Data Analytics and Machine Learning in Wide Area Surveillance Systems

Modern surveillance networks are able to provide trajectories of all kind of vessels and aircrafts within worldwide or at least extended environment. Most widely used are Automatic Dependent Surveillance - Broadcast (ADS-B) and (Satellite-) Automatic Identification System (AIS) used within air and maritime surveillance. Both of them are cooperative systems. Besides these systems, sensor networks based on ground installations or mounted on airborne and space-based platforms deliver object trajectories independent of any cooperation. Examples include GMTI radar-based systems operating on UAV platforms and coastal or air traffic control sensor network installations. These surveillance systems provide mid- and long-term trajectories. The challenging part is the related situational awareness and the estimation of the intent of the tracked objects. New technologies include activity-based intelligence and the determination of patterns of life. An approach for these technologies can be found in the advanced analysis of those trajectories, which are extracted by the mentioned surveillance systems. Trajectories are partitioned into specific segments of interest using cluster algorithms. This helps to decode their pattern of life based on unsupervised machine learning. Trajectories are aggregated into different routes with dedicated representatives. Calculated probabilities indicate the frequentation of these routes. This allows predictive analytics and the identification of anomalous behaviour. Finally, these new data analytic techniques have to be integrated in existing near real time surveillance systems. This requires specific system architectures as well as a completely new software and hardware landscape. So, trajectory-based Machine Learning is embedded in local or global clouds and uses dedicated mechanisms for distributed and parallel processing.