Automatic Traffic Red-Light Violation Detection Using AI

Our research is the design of a traffic signal violation detection system using machine learning that learns to prevent increasing number road accidents. The optimized in terms accuracy by region interest and location vehicle with red-signal state. By modifying some parameters YOLOV5s re-training COCO dataset, we can create model which be predicted high 82% for identification, 90% status change up 86% detection. This used red light will help police on management.