Pattern Recognition Using Queries in Relational Tracking Data Bases

Tracking systems provide kinematical information of objects in a scenario. This kinematical information can be combined with additional data to build higher-level-fusion systems that allow the detection of behaviour and threat patterns and thus contribute to situation awareness. The patterns that characterize situations of interest may vary over time and depend on the specific questions to be investigated. Data base systems provide a flexible way of combining data, and standing queries allow ongoing, automatic evaluation. In this paper, we present a way of using data base systems as the central component in a higher-level fusion system. We propose a possible architecture of this system using commercial database management software. Finally, we discuss how patterns for the detection of anomalies in tracking scenarios can be expressed in relational algebra.