Improving Workplace Safety in the Cargo Industry through Posture Monitoring using Mediapipe and Machine Learning

Cobb B. S., Candan F.

17th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2023, Hammamet, Tunus, 20 - 23 Eylül 2023 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/inista59065.2023.10310609
  • Basıldığı Şehir: Hammamet
  • Basıldığı Ülke: Tunus
  • Anahtar Kelimeler: Image Processing, Machine Learning, Mediapipe, OpenCV, Python
  • Erciyes Üniversitesi Adresli: Hayır

Özet

This research reveals the potential of Mediapipe with machine learning methods in addressing the critical need for real-time posture monitoring, offering a promising solution for creating secure work environments and improving health and safety conditions not only in the cargo industry but also in other fields, such as healthcare, sports, and industry. The findings indicate that the Random Forest Classifier demonstrates the highest accuracy in classifying untrained movements, indicating its potential for developing a posture correction warning system. Further research is needed to validate the findings and explore real-world applications. Overall, this study contributes to the advancement of workplace safety and sets the foundation for future developments in posture monitoring systems using Mediapipe and machine learning using Python programming.