Deep learning-based fatigue detection using kinematic information from videos

Long, Da et Yang, Sheng. 2025. « Deep learning-based fatigue detection using kinematic information from videos ». In Proceedings of the CSME-CFDSC-CSR 2025 International Congress (Montreal, QC, Canada, May 25-28, 2025) Coll. « Progress in Canadian Mechanical Engineering », vol. 8. https://doi.org/10.82417/6mtg-8x59 :

[thumbnail of 12 - Deep learning-based fatigue detecti.pdf]

Prévisualisation

PDF
12 - Deep learning-based fatigue detecti.pdf - Version publiée
Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur.
Télécharger (3MB) | Prévisualisation

Résumé

Detecting human fatigue in manufacturing scenarios has been a long-standing research focus, driven by its profound impact on worker welfare. Fatigue contributes to work-related accidents and long-term musculoskeletal disorders, underscoring the need for effective monitoring solutions. With advancements in deep learning and image processing technologies, fatigue detection methods are increasingly adopting noninvasive approaches. Such solutions minimize disruptions to workers’ activities while ensuring accurate monitoring. In this paper, we proposed a deep learning-based method that leverages motion and posture data extracted from videos to detect worker fatigue. This approach is both noninvasive and cost-effective, offering practical benefits for industrial applications.

Type de document:	Compte rendu de conférence
Éditeurs:	Éditeurs ORCID Hof, Lucas A. NON SPÉCIFIÉ Di Labbio, Giuseppe NON SPÉCIFIÉ Tahan, Antoine NON SPÉCIFIÉ Sanjosé, Marlène NON SPÉCIFIÉ Lalonde, Sébastien NON SPÉCIFIÉ Demarquette, Nicole R. NON SPÉCIFIÉ
Date de dépôt:	18 déc. 2025 15:16
Dernière modification:	18 déc. 2025 15:16
URI:	https://espace2.etsmtl.ca/id/eprint/32448

Actions (Authentification requise)

Dernière vérification avant le dépôt