Real-Time Traffic Camera-Light Control Systems for Intersections Subject to Accidents: A Petri Net Approach

Petri nets (PNs) are well utilized as a visual and mathematical formalism to model discrete event systems. Some extensions to PNs enhance their modeling capability. This work uses Time Petri nets (TPNs) and Synchronized Petri nets (SPNs) to design a traffic control system (ITCS) for intersections dealing with accidents such that emergency response is provided and additional accidents are prevented. It includes a camera surveillance subsystem (CSS) and a traffic light control subsystem (TLCS) simulated by using SPNs and TPNs, respectively: a multi-camera surveillance mechanism is established to sense and detect the accident, synchronously, and then according to the information of the accident, corresponding traffic light control policies are carried out to prevent additional accidents from happening. A reach ability tree method is adopted to demonstrate how the models are used to enforce the phase of traffic transitions, and verify their important properties. To our knowledge, this is the first work that employs PNs to model and design the real-time traffic control system for intersections facing accidents, and to perform the cooperation of cameras and traffic lights. This helps enhance the state of the art in real-time traffic accident detection and traffic safety at an intersection.