Zürn, Marc (Mercedes-Benz), Rehborn, Hubert (Mercedes-Benz AG), Querfurth, Lennart (Mercedes-Benz AG), Hoyer, Robert (University of Kassel)

Data-Driven Traffic Phase Detection and Jam Resolution Analysis Using Spatial-Temporal Observations

Scheduled for presentation during the Regular Session "S32a-AI-Driven Traffic Monitoring, Safety, and Anomaly Detection" (FR-LM-T32), Friday, November 21, 2025, 11:10−11:30, Southport 2

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Understanding the emergence and resolution of traffic jams on highways remains a persistent challenge in traffic management. The study proposes a novel data-driven methodology to automatically detect and validate traffic phase transitions, with a particular focus on wide moving jams, and to quantify the corresponding downstream front propagation speed. Building on Kerner’s Three-Phase-Traffic-Theory, this study uses high-resolution datasets to perform a microscopic, lane-specific analysis of jam dynamics. The results quantify wide moving jam propagation speeds on highways and outline regional, lane- and vehicle-dependent differences, showing that car-only traffic is characterized by front speeds ranging from − 13.3 km/h (Germany) to − 16.4 km/h (US). In comparison, truck-only traffic proved the fastest downstream front propagation with − 21.4 km/h (Germany). Applying the metrics to an exemplified wide moving jam, vehicles 400 m apart show waiting times varying from 67 s in truck-only to 108 s in car-only traffic until the resolution front reaches the following vehicle.