Abstract
Workplace safety in high-risk industrial sectors, such as heavy machinery maintenance, remains a critical challenge due to the improper use or omission of personal protective equipment (PPE). This study proposes an intelligent system based on computer vision and artificial intelligence, complemented by electronic devices for real-time detection and monitoring of helmet, vest, glove, and boot use. The research follows a quantitative approach with a quasi-experimental design, validated through controlled tests using a mannequin equipped with protective elements to simulate real working conditions. The system uses a camera connected to a Raspberry Pi running the YOLOv8 detection model, achieving 96.5% accuracy and 91.8% recall on a test set of 300 images. The model was trained on 2,250 images and validated with an additional 300. Detection results are transmitted to an ESP32 microcontroller, which controls local alerts through LEDs, an LCD screen, and a buzzer, as well as automatic notifications via Telegram over Wi-Fi. A sliding window filtering technique is applied to reduce false positives, improving monitoring reliability and reinforcing a preventative safety culture. It is concluded that integrating artificial intelligence into automated PPE detection offers an efficient, practical, and replicable solution for improving workplace safety in industrial environments.