This research targeted the development of a fully automated, vision-based traffic light for pedestrians. In contrast to traditional solutions, this system leverages intent prediction to estimate which pedestrians are actually going to cross the road by analyzing both short-term and long-term trajectory cues. In this way, waiting times are decreased, paving the road for adaptive traffic light scheduling. In cooperation with the project partners MA33 and GPV, two generations of this automated pedestrian traffic light system (research periods 2014-2017 and 2021-2024) have been investigated.
