Synthetic aperture radar inverse scattering reconstruction using convolutional neural networks

被引:0
作者
Alvarez, Jacqueline [1 ]
Kim, Arnold [1 ]
Marcia, Roummel F. [1 ]
Tsogka, Chrysoula [1 ]
机构
[1] Univ Calif Merced, 5200 N Lake Rd, Merced, CA 95343 USA
来源
APPLICATIONS OF MACHINE LEARNING 2022 | 2022年 / 12227卷
基金
美国国家科学基金会;
关键词
Synthetic aperture radar; machine learning; convolutional neural network; reconstruction; TUTORIAL;
D O I
10.1117/12.2633577
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a study to address the reconstruction of synthetic aperture radar (SAR) images using machine learning. From previous work, we utilize a single, fully-connected layer to learn the sensing matrix of the forward scattering problem by using a set of reflectivites as the inputs and the SAR measurements as the outputs. Using this result, we estimate the reflectivity of the SAR measurements by applying the conjugate transpose of the learned sensing matrix to the SAR measurement data. Then we further improve the reconstructions of the reflectivity using convolutional layers. Employing a training set made up of 50,000 images of randomly placed point scatterers as the reflectivities, we simulate SAR measurement data using a physical model for the sensing matrix. We apply the learned sensing matrix to our SAR measurement data and use this estimate of the reflectivity as the inputs to the model, while the true reflectivities are the outputs. The model is trained to reconstruct images containing a single target. We find that the resulting reconstructions are sharper images than those from the initial estimate from applying the conjugate transpose of the learned sensing matrix. In particular, we find that the background noise is significantly decreased. In addition, we test this model on a different dataset with multiple targets as reflectivities. Similar to previous results, and with no additional training, the model applied to data with multiple targets also demonstrated improved reconstructions of reflectivities.
引用
收藏
页数:10
相关论文
共 13 条
[1]   IMAGE CLASSIFICATION IN SYNTHETIC APERTURE RADAR USING RECONSTRUCTION FROM LEARNED INVERSE SCATTERING [J].
Alvarez, Jacqueline ;
DeGuchy, Omar ;
Marcia, Roummel F. .
IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, :2867-2870
[2]  
Balzter H, 2001, PROG PHYS GEOG, V25, P159, DOI 10.1191/030913301666986397
[3]   Coherent interferometric imaging in clutter [J].
Borcea, Liliana ;
Papanicolaou, George ;
Tsogka, Chrysoula .
GEOPHYSICS, 2006, 71 (04) :SI165-SI175
[4]   Synthetic Aperture Imaging of Direction- and Frequency-Dependent Reflectivities [J].
Borcea, Liliana ;
Moscoso, Miguel ;
Papanicolaou, George ;
Tsogka, Chrysoula .
SIAM JOURNAL ON IMAGING SCIENCES, 2016, 9 (01) :52-81
[5]   A mathematical tutorial on synthetic aperture radar [J].
Cheney, M .
SIAM REVIEW, 2001, 43 (02) :301-312
[6]  
Cheney M., 2009, Fundamentals of Radar Imaging, volume 79 of CBMS-NSF Regional Conference Series in Applied Mathematics
[7]  
DeGuchy O., 2020, Applications of Machine Learning 2020, V11511, P148
[8]   Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives [J].
Fracastoro, Giulia ;
Magli, Enrico ;
Poggi, Giovanni ;
Scarpa, Giuseppe ;
Valsesia, Diego ;
Verdoliva, Luisa .
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2021, 9 (02) :29-51
[9]   A Tutorial on Synthetic Aperture Radar [J].
Moreira, Alberto ;
Prats-Iraola, Pau ;
Younis, Marwan ;
Krieger, Gerhard ;
Hajnsek, Irena ;
Papathanassiou, Konstantinos P. .
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2013, 1 (01) :6-43
[10]   Convolutional Neural Networks for Synthetic Aperture Radar Classification [J].
Profeta, Andrew ;
Rodriguez, Andres ;
Clouse, H. Scott .
ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXIII, 2016, 9843