Recovery of impenetrable rough surface profiles via CNN-based deep learning architecture
Yükleniyor...
Tarih
2022-08-18
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Taylor and Francis Ltd.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In this paper, a convolutional neural network (CNN)-based deep learning (DL) architecture for the solution of an electromagnetic inverse problem related to imaging of the shape of the perfectly electric conducting (PEC) rough surfaces is addressed. The rough surface is illuminated by a plane wave and scattered field data is obtained synthetically through the numerical solution of surface integral equations. An effective CNN-DL architecture is implemented through the modelling of the rough surface variation in terms of convenient spline type base functions. The algorithm is numerically tested with various scenarios including amplitude only data and shown that it is very effective and useful.
Açıklama
Anahtar Kelimeler
Convolutional neural network, Deep learning, Inverse scattering problems, Rough surface imaging, Reconstruction, Deep neural networks, Electric conductance, Integral equations, Inverse problems, Network architecture, Surface measurement, Surface scattering, Electromagnetic inverse problems, Learning architectures, Network-based, Rough surfaces, Surface imaging, Surface profiles, Convolution
Kaynak
International Journal of Remote Sensing
WoS Q Değeri
Q2
Scopus Q Değeri
Q1
Cilt
43
Sayı
15-16
SI
SI
Künye
Aydın, İ., Budak, G., Sefer, A. & Yapar, A. (2022). Recovery of impenetrable rough surface profiles via CNN-based deep learning architecture. International Journal of Remote Sensing, 43(15-16) 5658-5685. doi:10.1080/01431161.2022.2105177
