Road Network
Road networks are the focus of extensive research aiming to improve their efficiency, safety, and understanding through data analysis and modeling. Current research emphasizes developing advanced algorithms, including graph neural networks, transformers, and deep learning models, for tasks such as traffic forecasting, route optimization, and automated road network extraction from various data sources (e.g., historical maps, satellite imagery, GPS traces). These advancements have significant implications for urban planning, transportation management, autonomous driving, and logistics, enabling more efficient resource allocation, improved safety measures, and better infrastructure design. The development of large, publicly available datasets is also a key focus, facilitating more robust model training and evaluation.
Papers
TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Version
Duc Kieu, Tung Kieu, Peng Han, Bin Yang, Christian S. Jensen, Bac Le
Paved or unpaved? A Deep Learning derived Road Surface Global Dataset from Mapillary Street-View Imagery
Sukanya Randhawa, Eren Aygun, Guntaj Randhawa, Benjamin Herfort, Sven Lautenbach, Alexander Zipf