Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance

Chika Edith Mgbemena, John Oyekan, Ashutosh Tiwari, Yuchun Xu, Sarah Fletcher, Windo Hutabarat, Vinayak Prabhu

Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

Abstract

Manual handling involves transporting of load by hand through lifting or lowering and operators on the manufacturing shop floor are daily faced with constant lifting and lowering operations which leads to Work-Related Musculoskeletal Disorders. The trend in data collection on the Shop floor for ergonomic evaluation during manual handling activities has revealed a gap in gesture detection as gesture triggered data collection could facilitate more accurate ergonomic data capture and analysis. This paper presents an application developed to detect gestures towards triggering real-time human motion data capture on the shop floor for ergonomic evaluations and risk assessment using the Microsoft Kinect. The machine learning technology known as the discrete indicator—precisely the AdaBoost Trigger indicator was employed to train the gestures. Our results show that the Kinect can be trained to detect gestures towards real-time ergonomic analysis and possibly offering intelligent automation assistance during human posture detrimental tasks.
Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Computing
Subtitle of host publicationManaging the Enterprise of the Future
EditorsC Schlick, S Trzcieliński
PublisherSpringer
Pages217-228
ISBN (Electronic)978-3-319-41697-7
ISBN (Print)978-3-319-41696-0
DOIs
Publication statusPublished - 10 Jul 2016

Publication series

NameAdvances in Ergonomics of Manufacturing: Managing the Enterprise of the Future
Volume490
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Fingerprint

Ergonomics
Automation
Data acquisition
Adaptive boosting
Risk assessment
Learning systems

Bibliographical note

© 2016 Springer Publishing. This is a post-peer-review, pre-copyedit version of an article published in [insert journal title]. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-41697-7_20

Cite this

Mgbemena, C. E., Oyekan, J., Tiwari, A., Xu, Y., Fletcher, S., Hutabarat, W., & Prabhu, V. (2016). Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance. In C. Schlick, & S. Trzcieliński (Eds.), Advances in Intelligent Systems and Computing: Managing the Enterprise of the Future (pp. 217-228). [Chapter 20] (Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future; Vol. 490). Springer. https://doi.org/10.1007/978-3-319-41697-7_20
Mgbemena, Chika Edith ; Oyekan, John ; Tiwari, Ashutosh ; Xu, Yuchun ; Fletcher, Sarah ; Hutabarat, Windo ; Prabhu, Vinayak. / Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance. Advances in Intelligent Systems and Computing: Managing the Enterprise of the Future. editor / C Schlick ; S Trzcieliński . Springer, 2016. pp. 217-228 (Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future).
@inbook{2a04cf6b00b3410f883bdb73f84cb950,
title = "Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance",
abstract = "Manual handling involves transporting of load by hand through lifting or lowering and operators on the manufacturing shop floor are daily faced with constant lifting and lowering operations which leads to Work-Related Musculoskeletal Disorders. The trend in data collection on the Shop floor for ergonomic evaluation during manual handling activities has revealed a gap in gesture detection as gesture triggered data collection could facilitate more accurate ergonomic data capture and analysis. This paper presents an application developed to detect gestures towards triggering real-time human motion data capture on the shop floor for ergonomic evaluations and risk assessment using the Microsoft Kinect. The machine learning technology known as the discrete indicator—precisely the AdaBoost Trigger indicator was employed to train the gestures. Our results show that the Kinect can be trained to detect gestures towards real-time ergonomic analysis and possibly offering intelligent automation assistance during human posture detrimental tasks.",
author = "Mgbemena, {Chika Edith} and John Oyekan and Ashutosh Tiwari and Yuchun Xu and Sarah Fletcher and Windo Hutabarat and Vinayak Prabhu",
note = "{\circledC} 2016 Springer Publishing. This is a post-peer-review, pre-copyedit version of an article published in [insert journal title]. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-41697-7_20",
year = "2016",
month = "7",
day = "10",
doi = "10.1007/978-3-319-41697-7_20",
language = "English",
isbn = "978-3-319-41696-0",
series = "Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future",
publisher = "Springer",
pages = "217--228",
editor = "C Schlick and {Trzcieliński }, { S}",
booktitle = "Advances in Intelligent Systems and Computing",
address = "Germany",

