Road safety is a critical issue, with efforts focused on reducing injuries and fatalities from traffic accidents. This study introduces a novel method for detecting helmets on motorcycle riders using YOLOv8, a state-of-the-art object detection framework. Leveraging real-time detection, the system enhances traffic monitoring and promotes motorcycle rider safety. Key processes such as data preparation, model training, and deployment are discussed, with rigorous testing showcasing YOLOv8’s robustness across diverse conditions. Comparative analysis with models like YOLOv7, Faster R-CNN, SSD, and Retinanet confirms YOLOv8’s superior accuracy in precision, recall, F1-score, and mAP, validating its effectiveness for real-time traffic applications.