I. Introduction
Traffic state estimation (TSE) and forecasting are central components in dynamic traffic management and information applications. Generally model-based TSE relies on two components: a model-based component and a data assimilation algorithm. The model-based component consists of two parts: a) a dynamic traffic flow model to predict the evolution of the state variables; and b) a set of observation equations relating sensor observations to the system state. Thereafter, a data-assimilation technique is adopted to combine the model predictions with the sensor observations.