Abstract
Work-related musculoskeletal disorders are a very impactful problem, both socially and economically, in the manufacturing sector. To control their effect, standardised methods and technologies for ergonomic assessment have been developed. The main technologies used are inertial sensors and vision-based systems. The former are accurate and reliable, but invasive and not affordable for many companies. The latter use machine learning algorithms to detect human pose and assess ergonomic risks. In this paper, using data collecting by reproducing the working environment in LUBE, the major Italian kitchen manufacturer, we propose SPECTRE (Sensor-independent Parallel dEep ConvoluTional leaRning nEtwork): a fully sensor-independent learning model based on convolutional networks to classify postures in the workplace. This system assesses ergonomic risks in major body segments through Deep Learning with a minimal impact. SPECTRE’s performance is evaluated using established metrics for imbalanced data (precision, recall, F1-score and area under the precision-recall curve). Overall, SPECTRE shows good performance and, thanks to an agnostic explainable machine learning method, is able to extrapolate which patterns are significant in the input.
Similar content being viewed by others
Availability of data and code
The datasets and the code used and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Abobakr, A., Nahavandi, D., Hossny, M., Iskander, J., Attia, M., Nahavandi, S., et al. (2019). RGB-D ergonomic assessment system of adopted working postures. Applied Ergonomics, 80, 75–88. https://doi.org/10.1016/j.apergo.2019.05.004.
Al-Amin, M., Qin, R., Moniruzzaman, M., Yin, Z., Tao, W., & Leu, M. (2021). An individualized system of skeletal data-based CNN classifiers for action recognition in manufacturing assembly. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-021-01815-x.
Andrade-Ambriz, Y. A., Ledesma, S., Ibarra-Manzano, M. A., Oros-Flores, M. I., & Almanza-Ojeda, D. L. (2022). Human activity recognition using temporal convolutional neural network architecture. Expert Systems with Applications, 191, 116287. https://doi.org/10.1016/j.eswa.2021.116287.
Battini, D., Berti, N., Finco, S., Guidolin, M., Reggiani, M., & Tagliapietra, L. (2022). WEM-Platform: A real-time platform for full-body ergonomic assessment and feedback in manufacturing and logistics systems. Computers & Industrial Engineering, 164, 107881. https://doi.org/10.1016/j.cie.2021.107881.
Battini, D., Persona, A., & Sgarbossa, F. (2014). Innovative real-time system to integrate ergonomic evaluations into warehouse design and management. Computers & Industrial Engineering, 11, 77. https://doi.org/10.1016/j.cie.2014.08.018.
Bibi, S., Anjum, N., & Sher, M. (2018). Automated multi-feature human interaction recognition in complex environment. Computers in Industry, 99, 282–293. https://doi.org/10.1016/j.compind.2018.03.015.
Biecek, P., & Burzykowski, T. (2021). Explanatory model analysis. Chapman and Hall/CRC.
Bordoni, L., Petracci, I., Pelikant-Malecka, I., Radulska, A., Piangerelli, M., Samulak, J. J., et al. (2021). Mitochondrial DNA copy number and trimethylamine levels in the blood: New insights on cardiovascular disease biomarkers. The FASEB Journal, 35(7), e21694. https://doi.org/10.1096/fj.202100056R.
Chan, V. C. H., Ross, G. B., Clouthier, A. L., Fischer, S. L., & Graham, R. B. (2022). The role of machine learning in the primary prevention of work-related musculoskeletal disorders: A scoping review. Applied Ergonomics, 98, 103574. https://doi.org/10.1016/j.apergo.2021.103574.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953.
Chen, C., Wang, T., Li, D., & Hong, J. (2020). Repetitive assembly action recognition based on object detection and pose estimation. Journal of Manufacturing Systems, 55, 325–333. https://doi.org/10.1016/j.jmsy.2020.04.018.
Clark, R. A., Mentiplay, B. F., Hough, E., & Pua, Y. H. (2019). Three-dimensional cameras and skeleton pose tracking for physical function assessment: A review of uses, validity, current developments and Kinect alternatives. Gait & Posture, 68, 193–200. https://doi.org/10.1016/j.gaitpost.2018.11.029.
Damle, R., Gurjar, A., Joshi, A., & Nagre, K. (2015). Human body skeleton detection and tracking. Human Body Skeleton Detection and Tracking, 3, 222–225.
Diego-Mas, J. A., Poveda-Bautista, R., & Garzon-Leal, D. (2017). Using RGB-D sensors and evolutionary algorithms for the optimization of workstation layouts. Applied Ergonomics, 65, 530–540. https://doi.org/10.1016/j.apergo.2017.01.012.
