NSF/USDOT Partnership for Exploratory Research - ICSST: Real-time Collision Warning at Traffic Intersections

Papanikolopoulos

Institution: University of Minnesota - Twin Cities.

NSF/USDOT: Real-time collision Warning at Traffic Intersections

Collisions between vehicles at urban and rural intersections account for nearly a third of all reported crashes in the United States. This research entails developing some of the components of a real-time system which uses cameras to continuously gather traffic data at intersections (e.g., vehicle speeds, positions, trajectories, accelerations/decelerations, vehicle sizes, signal status, etc.), applies efficient algorithmic techniques to detect potential collisions and near-misses, and then issues suitable countermeasures. At this stage, the goal is to establish the feasibility of this approach using both computer simulations and field tests at actual intersections (urban intersections in the Twin Cities---Minneapolis and St. Paul, MN). The proposed work has as main emphasis the design of efficient and robust computer vision and collision-detection algorithms that can address the intersection collision warning problem.