Dynamic traffic light controller using machine vision and optimization algorithms

This paper presents a fuzzy traffic controller that in an autonomous, centralized and optimal way, manages traffic flow in a group of intersections. The system obtains information from a network of cameras and through machine vision algorithms can detect the number of vehicles in each of the roads. Using this information, the fuzzy system selects the sequence of phases that optimize traffic flow globally. To evaluate the performance of the controller, a scenario was developed where it was possible to simulate through artificially created videos two adjacent intersections. System performance was compared versus fixed time controllers as they are currently the most used in the city of Bogota. As a control variable it was used the average waiting time of each vehicle. The results show that the system performance increases by about 20% over situations with heavy traffic conditions and that the controller is able to adapt smoothly to different flow changes.