Helmet and Equipment Detection with Worker’s Mobility Tracker In Mining Sector Using YOLOv8 & LSTM

Monitoring personal protective equipment and compliance with safety procedures for mining operations is essential to ensuring personnel safety. Nevertheless, sending humans underground is impractical, as mining conditions are fast-changing and dangerous. Most of the existing systems are still not able to detect helmets, PPE, and the worker mobility in real-time, which are two critical aspects of safety. To overcome these challenges, this project bases its approach on enhancing monitoring and security by integrating machine learning technologies. Using YOLOv8, a cutting-edge object detection model, the system enables workers' helmet and PPE detection in real-time. This work also uses Long Short-Term Memory (LSTM), a special type of RNN, to track the behavior of workers within and over time. By reading the frames at 10 millisecond intervals, the system detects movement deviations be it unsafe movements or fatigue induced deviations and provides proactive measures for safety. The devised method reaches an outstanding accuracy of 95.9%, combining YOLOv8 and LSTM, which reduces human error and improves safety at the workplace. This state-of-the-art solution is not only providing continuous monitoring but is also increasing operational efficiency, thereby transforming safety solutions in the mining space.