With recent advances in sensory and mobile computing technology, many interesting applications involving moving objects have
emerged. One of them is
identification of suspicious movements: an important problem in homeland security. The objects in question can be vehicles, airplanes, or ships; however, due to
the sheer volume of data and the complexities within, manual inspection of the moving objects would require too much manpower.
Thus, an automated or semi-automated solution to this problem would be very helpful. That said, it is challenging to develop
a method that can efficiently and effectively detect anomalies. The problem is exacerbated by the fact that anomalies may
occur at arbitrary levels of abstraction and be associated with multiple granularity of spatiotemporal features.
In this study, we propose a new framework named ROAM ( Rule- and Motif-based Anomaly Detection in Moving Objects). In ROAM, object trajectories are expressed using discrete pattern fragments called motifs. Associated features are extracted to form a hierarchical feature space, which facilitates a multi-resolution view of the
data. We also develop a general-purpose, rule-based classifier which explores the structured feature space and learns effective
rules at multiple levels of granularity. Such rules are easily readable and can be easily provided to humans to aid better
inspection of moving objects.