European Agency for Safety and Health at Work. (2019). Work-related musculoskeletal disorders: Prevalence, costs and demographics in the EU. Publications Office of the European Union.
Fernández, M. M., Álvaro Fernández, J., Bajo, J. M., & Delrieux, C. A. (2020). Ergonomic risk assessment based on computer vision and machine learning. Computers & Industrial Engineering, 149, 106816. https://doi.org/10.1016/j.cie.2020.106816.
Gamra, M. B., & Akhloufi, M. A. (2021). A review of deep learning techniques for 2D and 3D human pose estimation. Image and Vision Computing, 114, 104282. https://doi.org/10.1016/j.imavis.2021.104282.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys (CSUR), 51(5), 1–42. https://doi.org/10.1145/3236009.
Kim, W., Sung, J., Saakes, D., Huang, C., & Xiong, S. (2021). Ergonomic postural assessment using a new open-source human pose estimation technology (OpenPose). International Journal of Industrial Ergonomics, 84, 103164. https://doi.org/10.1016/j.ergon.2021.103164.
Korhan, O., & Memon, A. A. (2019). Introductory chapter: work-related musculoskeletal disorders. In Work-related musculoskeletal disorders. IntechOpen.
Li, C., Zhong, Q., Xie, D., & Pu, S. (2017) Skeleton-based action recognition with convolutional neural networks. In 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) (pp. 597–600). IEEE.
Li, L., Martin, T., & Xu, X. (2020). A novel vision-based real-time method for evaluating postural risk factors associated with musculoskeletal disorders. Applied Ergonomics, 87, 103138. https://doi.org/10.1016/j.apergo.2020.103138.
Lim, S., & D’Souza, C. (2020). A narrative review on contemporary and emerging uses of inertial sensing in occupational ergonomics. International Journal of Industrial Ergonomics, 76, 102937. https://doi.org/10.1016/j.ergon.2020.102937.
Liu, B., Cai, H., Ju, Z., & Liu, H. (2020). Multi-stage adaptive regression for online activity recognition. Pattern Recognition, 98, 107053. https://doi.org/10.1016/j.patcog.2019.107053.
Liu, J., Wang, Y., Liu, Y., Xiang, S., & Pan, C. (2020). 3D PostureNet: A unified framework for skeleton-based posture recognition. Pattern Recognition Letters, 140, 143–149. https://doi.org/10.1016/j.patrec.2020.09.029.
Lopez, M., Beurton-Aimar, M., Diallo, G., & Maabout, S. (2022). A simple yet effective approach for log based critical errors prediction. Computers in Industry, 137, 103605. https://doi.org/10.1016/j.compind.2021.103605.
Malchaire, J., Gauthy, R., Piette, A., & Strambi, F. (2011). A classification of methods for assessing and/or preventing the risks of musculoskeletal disorders. European Trade Union Institute: ETUI.
Mancini, A., Vito, L., Marcelli, E., Piangerelli, M., De Leone, R., Pucciarelli, S., et al. (2020). Machine learning models predicting multidrug resistant urinary tract infections using DsaaS. BMC Bioinformatics, 21(10), 1–12. https://doi.org/10.1186/s12859-020-03566-7.
McAtamney, L., & Nigel, Corlett E. (1993). RULA: A survey method for the investigation of work-related upper limb disorders. Applied Ergonomics, 24(2), 91–99. https://doi.org/10.1016/0003-6870(93)90080-S.
Merino, G., da Silva, L., Mattos, D., Guimarães, B., & Merino, E. (2019). Ergonomic evaluation of the musculoskeletal risks in a banana harvesting activity through qualitative and quantitative measures, with emphasis on motion capture (Xsens) and EMG. International Journal of Industrial Ergonomics, 69, 80–89. https://doi.org/10.1016/j.ergon.2018.10.004.
Nayak, G. K., & Kim, E. (2021). Development of a fully automated RULA assessment system based on computer vision. International Journal of Industrial Ergonomics, 86, 103218. https://doi.org/10.1016/j.ergon.2021.103218.
Peppoloni, L., Filippeschi, A., Ruffaldi, E., & Avizzano, C. A. (2016). A novel wearable system for the online assessment of risk for biomechanical load in repetitive efforts. International Journal of Industrial Ergonomics, 52, 1–11. https://doi.org/10.1016/j.ergon.2015.07.002 (New Approaches and Interventions to Prevent Work Related Musculoskeletal Disorders).
