Leibniz Universität Hannover Faculty Faculty of Civil Engineering and Geodetic Science
Deutsch Contact Deutsch
Institute for Steel Construction
© Institut für Stahlbau
Welcome to the page of the Institute for Steel Construction.

Our institute is involved in teaching and academic training in Bachelor and Master programs as well as basic and applied research in the Doctoral program. The main aim of our research is to improve sustainability in construction toward Net Zero 2050. To accomplish this goal, the institute focuses on various research topics such as steel support structures for wind energy (e.g., onshore and offshore wind turbines), advanced structural materials and automated/robotic/additive construction (as one of the critical pillars of Industry 4.0 and the next construction revolution).

Paper published in KN - Kartographische Nachrichten: Traffic Regulator Detection Using GPS Trajectories

Jens Golze and Stefania Zourlidou developed a method to derive traffic regulators from GPS trajectories

This paper explores the idea of enriching maps with features predicted from GPS trajectories. More specifically, it proposes a method of classifying street intersections according to traffic regulators (traffic light, yield/priority-sign and right-of-way rule). Intersections are regulated locations and the observable movement of vehicles is affected by the underlying traffic rules. Movement patterns such as stop events or start-and-stop sequences are commonly observed at those locations due to traffic regulations. In this work, we test the idea of detecting traffic regulators by learning them in a supervised way from features derived from GPS trajectories. We explore and assess different settings of the feature vector being used to train a classifier that categorizes the intersections based on traffic regulators; also, we test several experimental setups. The results show that a Random Forest classifier with oversampling and Bagging booster enabled can predict the intersection regulators with 90.4% accuracy. We discuss future research directions and recommend next steps for improving the results of this research.

 

link.springer.com/article/10.1007/s42489-020-00048-x

Published by m sester

The Institute of Steel Construction is also represented on Linkedin. Follow us for news and insights into our research projects.
Linkedin

Events

Paper published in KN - Kartographische Nachrichten: Traffic Regulator Detection Using GPS Trajectories

Jens Golze and Stefania Zourlidou developed a method to derive traffic regulators from GPS trajectories

This paper explores the idea of enriching maps with features predicted from GPS trajectories. More specifically, it proposes a method of classifying street intersections according to traffic regulators (traffic light, yield/priority-sign and right-of-way rule). Intersections are regulated locations and the observable movement of vehicles is affected by the underlying traffic rules. Movement patterns such as stop events or start-and-stop sequences are commonly observed at those locations due to traffic regulations. In this work, we test the idea of detecting traffic regulators by learning them in a supervised way from features derived from GPS trajectories. We explore and assess different settings of the feature vector being used to train a classifier that categorizes the intersections based on traffic regulators; also, we test several experimental setups. The results show that a Random Forest classifier with oversampling and Bagging booster enabled can predict the intersection regulators with 90.4% accuracy. We discuss future research directions and recommend next steps for improving the results of this research.

 

link.springer.com/article/10.1007/s42489-020-00048-x

Published by m sester

Last Change: 09.01.25; Brömer

Contact us
Contact