Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB 
Motivation
The surveillance of maritime areas is necessary, among other things, to ensure the safety requirements and environmental protection that apply there. For this task, a high degree of situational awareness is crucial in order to be able to make appropriate decisions regarding the current situation. Awareness of a situation or current situation is created by perceiving objects in a relevant environment, understanding their significance and predicting their condition within a defined period of time. The more complex the situations are, the more difficult it is for the human decision-maker to grasp the complete context of a situation, e.g. situations in a dynamic environment where many objects interact with each other. In the maritime context, for example, this applies to the surveillance of a large area where illegal fishing and a high volume of ships represent a growing challenge for the maritime authorities.
Maritime situation analysis
In today's surveillance systems, the possibilities for object perception (e.g. object detection and tracking in videos) are largely available. However, there is a need for methods for automatic situation or intention recognition (situation analysis), which can support the human decision maker in his situation awareness.
The amount of data captured by sensors, e.g. radio signals, radar or optronic sensors, has become so diverse and extensive in recent years that it can no longer be analyzed manually with the required care. Therefore, automatic procedures are being developed in order to reliably detect specific situations of special interest on the one hand and to identify specific anomalies in the recorded data on the other hand. These procedures should help human decision-makers to focus their attention on the information relevant to the decision.