Street-level traffic flow and context sensing analysis through semantic modelling

Sensing urban spaces from multisource geospatial data is vital to understanding the transportation system in the urban context. However, sometimes the complexity of the urban context and its indirect interaction with traffic flow deepens the difficulty of exploring their relationship.

In their paper, external pageStreet-level traffic flow and context sensing analysis through semantic integration of multisource geospatial datacall_made, Yatao Zhang and Prof. Dr. Martin Raubal from FRS come up with a geo-semantic framework to generate semantic representations of multi-hierarchical urban context and street-level traffic flow. Their paper also investigates the mutual correlation and predictability between urban context and traffic flow using a novel semantic matching method.

For each street, their results provide multi-hierarchical urban context signatures specified by land use distribution from a spatial perspective and traffic flow signatures specified by human mobility patterns from a temporal perspective. The correlation between urban context and traffic flow displays higher values after semantic matching than those in multi-hierarchies. Moreover, we found that utilising traffic flow to predict urban context results in better accuracy than the reversed prediction. The results of signature analysis and relationship exploration can contribute to a deeper understanding of context-aware transportation research.