YOLOv8 based Traffic Signal Detection in Indian Road
Supratim Biswas, Suvojit Acharjee, Asfak Ali, Sheli Sinha Chaudhari
Abstract
In the contemporary era of automation, the efficient utilization of technology is of paramount importance. However, despite these advancements, incidents such as road accidents persist as a critical concern. This study endeavors to streamline traffic signal detection as a proactive measure to mitigate road accidents and enhance road safety. The Smart Traffic Signal Detection System has been designed to identify traffic signals and proactively alert drivers, particularly in high-traffic situations. Additionally, the system assists in monitoring and recording traffic signal violators, providing valuable data for relevant authorities. This research introduces a novel system, utilizing the You Only Look Once (YOLO) algorithm within a Convolutional Neural Network (CNN) framework, to enhance signal detection accuracy. Real-time data collected from various locations across the city of Kolkata forms the foundation for this system’s development.