Adaptive & Coordinated Traffic Signal System

Traffic congestion is a major issue all over the world. Despite numerous research the aforesaid problem has not optimally and sufficiently solved. In this research we introduce an adaptive traffic signaling system based on road traffic density to facilitate optimal traffic signal control as well as effective traffic management. We also proposed effective coordination of traffic. The proposed scheme uses live video as an input provided to a deep Q network to provide adaptive phase timings as the system output. Compared to the existing work, we introduced per car unit (PCU) as a novel input to represent the effect of each vehicle type on the traffic condition. Extensive tests on real time data amply proves that the proposed system enhances the average speed of traffic by 82% in a single junction scenario and 18% when considering the multiple junction scenario. Further research in progress to identify and accommodate emergency situations: accidents and high priority vehicle as well as to consider movement patterns of pedestrians as an input to the system.