SAR Object Classification with a Multi-Scale Convolutional Auto-Encoder

Despite of the significant success obtained by the deep networks, insufficient labelled training has often been the major problem while applying the deep learning models in SAR object classification tasks. In this paper, an unsupervised deep learning model that is implemented in the encoding-decoding architecture is proposed. The proposed deep network learns feature maps at different scales and combined them together to generate feature vectors for object classification. Besides, the reconstruction loss is improved by computing the mean square error between the reconstructed images and the data processed by an improved Lee Sigma (ILS) filter so that the background clutter in the target patches can be suppressed. The open published MSTAR dataset is utilized for performance evaluation. Both the validation results and comparison experiments demonstrates that the proposed model can adaptively learn discriminatory features from raw SAR data.

[1]  Jia Cheng Ni,et al.  SAR automatic target recognition based on a visual cortical system , 2013, 2013 6th International Congress on Image and Signal Processing (CISP).

[2]  H. Scott Clouse,et al.  Convolutional neural networks for synthetic aperture radar classification , 2016, SPIE Defense + Security.

[3]  Abdulkadir Eryildirim,et al.  Man-made object classification in SAR images using 2-D cepstrum , 2009, 2009 IEEE Radar Conference.

[4]  David Morgan,et al.  Deep convolutional neural networks for ATR from SAR imagery , 2015, Defense + Security Symposium.

[5]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[6]  Nabil Aouf,et al.  SAR automatic target recognition based on convolutional neural networks , 2017 .

[7]  Jianyu Yang,et al.  Target recognition in synthetic aperture radar images via non-negative matrix factorisation , 2015 .

[8]  Xuan Li,et al.  SAR ATR based on dividing CNN into CAE and SNN , 2015, 2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR).

[9]  Simon Wagner,et al.  A deep learning SAR ATR system using regularization and prioritized classes , 2017, 2017 IEEE Radar Conference (RadarConf).

[10]  Thomas L. Ainsworth,et al.  Improved Sigma Filter for Speckle Filtering of SAR Imagery , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Atle O. Knapskog,et al.  Classification of Ships in TerraSAR-X Images Based on 3D Models and Silhouette Matching , 2010 .

[12]  Lin Jin,et al.  A method for automatic target recognition using shadow contour of SAR image , 2013 .

[13]  Olaf Ronneberger,et al.  Invited Talk: U-Net Convolutional Networks for Biomedical Image Segmentation , 2017, Bildverarbeitung für die Medizin.

[14]  Michael A. Saville,et al.  A High-Frequency Multipeak Model for Wide-Angle SAR Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Hongwei Liu,et al.  Convolutional Neural Network With Data Augmentation for SAR Target Recognition , 2016, IEEE Geoscience and Remote Sensing Letters.

[16]  Wang Ning,et al.  A survey on feature extraction of SAR Images , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[17]  Simon A. Wagner,et al.  SAR ATR by a combination of convolutional neural network and support vector machines , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[18]  David Malmgren-Hansen,et al.  Training Convolutional Neural Networks for Translational Invariance on SAR ATR , 2016 .

[19]  Haipeng Wang,et al.  Target Classification Using the Deep Convolutional Networks for SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.