Intelligent Traffic Signal Optimization via Real-Time Density Estimation and Vehicle Counting with Canny Edge Detection and YOLOv8

By and large, traffic congestion is a chronic problem in urban transportation systems, because it causes elongation of travel time, additional fuel consumption, and amplified environmental pollution. However, traditional traffic signal control systems, such as fixed time interval control or rudimentary sensors, adapt poorly to real time traffic conditions, making problems worse. An intelligent traffic signal optimization system based on real time traffic density estimation and vehicle counting is proposed by this research. The system implements Canny edge detection to enable traffic density estimation, and YOLOv8 for distinguishing and counting vehicles. The system attempts to reduce congestion as well as improve traffic flow by dynamically adapting traffic signal timings to real time data. To ensure robustness of the model in various traffic scenarios, real world traffic video datasets will be utilized in order to train and evaluate the model. Results from this study would greatly help develop traffic management systems to enhance urban transportation and could offer a scalable and economical solution to transportation problems in an urban environment.