Abstract
In recent years, human pose estimation has become a very important research topic in the context of control engines, and exoskeletons. In this paper, we propose a Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) based Hybrid Deep Neural network, aimed to estimate human pose while handling of loads. The proposed model is capable to identify three such activities, i.e. load lifting from the ground, load shifting, and uplifting of the load. For this purpose, a inertial sensor unit (IMU)-based system was developed to collect the raw data. Next, to obtain more robust and accurate results, Kalman filtering has been used as a fusion technique. Rigorous fine-tuning and simulations show that the model obtained from the Kalman filtering achieves better results as compared to the raw data. Our proposed model can classify the target activities with a test accuracy of 86%.
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
H.F. Nweke, Y.W. Teh, G. Mujtaba, U.R. Alo, M.A. Al-garadi, Multi-sensor fusion based on multiple classifier systems for human activity identification. Human-Centric Comput. Inf. Sci. 9(1), 34 (2019)
S. Ashry, R. Elbasiony, W. Gomaa, An LSTM-based descriptor for human activities recog-nition using IMU sensors, in Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics, ICINCO, vol. 1 (2018), pp. 494–501
L.A. Mateos, Characterizing Lifting and Lowering Activities with Insole FSR sensors in industrial exoskeletons (2017). arXiv:1706.05440
S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Y. Kim, H. Bang, Introduction to Kalman filter and its applications by Submitted: April 26th 2018, Reviewed: July 30th 2018, Published: November 5th 2018. https://doi.org/10.5772/intechopen.80600
European foundation for the improvement of living and working conditions, in First Findings: Sixth European Working Conditions Survey: Résu-mé (Publications Office, 2015)
D. Anxo, C. Franz, A. Kümmerling, Working time and work–life balance in a life course perspective: a report based on the fifth European working conditions survey (Eurofound, 2013)
European Foundation, for the improvement of living and working conditions and others, in First Findings: Sixth European Working Conditions Survey (Publications Office, 2015). ISBN: 978-92-897-1429-7. https://doi.org/10.2806/59106
D. Anxo, C. Franz, A. Kümmerling, Working time and work–life balance in a life course perspective: a report based on the fifth European working conditions survey (Eurofound, 2013). http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-30766
Acknowledgements
Supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy - EXC 2120/1 - 390831618.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bances, E., Karol, A.M.A., Schneider, U. (2022). LSTM and CNN Based IMU Sensor Fusion Approach for Human Pose Identification in Manual Handling Activities. In: Moreno, J.C., Masood, J., Schneider, U., Maufroy, C., Pons, J.L. (eds) Wearable Robotics: Challenges and Trends. WeRob 2020. Biosystems & Biorobotics, vol 27. Springer, Cham. https://doi.org/10.1007/978-3-030-69547-7_74
Download citation
DOI: https://doi.org/10.1007/978-3-030-69547-7_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69546-0
Online ISBN: 978-3-030-69547-7
eBook Packages: EngineeringEngineering (R0)