Details
| Original language | English |
|---|---|
| Pages (from-to) | 95-105 |
| Number of pages | 11 |
| Journal | KN - Journal of Cartography and Geographic Information |
| Volume | 70 |
| Issue number | 3 |
| Early online date | 26 Jul 2020 |
| Publication status | Published - Sept 2020 |
Abstract
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.
Keywords
- GPS trajectories, Intersection classification, Random forest, Traffic regulator detection
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth-Surface Processes
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: KN - Journal of Cartography and Geographic Information, Vol. 70, No. 3, 09.2020, p. 95-105.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Traffic Regulator Detection Using GPS Trajectories
AU - Golze, Jens
AU - Zourlidou, Stefania
AU - Sester, Monika
N1 - Funding information: Open Access funding provided by Projekt DEAL. This research was funded by the German Research Foundation (Deutsche Forschungsgemeinschaft (DFG)) with grant number 227198829/GRK1931. The authors gratefully acknowledge this financial support.
PY - 2020/9
Y1 - 2020/9
N2 - 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.
AB - 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.
KW - GPS trajectories
KW - Intersection classification
KW - Random forest
KW - Traffic regulator detection
UR - http://www.scopus.com/inward/record.url?scp=85088643305&partnerID=8YFLogxK
U2 - 10.1007/s42489-020-00048-x
DO - 10.1007/s42489-020-00048-x
M3 - Article
AN - SCOPUS:85088643305
VL - 70
SP - 95
EP - 105
JO - KN - Journal of Cartography and Geographic Information
JF - KN - Journal of Cartography and Geographic Information
SN - 2524-4957
IS - 3
ER -