Training Convolutional Neural Networks for Translational Invariance on SAR ATR
Conference: EUSAR 2016 - 11th European Conference on Synthetic Aperture Radar
06/06/2016 - 06/09/2016 at Hamburg, Germany
Proceedings: EUSAR 2016
Pages: 4Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Malmgren-Hansen, David (Technical University of Denmark, Denmark)
Engholm, Rasmus; Pedersen, Morten Ostergaard (Terma A/S, Denmark)
Abstract:
In this paper we present a comparison of the robustness of Convolutional Neural Networks (CNN) to other classifiers in the presence of uncertainty of the objects localization in SAR image. We present a framework for simulating simple SAR images, translating the object of interest systematically and testing the classification performance. Our results show that where other classification methods are very sensitive to even small translations, CNN is quite robust to translational variance, making it much more useful in relation to Automatic Target Recognition (ATR) in a real life context.