An Autonomous Helmet Detection Model in Diversified Application Areas using DNN-YOLOv8 Technique

An increasing need for cutting-edge technology that can improve situational awareness and reduce hazards has resulted from the growing significance of safety in a variety of fields. This paper combines the state-of-the-art YOLOv8 (You Only Look Once version 8) technique with the power of Deep Neural Networks (DNN) to provide a new solution for autonomous helmet identification across a variety of application areas. The goal of the project is to create and apply a reliable helmet identification model that can function independently in real-time situations. The paper investigates the difficulties in detecting helmets in a variety of settings, such as traffic management, construction sites, factories and thermal power plants. The suggested model seeks to improve safety regulations and risk management techniques in a variety of contexts by tackling these issues.