Vehicle Trajectory Analysis by Clustering

Abstract

With widespread availability of low cost GPS devices, it is becoming possible to record data about the moving objects on a large scale. The analysis of moving objects trajectory data is a critical component in a wide range of research and decision-making fields. To analyze the object movement regularities and anomalies, trajectory clustering plays an important role in trajectory mining. Trajectory clustering provides new and helpful information such as Jam detection and significant location recognition. In this paper, we focus on vehicle movement trajectory data and analyze to discover the various significant locations. We propose a K-means based clustering algorithm to mine the trajectory data for extracting the important information. The truck trajectory dataset of Athens is used in the proposed approach as an illustrative example. The result of clustering is visualized with the help of Google Maps.