SAR Image Restoration From Spectrum Aliasing by Deep Learning

The diversity and the space-variance of the spectrum-aliasing effects in SAR bring challenges to the available model-driven restoration methods. In this paper, a hybrid data-driven and model-driven deep learning scheme is innovatively proposed to deal with this problem. In this scheme, the SAR image restoration is realize via a U-shaped deep neural network (DNN). Meanwhile, the model of the SAR echo data is used to generate the training data to learn the weighting parameters of the network. The DNN in this method is designed to suit the SAR spectrum-aliasing application. Due to the general SAR echo mathematical model is employed for training data construction, the spectrum aliasing features in different SAR systems can be accommodated and learned. Hence, the proposed method can work well for various SAR configurations. Simulation results using the real Radarsat-1 data as well as the synthetic data prove the effectiveness as well as the robustness of the proposed method.

[1]  Chen Chen,et al.  Deep Learning and Superpixel Feature Extraction Based on Contractive Autoencoder for Change Detection in SAR Images , 2018, IEEE Transactions on Industrial Informatics.

[2]  Zongben Xu,et al.  Fast Compressed Sensing SAR Imaging Based on Approximated Observation , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[3]  Wei Liu,et al.  Accurate Reconstruction and Suppression for Azimuth Ambiguities in Spaceborne Stripmap SAR Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[5]  Antonio Iodice,et al.  Filtering of Azimuth Ambiguity in Stripmap Synthetic Aperture Radar Images , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Bing Sun,et al.  Mitigation of Azimuth Ambiguities in Spaceborne Stripmap SAR Images Using Selective Restoration , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Alberto Moreira,et al.  Suppressing the azimuth ambiguities in synthetic aperture radar images , 1993, IEEE Trans. Geosci. Remote. Sens..

[8]  Ze Yu,et al.  Suppression of Azimuth Ambiguities in Spaceborne SAR Images Using Spectral Selection and Extrapolation , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Feng Hong,et al.  Maritime Surveillance With Undersampled SAR , 2017, IEEE Geoscience and Remote Sensing Letters.

[10]  Thomas Fritz,et al.  Ship Surveillance With TerraSAR-X , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Daniel F. Marshall,et al.  The ARPA/NAVY Mountaintop Program: adaptive signal processing for airborne early warning radar , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[12]  Pourya Shamsolmoali,et al.  A Novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Don Geman,et al.  Modeling and Inverse Problems in Image Analysis , 2006 .

[14]  Bariscan Yonel,et al.  Deep Learning for Passive Synthetic Aperture Radar , 2017, IEEE Journal of Selected Topics in Signal Processing.

[15]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[16]  Yunhua Zhang,et al.  A Novel Compressive Sensing Algorithm for SAR Imaging , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Xiang-Gen Xia,et al.  Nonambiguous SAR Image Formation of Maritime Targets Using Weighted Sparse Approach , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Jong Chul Ye,et al.  Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis , 2016, ArXiv.

[19]  Chris Kreucher,et al.  Modern approaches in deep learning for SAR ATR , 2016, SPIE Defense + Security.

[20]  Domenico Velotto,et al.  Azimuth ambiguities removal for ship detection using full polarimetric X-band SAR data , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[21]  Seyed Majid Azimi,et al.  Road Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks , 2018, IEEE Geoscience and Remote Sensing Letters.

[22]  Jian Sun,et al.  Convolutional neural networks at constrained time cost , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Ian G. Cumming,et al.  Digital Processing of Synthetic Aperture Radar Data: Algorithms and Implementation , 2005 .

[24]  Andrea Monti Guarnieri,et al.  Adaptive removal of azimuth ambiguities in SAR images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Yonina C. Eldar,et al.  Sub-Nyquist SAR via Fourier Domain Range-Doppler Processing , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Jong Chul Ye,et al.  Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems , 2017, SIAM J. Imaging Sci..

[27]  Jianyu Yang,et al.  SAR Automatic Target Recognition Based on Multiview Deep Learning Framework , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[29]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

[30]  Jiachun An,et al.  High-Performance SAR Automatic Target Recognition Under Limited Data Condition Based on a Deep Feature Fusion Network , 2019, IEEE Access.