Learning-Based Inversion Method for Solving Electromagnetic Inverse Scattering With Mixed Boundary Conditions
- 10 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 70 (8) , 6218-6228
Abstract
In this article, a unified learning-based approach is introduced to solve inverse scattering problems (ISPs) with mixed boundary conditions (BCs). The scattering behavior of hybrid dielectric and perfect electric conductors (PEC) scatterers is modeled by the T-matrix method. A rough image of the zero-order T-matrix coefficients for unknown scatterers is first reconstructed by the backpropagation (BP) method, which is then refined by an attention-assisted pix2pix generative adversarial network (GAN). The spatial attention mechanism is utilized to enforce the generator network to learn salient features of the unknown scatterers instead of the background. The adversarial training of the generator and the discriminator further enables the reconstructed image to be constrained by high-level features of reference scatterers. Numerical tests on both synthetic and experimental data verify the superior performance of the proposed method for ISP reconstructions with hybrid scatterers. It effectively expands the application scope of learning-based ISP methods to reconstruct scatterers without knowing the BCs of scatterers in advance.Keywords
Funding Information
- National Natural Science Foundation of China (61922075, 61971174, 41901350)
- Provincial Natural Science Foundation of Anhui (2108085MF201, 2008085QF285)
- Aeronautical Science Foundation of China (20181837002)
- Fundamental Research Funds for the Central Universities (PA2021KCPY0051, JZ2021HGTB0078)
This publication has 34 references indexed in Scilit:
- Reconstruction of scatterers with four different boundary conditions by T-matrix methodInverse Problems in Science and Engineering, 2014
- Simultaneous Reconstruction of Dielectric and Perfectly Conducting Scatterers Via $T$-Matrix MethodIEEE Transactions on Antennas and Propagation, 2013
- SUBSPACE-BASED OPTIMIZATION METHOD FOR RECONSTRUCTING PERFECTLY ELECTRIC CONDUCTORSProgress In Electromagnetics Research, 2010
- Twofold subspace-based optimization method for solving inverse scattering problemsInverse Problems, 2009
- Superresolution in total internal reflection tomographyJournal of the Optical Society of America A, 2005
- Electromagnetic inverse scattering of two-dimensional perfectly conducting objects by real-coded genetic algorithmIEEE Transactions on Geoscience and Remote Sensing, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- BiCG-FFT T-Matrix method for solving for the scattering solution from inhomogeneous bodiesIEEE Transactions on Microwave Theory and Techniques, 1996
- Microwave inverse scattering - local shape function imaging for improved resolution of strong scatterersIEEE Transactions on Microwave Theory and Techniques, 1994
- A fast algorithm for solution of a scattering problem using a recursive aggregate τ matrix methodMicrowave and Optical Technology Letters, 1990