Mobile Application Utilizing YOLO for Analysis and Monitoring of PPE Usage in a Manufacturing Plant in Lima

Ruiz Cubillas L.; Tuesta Yoplac O.J.; Rosales Caururu A. · Lecture Notes in Networks and Systems (2026) · DOI: 10.1007/978-3-032-26217-2_4

Resumen

This study discusses an urgent subject: that non-compliance with personal protective equipment (PPE) causes great occupational injuries and fatalities worldwide. Every year, workplace accidents directly cause about 330,000 deaths. These incidents also represent a significant economic loss, accounting for around 4% of global GDP per year. The study proposes a mobile application that integrates YOLOv8 system for the real-time detection of PPE compliance and utilizes Azure-based infrastructure for video transmission and data processing. The solution is used as a Software-as-a-Service (SaaS) architecture enabling scalability, reliability, and ease of implementation across industrial environments. Contrary to conventional systems for PPE monitoring, which are based on manual spot checks, according to this study, the device provides continuous monitoring by uploading the video from industrial cameras via Raspberry Pi edge devices all the way to the cloud, and automatic analysis of PPE compliance using deep learning techniques. The app provides management with real-time notifications and brief compliance summaries directly via the mobile application, so it can react quickly before minor problems escalate. Different trials in industrial setups confirmed that this detection method was capable of sustaining accuracy above 90%. This indicates that strategy could actually improve job site safety and minimize monitoring lag times. Future work will consist of improving the detection performance to a further level and the model will be adapted for common application in various domains—potentially not limited to manufacturing sites. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad Peruana de Ciencias Aplicadas