Detection of personal equipment used in occupational safety with artificial intelligence based image processing techniques

Artificial intelligence (AI), has emerged as one of the most transformative technologies across various industries today. In particular, advances in computer vision have enabled real-time data analysis, offering solutions that directly impact human life. In this study, an application was developed to enhance worker safety using AI-powered object detection techniques. The research utilizes the "Railroad Worker Detection Dataset" available on the Kaggle platform to determine whether railway workers are wearing personal protective equipment (PPE)—specifically helmets and safety vests—based on real-time imagery. To this end, deep learning-based object detection algorithms YOLOv5, YOLOv7, and YOLOv8 were employed, and their performance was compared to identify the most effective solution. The findings indicate that the selected object detection models can accurately identify workers in various environments and detect the presence of safety equipment with high precision, thereby contributing to the prevention of occupational accidents. This study not only constitutes an academic research effort but also offers practical solutions that can be directly implemented in industrial settings to support the creation of safer working environments. Furthermore, it demonstrates the potential of deep learning-based object detection algorithms to be effectively utilized in the field of occupational health and safety.