Piñero-Fuentes, E., Canas-Moreno, S., Rios-Navarro, A., Domínguez-Morales, M., Sevillano, J. L., & Linares-Barranco, A. (2021). A deep-learning based posture detection system for preventing telework-related musculoskeletal disorders. Sensors. https://doi.org/10.3390/s21155236.
Regazzoni, D., Vecchi, G. D., & Rizzi, C. (2014). RGB cams vs RGB-D sensors: Low cost motion capture technologies performances and limitations. Journal of Manufacturing Systems, 33(4), 719–728. https://doi.org/10.1016/j.jmsy.2014.07.011.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) “Why should i trust you?” Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144).
Seo, J., & Lee, S. (2021). Automated postural ergonomic risk assessment using vision-based posture classification. Automation in Construction, 128, 103725. https://doi.org/10.1016/j.autcon.2021.103725.
Slembrouck, M., Luong, H. Q., Gerlo, J., Schütte, K., Cauwelaert, DV., Clercq, D.D., et al. (2020). Multiview 3D markerless human pose estimation from OpenPose skeletons. In Advanced Concepts for Intelligent Vision Systems (pp. 166–178).
Tu, H., Wang, C., & Zeng, W. (2020) End-to-end estimation of multi-person 3D poses from multiple cameras. CoRR. abs/2004.06239. https://doi.org/10.1007/978-3-030-58604-1_29. arXiv:2004.06239.
Vignais, N., Miezal, M., Bleser, G., Mura, K., Gorecky, D., & Marin, F. (2013). Innovative system for real-time ergonomic feedback in industrial manufacturing. Applied Ergonomics, 44(4), 566–574. https://doi.org/10.1016/j.apergo.2012.11.008.
Vlasic, D., Adelsberger, R., Vannucci, G., Barnwell, J., Gross, M., Matusik, W., et al. (2007). Practical motion capture in everyday surroundings. ACM Transactions on Graphics, 10(1145/1276377), 1276421.
Xiao, B., Xiao, H., Wang, J., & Chen, Y. (2022). Vision-based method for tracking workers by integrating deep learning instance segmentation in off-site construction. Automation in Construction, 136, 104148. https://doi.org/10.1016/j.autcon.2022.104148.
Xu, H., Bazavan, EG., Zanfir, A., Freeman, B., Sukthankar, R., & Sminchisescu, C. (2020) GHUM & GHUML: Generative 3D human shape and articulated pose models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6184–6193).
Yadav, S. K., Tiwari, K., Pandey, H. M., & Akbar, S. A. (2021). A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions. Knowledge-Based Systems, 223, 106970. https://doi.org/10.1016/j.knosys.2021.106970.
Yoshikawa, Y., Shishido, H., Suita, M., Kameda, Y., & Kitahara, I. (2021) Shot detection using skeleton position in badminton videos. In International Workshop on Advanced Imaging Technology (IWAIT) 2021 (Vol. 11766, p. 117661K). International Society for Optics and Photonics.
Zhu, S., Fang, Z., Wang, Y., Yu, J., & Du, J. (2019). Multimodal activity recognition with local block CNN and attention-based spatial weighted CNN. Journal of Visual Communication and Image Representation, 60, 38–43. https://doi.org/10.1016/j.jvcir.2018.12.026.
Acknowledgements
This work is partly funded by the URRÁ project “Usability of Robots and Reconfigurbility of processes: enabling technologies and use cases”, on the topics of User-Centered Manufacturing and Industry 4.0, which is part of the project EU ERDF, POR MARCHE Region FESR 2014/2020-AXIS 1-Specific Objective 2-ACTION 2.1, “HD3Flab-Human Digital Flexible Factory of the Future Laboratory”, coordinated by the Polytechnic University of Marche.
Author information
Authors and Affiliations
Contributions
MC: conceptulization of this study, Methodology, Data curation, Writing Paper. FC: funding acquisition, writing—rerview & editing. MG: funding acquisition, writing—rerview & editing. GM: data curation, software. LM: supervision writing—review & editing. AP: conceptualization of this study, methodology, investigation, writing paper. MP: conceptualization of this study, methodology, formal analysis, software, writing paper.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ciccarelli, M., Corradini, F., Germani, M. et al. SPECTRE: a deep learning network for posture recognition in manufacturing. J Intell Manuf 34, 3469–3481 (2023). https://doi.org/10.1007/s10845-022-02014-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-022-02014-y