Traffic monitoring and modeling for Intersection Safety

The INTERSAFE-2 project aims to develop and demonstrate a Cooperative Intersection Safety System that is able to significantly reduce injury and fatal accidents at intersections. The cooperative sensor data fusion is based on state-of-the-art and advanced on-board sensors for object recognition and relative localisation, a standard navigation map and information from other road users, infrastructure sensors and traffic lights. We created a traffic safety model for the INTERSAFE-2 system. The system incorporates a high level fusion module and local dynamic maps database that store static intersection topology. Furthermore, risk assessment from the infrastructure side has been performed in order to detect potentially dangerous situations, and to determine when the system should give a warning in order to prevent a possible collision. To evaluate the safety algorithm, video sequences of two intersections in Helsinki are used, which were processed with a generic tool for image processing and traffic monitoring.