Imaging reconstruction through long-range scattering media by using deep learning

2021 ◽  
Author(s):  
Bochao Zhang ◽  
Fang Liu ◽  
Baoxing Xiong ◽  
Fan Gao ◽  
Xiang Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Long Range ◽  
Scattering Media ◽  
Imaging Reconstruction

scholarly journals A Green Prospective for Learned Post-processing in Sparse-view Tomographic Reconstruction

2021 ◽  
Author(s):  
Elena Morotti ◽  
Davide Evangelista ◽  
Elena Loli Piccolomini
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Tomographic Reconstruction ◽  
Research Field ◽  
Filtered Backprojection ◽  
Post Processing ◽  
Training Set ◽  
Imaging Reconstruction ◽  
Active Research

Deep Learning is developing interesting tools which are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green-AI literature, we here propose a shallow neural network to perform an efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results obtained on images from the training set and on unseen images, using both the non-expensive network and the widely used very deep ResUNet show that the proposed network computes images of comparable or higher quality in about one fourth of time.

scholarly journals Analysis of deep learning architectures for turbulence mitigation in long-range imagery

2020 ◽  
Author(s):  
David Vint ◽  
Gaetano Di Caterina ◽  
John J. Soraghan ◽  
Robert A. Lamb ◽  
David Humphreys
Keyword(s):  
Deep Learning ◽  
Long Range ◽  
Learning Architectures

The horizontal propagation of P waves through scattering media: Analog model studies relevant to long-range Pn propagation

1983 ◽  
Vol 73 (1) ◽  
pp. 125-142
Author(s):  
William Menke ◽  
Paul G. Richards
Keyword(s):  
Long Range ◽  
Crustal Material ◽  
Scattering Media ◽  
Uppermost Mantle ◽  
Low Velocity ◽  
P Waves ◽  
Model Studies ◽  
Homogeneous Models ◽  
Amplifying Effect ◽  
Lateral Heterogeneities

abstract We compare seismograms produced through the use of analog models of scattering and nonscattering Earth structure to access the effect of lateral heterogeneities on the horizontal propagation of P waves. Our results are applicable to propagation out to 16° and to periods as short as 5 sec. We find that layers of scatterers within the mantle near the turning points of P waves can cause these phases to have long coda similar in certain respects to the coda observed in long-range Pn. The overall appearance of this coda is similar to that produced in laterally homogeneous models that include low-velocity crustal material near their surfaces. Scatterers at shallower depths in the mantle or crust have a different effect. Those in very uppermost mantle seem to suppress the horizontal propagation of P waves while those in the crust have very little overall effect, at least at the perod range we studied. We also find that the scatterers have an amplifying effect on the horizontal propagation of the very longest periods (>20 sec), an effect that may be related to the scattering-controlled boundary waves discovered by Biot (1968).

Inverse Design of Long-range Intensity Correlations in Scattering Media

2018 ◽  
Author(s):  
Milan Koirala ◽  
Raktim Sarma ◽  
Hui Cao ◽  
Alexey Yamilov
Keyword(s):  
Long Range ◽  
Inverse Design ◽  
Scattering Media

Imaging reconstruction through strongly scattering media by using convolutional neural networks

2020 ◽  
Vol 477 ◽  
pp. 126341
Author(s):  
Qiongyao Li ◽  
Jun Zhao ◽  
Yanzhu Zhang ◽  
Xuetian Lai ◽  
Ziyang Chen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Scattering Media ◽  
Imaging Reconstruction
Sign in / Sign up

Export Citation Format

Share Document