

Nikos Papanikolopoulos, Professor, Computer Science and Engineering
Traffic counts of bicycles and pedestrians are essential in a variety of tasks such as the design of traffic control schemes, the design and modification of intersections, and assessment of traffic measures such as stop signs and traffic signals. Manual counts are expensive and often not accurate. This project examines available technologies for automated counting and highlights the strengths and the pitfalls of each one of them. The goal is to create a matrix of methods and protocol which can be used by different municipalities and traffic engineers to evaluate the claims of the various vendors of traffic counters. This research also investigates counting systems based on computer vision technologies, in light of falling hardware costs and the fact that camera networks are becoming extremely common.