Worker safety is a critical concern in industrial sectors such as construction, manufacturing, and maintenance, where accidents often occur due to the absence or improper use of personal protective equipment (PPE) like helmets and safety harnesses. Manual monitoring of PPE compliance is time-consuming and prone to human error. To address this issue, this project proposes a Helmet and Harness Detection System using Artificial Intelligence (AI) and Computer Vision with the YOLOv8 deep learning model.

The system captures live video streams from surveillance cameras installed at industrial sites and processes them in real time to detect whether workers are wearing helmets and harnesses. YOLOv8, being a state-of-the-art object detection model, provides high accuracy and fast inference speed, making it suitable for real-time safety monitoring applications. The model is trained on a labeled dataset containing images of workers with and without safety gear to accurately classify compliance and violations. When a violation is detected, the system automatically generates an alert or notification to the safety supervisor through a connected dashboard or IoT device.