Exploring trajectory behavior model for anomaly detection in maritime moving objects
Po-Ruey Lei · 2013
As security requirements in coastal water and sea ports, maritime surveillance increases the duty. In this research, we focus on the maritime trajectory data to explore movement behavior for anomaly detection in maritime traffic. Trajectory data records the moving objects' true movement and provides the opportunity to discover the movement behavior for anomaly detection. The multidimensional outlying features are first identified and defined. To deal with the uncertain property of trajectory, a maritime trajectory modeling is developed to explore the movement behavior from historical trajectories and build a maritime trajectory model for anomaly detection. Then, our ongoing work is developing an anomaly detection algorithm to detect anomalous moving objects from real time maritime trajectory stream effectively. This work should contribute the area of maritime security surveillance by trajectory data mining.