Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A knowledge-based approach for task-oriented mission planning

: El Bekri, Nadia; Fischer, Yvonne; Marosz, D.


Broome, Barbara D. (Ed.) ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Next-Generation Analyst IV : 18-19 April 2016, Baltimore, Maryland, United States
Bellingham, WA: SPIE, 2016 (Proceedings of SPIE 9851)
ISBN: 978-1-5106-0092-8
Paper 98510A, 9 pp.
Conference "Next-Generation Analyst" <4, 2016, Baltimore/Md.>
Conference Paper
Fraunhofer IOSB ()
sensor mission planning; knowledge-based assistance; Bayesian Networks; expectation maximization algorithm; NIIRS

A key issue in mission planning for aerial reconnaissance is to use the sensor ressources in an appropriate way. The sensor mission planning requires knowledge, e.g., about the optimal sensor type (IR/EO) or the necessary flying altitude for a specific task. There are various types of task that can be part of the mission, e.g., to detect a vehicle or investigate a bridge. The goal of this work is to examine knowledge-based approaches like ontologies and the use of them to automatically derive all needed parameters for an optimal sensor mission planning based on the task. The task-oriented mission planning is processed on the tactical level. Based on the task the aerial image analyst defines the specific evaluation conditions. Various parameters are part of the task-oriented mission planning. For example there are the scene, the flight mode, the sensor, the system and the image analysis parameters. We introduce an idea to represent the sensor mission planning task at a relatively high-level knowledge-based approach. We want to create a representation of a useful sensor mission planning where all aspects and its components are considered, what these parts do, how they relate to each other and define the rules and constraints within. The main framework is based on the definitions of target categories and purpose codes (STANAG 3596) and NIIRS level.