A semantic-based approach to the representation of network-constrained trajectory data

Recent technological advances in urban traffic systems engender the availability of large trajectory data sets. However, the potential of these large urban databases are often neglected. This is due to a twofold problem. First, the volumes generated represent gigabytes of information per day, thus making data processing and analysis a computationally costly operation. Secondly, there is a lack of analysis of the semantics revealed by urban trajectories, at both the representation and data manipulation levels. The research presented in this paper addresses these two issues. We introduce an optimized representation approach that can efficiently reduce trajectory data volumes and facilitate data access and query languages. Our approach is a semantic-based representation model that characterizes significant trajectory points within a network. Key points are selected according to a combination of network, velocity, and direction criteria. This semantic approach facilitates trajectory data queries, the implicit modeling of trajectory processes. The proposed model is illustrated by a prototype implemented in a district of Hong Kong.