Traffic Congestion Estimation Using Floating Car Data (External thesis / BMW) (Diplomathesis)


Nesrine Laamouri

21.03.2014, 14:00, room 3945


This diploma thesis investigates the estimation and prediction of traffic congestion using floating car data. Unlike previous works dealing with infrastructure-based traffic density estimation, this thesis focuses on  estimating the density based only on speed and distance to the preceding vehicle. Input data was collected  within the simTD project.

A traffic simulation tool SUMO has been used for testing the methods before  deploying them on real data. For this purpose, various approaches and methods namely fuzzy system and particle filter were tested. The number of probe vehicles within the traffic influences the accuracy of results.

The higher the number of probe cars, the more robust the estimation results. This work examines the sufficient percentage of probe cars within the total traffic in order to get accurate traffic state evaluation.