SAR moving target imaging based on convolutional neural network

Abstract SAR images are a high-resolution map of surface target areas and terrain in the range and the cross-range dimension. Usually, moving targets appear as defocused and spatially displaced objects superimposed on the SAR map. In this paper, a new moving target refocusing imaging method based on Range Doppler (RD) Algorithm and convolutional neural network is proposed. Firstly, Range Doppler (RD) Algorithm is used to preprocess the echo data to obtain the blurring SAR image as the input data of convolution neural network. Secondly, according to SAR imaging characteristics, the original U-net structure is improved to extract the structure information of input data and provide good target reconstruction. The trained network can focus moving targets in case of different azimuth velocities. Finally, the experimental results prove the effectiveness of the proposed method in radar image focusing.

[1]  Müjdat Çetin,et al.  SAR moving target imaging in a sparsity-driven framework , 2011, Optical Engineering + Applications.

[2]  Xinhua Mao,et al.  Autofocus Correction of Azimuth Phase Error and Residual Range Cell Migration in Spotlight SAR Polar Format Imagery , 2012, ArXiv.

[3]  Xinhua Mao,et al.  Autofocus Correction of APE and Residual RCM in Spotlight SAR Polar Format Imagery , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Jie Wang,et al.  Dimension-Factorized Range Migration Algorithm for Regularly Distributed Array Imaging , 2017, Sensors.

[5]  James R. Fienup,et al.  Reconstruction of a complex-valued object from the modulus of its Fourier transform using a support constraint , 1987 .

[6]  J. Miao,et al.  Oversampling smoothness: an effective algorithm for phase retrieval of noisy diffraction intensities. , 2012, Journal of applied crystallography.

[7]  Charles V. Jakowatz,et al.  Phase gradient autofocus-a robust tool for high resolution SAR phase correction , 1994 .

[8]  Heinz H. Bauschke,et al.  Hybrid projection-reflection method for phase retrieval. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[9]  Junfeng Wang,et al.  SAR Minimum-Entropy Autofocus Using an Adaptive-Order Polynomial Model , 2006, IEEE Geoscience and Remote Sensing Letters.

[10]  Ming Yang,et al.  Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling , 2018, Journal of Medical Systems.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Birsen Yazici,et al.  Deep learning for SAR image formation , 2017, Defense + Security.

[13]  Alberto Moreira,et al.  Extended chirp scaling algorithm for air- and spaceborne SAR data processing in stripmap and ScanSAR imaging modes , 1996, IEEE Trans. Geosci. Remote. Sens..

[14]  Hao Ling,et al.  Time-Frequency Transforms for Radar Imaging and Signal Analysis , 2002 .

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

[16]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[17]  Xiang-Gen Xia,et al.  Dual-speed SAR imaging of moving targets , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[18]  F. H. Wong,et al.  Error Sensitivities Of A Secondary Range Compression Algorllthm For Processing Squinted Satellite Sar Data , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[19]  Hongyin Shi,et al.  SAR Slow Moving Target Imaging Based on Over-Sampling Smooth Algorithm , 2017 .

[20]  Gang Li,et al.  Doppler Keystone Transform: An Approach Suitable for Parallel Implementation of SAR Moving Target Imaging , 2008, IEEE Geoscience and Remote Sensing Letters.

[21]  Xingzhao Liu,et al.  A Compact Real-Time Optical Processor For High Resolution SAR Data , 2014 .

[22]  Qun Zhang,et al.  Two-dimensional sparse synthetic aperture radar imaging method with stepped-frequency waveform , 2015 .

[23]  Ran Duan,et al.  Deep kernel learning method for SAR image target recognition. , 2017, The Review of scientific instruments.

[24]  I. Cumming,et al.  A Digital Processor for the Production of Seasat Synthetic Aperture Radar Imagery , 1979 .

[25]  J R Fienup,et al.  Reconstruction of an object from the modulus of its Fourier transform. , 1978, Optics letters.

[26]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[27]  Xinhua Mao,et al.  Far-field limit of PFA for SAR moving target imaging , 2009, 2009 2nd Asian-Pacific Conference on Synthetic Aperture Radar.

[28]  M. N. Doja,et al.  Analysis of weight initialization methods for gradient descent with momentum , 2015, 2015 International Conference on Soft Computing Techniques and Implementations (ICSCTI).

[29]  Andrei Dmitri Gavrilov,et al.  Convolutional Neural Networks: Estimating Relations in the Ising Model on Overfitting , 2018, 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC).