Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A deep learning SAR ATR system using regularization and prioritized classes

: Wagner, S.; Barth, K.; Brüggenwirth, S.


Sego, D.J. ; Institute of Electrical and Electronics Engineers -IEEE-:
IEEE Radar Conference 2017 : 8-12 May, 2017, The Westin Seattle, Seattle, WA, USA
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-4673-8823-8
ISBN: 978-1-4673-8824-5
Radar Conference (RadarConf) <2017, Seattle/Wash.>
Fraunhofer FHR ()

Recently an increased interest in deep learning for radar and particularly SAR ATR systems has been observed. Many authors proposed systems that outperform established classification systems on benchmark datasets like MSTAR. In this paper we present a new implementation of our recently proposed convolutional neural network classifier, which has a more flexible structure and at the same time less free parameters and thus a reduced training time. Furthermore, the training itself is improved through regularization techniques that improve the convergence properties of the network. Another feature of this new implementation is the dependency of the learning rate on the target class. With this feature the network can focus on classes that cause higher costs of misclassification.