Trajectory are ubiquitous in the real world. This patterns that succinctly show the cumulative behavior of a population of moving objects are useful abstractions to understand mobility-related phenomena. In particular, a form of pattern, which represents an aggregated abstraction of many individual trajectories of moving objects within an observed population, would be extremely useful in the domain of sustainable mobility and traffic management in metropolitan areas, where the discovery of traffic flows among sequences of different places in a town is a key issue. Trajectory classification, model construction for predicting the class labels of moving objects based on their trajectories and other features, has many important, real-world applications. A number of methods have been reported in the literature, but due to using the shapes of whole trajectories for classification, they have limited classification capability when discriminative features appear at parts of trajectories or are not relevant to the shapes of trajectories. In this project, the system proposes a unifying framework of mining trajectory patterns of various temporal tightness. It is called unifying trajectory patterns (UT-patterns). It consists of two phases. Initial pattern discovery and granularity adjustment. The system presents an algorithm of discovering a good set of initial UT-patterns for the first phase to ensure high efficiency.