}

Mgbemena, CE, Oyekan, J, Tiwari, A, Xu, Y, Fletcher, S, Hutabarat, W & Prabhu, V 2016, Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance. in C Schlick & S Trzcieliński (eds), Advances in Intelligent Systems and Computing: Managing the Enterprise of the Future., Chapter 20, Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future, vol. 490, Springer, pp. 217-228. https://doi.org/10.1007/978-3-319-41697-7_20

Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance. / Mgbemena, Chika Edith; Oyekan, John; Tiwari, Ashutosh; Xu, Yuchun; Fletcher, Sarah; Hutabarat, Windo; Prabhu, Vinayak.

Advances in Intelligent Systems and Computing: Managing the Enterprise of the Future. ed. / C Schlick; S Trzcieliński . Springer, 2016. p. 217-228 Chapter 20 (Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future; Vol. 490).

Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

TY - CHAP

T1 - Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance

AU - Mgbemena, Chika Edith

AU - Oyekan, John

AU - Tiwari, Ashutosh

AU - Xu, Yuchun

AU - Fletcher, Sarah

AU - Hutabarat, Windo

AU - Prabhu, Vinayak

N1 - © 2016 Springer Publishing. This is a post-peer-review, pre-copyedit version of an article published in [insert journal title]. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-41697-7_20

PY - 2016/7/10

Y1 - 2016/7/10

N2 - Manual handling involves transporting of load by hand through lifting or lowering and operators on the manufacturing shop floor are daily faced with constant lifting and lowering operations which leads to Work-Related Musculoskeletal Disorders. The trend in data collection on the Shop floor for ergonomic evaluation during manual handling activities has revealed a gap in gesture detection as gesture triggered data collection could facilitate more accurate ergonomic data capture and analysis. This paper presents an application developed to detect gestures towards triggering real-time human motion data capture on the shop floor for ergonomic evaluations and risk assessment using the Microsoft Kinect. The machine learning technology known as the discrete indicator—precisely the AdaBoost Trigger indicator was employed to train the gestures. Our results show that the Kinect can be trained to detect gestures towards real-time ergonomic analysis and possibly offering intelligent automation assistance during human posture detrimental tasks.

AB - Manual handling involves transporting of load by hand through lifting or lowering and operators on the manufacturing shop floor are daily faced with constant lifting and lowering operations which leads to Work-Related Musculoskeletal Disorders. The trend in data collection on the Shop floor for ergonomic evaluation during manual handling activities has revealed a gap in gesture detection as gesture triggered data collection could facilitate more accurate ergonomic data capture and analysis. This paper presents an application developed to detect gestures towards triggering real-time human motion data capture on the shop floor for ergonomic evaluations and risk assessment using the Microsoft Kinect. The machine learning technology known as the discrete indicator—precisely the AdaBoost Trigger indicator was employed to train the gestures. Our results show that the Kinect can be trained to detect gestures towards real-time ergonomic analysis and possibly offering intelligent automation assistance during human posture detrimental tasks.

U2 - 10.1007/978-3-319-41697-7_20

DO - 10.1007/978-3-319-41697-7_20

M3 - Other chapter contribution

SN - 978-3-319-41696-0

T3 - Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future

SP - 217

EP - 228

BT - Advances in Intelligent Systems and Computing

A2 - Schlick, C

A2 - Trzcieliński , S

PB - Springer

ER -

Mgbemena CE, Oyekan J, Tiwari A, Xu Y, Fletcher S, Hutabarat W et al. Gesture Detection Towards Real-Time Ergonomic Analysis for Intelligent Automation Assistance. In Schlick C, Trzcieliński S, editors, Advances in Intelligent Systems and Computing: Managing the Enterprise of the Future. Springer. 2016. p. 217-228. Chapter 20. (Advances in Ergonomics of Manufacturing: Managing the Enterprise of the Future). https://doi.org/10.1007/978-3-319-41697-7_20