AI-Based Decision Support for Helmet Detection and Safety Monitoring in Construction Sites

Abstract

This paper explores the application of advanced deep learning models, particularly YOLOv7, for helmet detection in construction sites to enhance workplace safety. The study evaluates YOLOv7's performance through key performance metrics, demonstrating its effectiveness in accurately detecting workers wearing helmets. A comparative analysis with YOLOv8 highlights YOLOv7’s superior performance in detection accuracy and computational efficiency, making it a practical choice for resource-constrained environments. Despite challenges such as adapting to dynamic and complex construction site conditions, YOLOv7 proves to be a reliable and efficient tool in real-time safety monitoring. The findings suggest that YOLOv7-based helmet detection systems can significantly reduce human error, improve worker safety, and contribute to lowering incident rates. Thus, the results emphasize the potential of deep learning in transforming safety protocols, ensuring regulatory compliance, and fostering a culture of accountability in construction.