A conceptual framework for automatic situation assessment

Humans make decisions on the basis of their situation awareness and it is well-known that insufficient situation awareness leads to incorrect decisions. The challenge of an advanced surveillance system for supporting situation awareness of a human decision maker is therefore to detect and assess complex situations that evolve over time. In this article, we present a conceptual framework for automatic situation assessment that consists of four parts, namely the situation characterization, the situation abstraction, the situation recognition and the situation projection. The situation itself can be described at several different levels of abstraction. The proposed framework can be used as a guideline when designing automatic situation assessment processes.