Ghayvat and Yap, {Moi Hoon}",
year = "2017",
month = "7",
day = "19",
doi = "10.23919/MVA.2017.7986863",
language = "English",
isbn = "9781538604953",
pages = "310--313",
booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA)",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
address = "United States",

}

Leightley, D, Mukhopadhyay, SC, Ghayvat, H & Yap, MH 2017, Deep convolutional neural networks for motion instability identification using kinect. in Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA)., 7986863, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, USA, pp. 310-313, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 8/05/17. https://doi.org/10.23919/MVA.2017.7986863

Deep convolutional neural networks for motion instability identification using kinect. / Leightley, Daniel; Mukhopadhyay, Subhas C.; Ghayvat, Hemant; Yap, Moi Hoon.

Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA). Piscataway, NJ, USA : Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 310-313 7986863.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Deep convolutional neural networks for motion instability identification using kinect

AU - Leightley, Daniel

AU - Mukhopadhyay, Subhas C.

AU - Ghayvat, Hemant

AU - Yap, Moi Hoon

PY - 2017/7/19

Y1 - 2017/7/19

N2 - Evaluating the execution style of human motion can give insight into the performance and behaviour exhibited by the participant. This could enable support in developing personalised rehabilitation programmes by providing better understanding of motion mechanics and contextual behaviour. However, performing analyses, generating statistical representations and models which are free from external bins, repeatable and robust is a difficult task. In this work, we propose a framework which evaluates clinically valid motions to identify unstable behaviour during performance using Deep Convolutional Neural Networks. The framework is composed of two parts; 1) Instead of using the whole skeleton as input, we divide the human skeleton into five joint groups. For each group, feature encoding is used to represent spatial and temporal domains to permit high-level abstraction and to remove noise these are then represented using distance matrices. 2) The encoded representations are labelled using an automatic labelling method and evaluated using deep learning. Experimental results demonstrates the ability to correctly classify data compared to classical approaches.

AB - Evaluating the execution style of human motion can give insight into the performance and behaviour exhibited by the participant. This could enable support in developing personalised rehabilitation programmes by providing better understanding of motion mechanics and contextual behaviour. However, performing analyses, generating statistical representations and models which are free from external bins, repeatable and robust is a difficult task. In this work, we propose a framework which evaluates clinically valid motions to identify unstable behaviour during performance using Deep Convolutional Neural Networks. The framework is composed of two parts; 1) Instead of using the whole skeleton as input, we divide the human skeleton into five joint groups. For each group, feature encoding is used to represent spatial and temporal domains to permit high-level abstraction and to remove noise these are then represented using distance matrices. 2) The encoded representations are labelled using an automatic labelling method and evaluated using deep learning. Experimental results demonstrates the ability to correctly classify data compared to classical approaches.

UR - http://www.scopus.com/inward/record.url?scp=85027845805&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986863

DO - 10.23919/MVA.2017.7986863

M3 - Conference proceeding contribution

SN - 9781538604953

SP - 310

EP - 313

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ, USA

ER -

Leightley D, Mukhopadhyay SC, Ghayvat H, Yap MH. Deep convolutional neural networks for motion instability identification using kinect. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications (MVA). Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 310-313. 7986863 https://doi.org/10.23919/MVA.2017.7986863