The Sailport Project: A Trilateral Approach to the Improvement of Workers’ Safety and Health in Ports
This work presents a novel method for the improvement of safety and health in ports. Traditional and consolidated approaches to this goal are based on questionnaires and training activities that Local Health Authorities and the National Institute for Insurance against Accidents offer to the personnel of the companies that work in the port. We propose to complement this method by means of quantitative and pervasive measuring of risks related to safety and health. For the former, we propose a system that measures the collision risk in relevant areas of the port by means of cameras. For the latter, workers wear inertial measurement units and EMG electrodes to estimate the biomechanical overload. The results of these three actions are then merged and presented to the selected companies to make corrective actions, in order to reduce the safety and health risks for the port workers.
KeywordsWorkers safety Work-related musculoskeletal disorders Biomechanical overload Machine learning Surveillance
We would like to thank the personnel of the Local Health Authorities involved in the project as well as the Port Authority of north Tyrrhenian Sea. Sailport is a project co-funded by INAIL, the Italian National Institute for Insurance against Accidents at Work, under the BRiC 2016 programme (ID24-2016).
- 1.Campo, G., Gulglielmi, A., Piz, C., Dei, M.: Approfondimento delle dinamiche, dei fattori causali e delle cause. In: Schede Informative del Sistema Informo (2017). ISBN 978-88-7484-523Google Scholar
- 2.Campo, G., Guglielmi, A., Marconi, M., Pianosi, G.: La ricostruzione delle cause e delle dinamiche infortunistiche negli ambienti di lavoro attraverso il modello Sbagliando s’impara. Prev. Oggi 2(1–2), 27–40 (2006)Google Scholar
- 3.Redmon, J., Farhadi, A.: Yolov3: An incremental improvement, arXiv (2018)Google Scholar
- 5.Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004). https://doi.org/10.1023/B:VISI.0000029664.99615.94CrossRefGoogle Scholar
- 6.Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs, CoRR, vol. abs/1606.00915 (2016). http://arxiv.org/abs/1606.00915
- 10.Peppoloni, L., Filippeschi, A., Ruffaldi, E., Avizzano, C.: A novel 7 degrees of freedom model for upper limb kinematic reconstruction based on wearable sensors. In: 11th International Symposium on Intelligent Systems and Informatics (SISY), vol. 52, pp. 105–110 (2013)Google Scholar
- 11.Ruffaldi, E., Peppoloni, L., Filippeschi, A.: Sensor fusion for complex articulated body tracking applied in rowing. Proc. Inst. Mech. Eng. Part P J. Sports Eng. Tehchnol. 229(2), 92–102 (2015)Google Scholar
- 13.Hignett, S., McAtamney, L.: Rapid entire body assessment. In: Handbook of Human Factors and Ergonomics Methods, pp. 97–108. CRC Press (2004)Google Scholar
- 19.Meredith, M., Maddock, S.: Motion capture file formats explained, vol. 211, pp. 241–244. Department of Computer Science, University of Sheffield (2001)Google Scholar