Abstract
Time study is a technique to analyze human action based on ergonomic discipline and has been widely applied in various manufacturing sites. How to identify the standard operation by personnel and extract the operating time duration of each action is an emerging research problem in the human action recognition (HAR) research domain. In the real-world manufacturing, the operators actually conduct exceptional actions beyond the designed operation under standard operating procedures (SOP). These exceptional actions will lead to miss-recognition and disturb the measurement of action time. In this research, an exceptional action detection framework was proposed to detect exceptional actions that are not defined or should be avoided during HAR. First, the skeleton of human workers was computed, and Spatial-Temporal Graph Convolution Network model was implemented to provide the score of each action label. Then, the exceptional action can be classified by score correction with multiple support vector machine (SVM) classifiers. A dataset was created by simulating the actions which may occur during the drilling process. The preliminary experiment shows that the proposed framework is able to detect SOP and exceptional actions with up to 79.1% accuracy
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Andris, F., Benjamin, W.N.: Niebel's Methods, Standards, and Work Design, 13e. McGraw-Hill Education (2013)
Golabchi, A., Han, S., AbouRizk, S.: A simulation and visualization-based framework of labor efficiency and safety analysis for prevention through design and planning. Autom. Constr. 96, 310–323 (2018)
Dang, L.M., et al.: Sensor-based and vision-based human activity recognition: A comprehensive survey. Pattern Recogn. 108, 107561 (2020)
Shi, L., et al.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Bouindour, S., et al.: Abnormal event detection using convolutional neural networks and 1-class SVM classifier. In: 8th International Conference on Imaging for Crime Detection and Prevention (ICDP 2017) (2017)
Amraee, S., et al.: Abnormal event detection in crowded scenes using one-class SVM, 12(6), 1115–1123 (2018)
Ionescu, R.T., et al.: Detecting Abnormal Events in Video Using Narrowed Normality Clusters. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (2019)
Cao, Z., et al.: Realtime multi-person 2D pose estimation using part affinity fields. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Hawaii, USA (2017)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence. Hilton New Orleans Riverside, NewOrleans, Louisiana, USA (2018)
Wang, L.: Support vector machines: theory and applications, 177. Springer Science & Business Media (2005)
Acknowledgment
We appreciate the financial support from the Ministry of Science and Technology of Taiwan, R.O.C. (Contract No. 109–2221-E-011 -101), and the Center for Cyber-Physical System Innovation” from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan. We also thank Wang Jhan-Yang Charitable Trust Fund (Contract No. WJY 2020-HR-01) for the generosity of financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, CL., Hsu, SC., Hsu, YW., Kang, YC. (2021). Human Action Recognition on Exceptional Movement of Worker Operation. In: Trzcielinski, S., Mrugalska, B., Karwowski, W., Rossi, E., Di Nicolantonio, M. (eds) Advances in Manufacturing, Production Management and Process Control. AHFE 2021. Lecture Notes in Networks and Systems, vol 274. Springer, Cham. https://doi.org/10.1007/978-3-030-80462-6_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-80462-6_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80461-9
Online ISBN: 978-3-030-80462-6
eBook Packages: EngineeringEngineering (R0)