FRAUNHOFER INSTITUTE OF OPTRONICS, SYSTEM TECHNOLOGIES AND IMAGE EXPLOITATION IOSB
IN COOPERATION WITH AIRBUS DEFENSE AND SPACE, THE FRAUNHOFER IOSB GIVES YOU THE CHANCE TO COMPLETE YOUR STUDIES WITH A
“Hybrid Artificial Intelligence (AI) combining Machine Learning (ML) and Dynamic Bayesian Networks (DBN) for Behavior Recognition"
Fraunhofer IOSB and its 530 employees offers committed scientists and technicians challenging work with responsibility and a lot of room for creativity in an excellent and international environment. On behalf of our clients from the various fields of industry and government, we apply the latest findings from science and practice in an interdisciplinary manner to concrete projects. Contact to international partners and customers as well as to the academic environment is a matter of course. Our internal personnel development concept leads to a clear career orientation and systematic advancement. Whether you are a student, graduate or expert, Fraunhofer IOSB will provide you with the perfect start into the world of applied research.
Modern monitoring networks are able to provide trajectories of all kind of vessels and aircrafts within worldwide or at least extended environment. Best known are Automatic Dependent Surveillance – Broadcast (ADS-B) and Automatic Identification System (AIS) used within air and maritime surveillance. It is foreseeable that ongoing trends like Internet of Things (IoT), digitalisation, automotive, smart cities and decentralisation (blockchain) will enable additional systems in the near future – e.g. in traffic control and monitoring. The real challenge becomes the related situational awareness and the estimation of the intent of the tracked objects. Activity recognition and the determination of suspicious situations are a significant challenge. To address these topics in the context of trajectories, several technics are available. Here, two techniques should be considered:
Deep Learning demonstrates to deliver fascinating results. However, large data sets are needed. This makes it difficult to apply Deep Learning if these data sets are not available. Further, Deep Learning techniques lack to be explainable, but this is important to estimate confidence in the AI results and also to have a chance to certificate the techniques for critical applications. On the other hand, there are model-based methods like Bayesian Networks. These methods are explainable due to their very nature. They depend on expert knowledge during their design. New studies apply these DBNs more and more to complex environments – especially for situation assessment and anomaly detection, e.g. the detection of illegal, unreported and unregulated (IUU) fishing. The focus of this thesis is on the combination of DBNs and data-driven methods, like Deep Learning, for trajectory-based anomaly detection:
What we expect from you
What you can expect from us
Please submit your online application via:
For questions about this position, please do not hesitate to contact:
Mr. Mathias Anneken, M. Sc.
Phone: +49 721 6091-619
Additional information is available at:
|Intitulé||Bachelor Thesis / Master Thesis|
|Employer||Fraunhofer IOSB, Karlsruhe|
|Job location||Fraunhoferstraße 1, 76131 Karlsruhe|
|Publié||août 5, 2019|
|Date limite d'inscription||Non Spécifiée|
|Types d'emploi||Autre  |
|Domaines de recherche :||Algorithmes,   Intelligence artificielle,   Réseau de neurones artificiels,   Communications informatiques (réseaux),   Structures de données,   Bases de données,   Interactions homme-machine,   Systèmes d'exploitation,   Langages de programmation,    and 2 more. Génie logiciel,   Apprentissage automatique  |