Traffic Owl
AI-supported traffic light system for pedestrian crossings
Overview
Traffic Owl is a camera-based, adaptive traffic control system that responds to real-time road events using object detection and segmentation. Developed in collaboration with Yunex Traffic as part of a student program, the project aims to reduce waiting times and dynamically coordinate pedestrian, car, and tram traffic..
Challenge
Fixed traffic light cycles often conflict with real-world dynamics: large groups of pedestrians arrive simultaneously, waiting times become unnecessarily long, and unsafe crossing behavior can occur — especially at tram interchanges.
Concept & Implementation
The system uses AI-based detection to identify pedestrians and analyze their behavior in real time. Based on this data, traffic light phases are dynamically adjusted. The prototype processes live traffic flows, adaptively controls signal timing, and provides visual feedback to make its decisions transparent — resulting in reduced waiting times and smoother traffic flow.
Showroom