A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Berenger, Zoé, Denis, Loïc, Tupin, Florence, Ferro-Famil, Laurent, Huang, Yue
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914670774845440
author Berenger, Zoé
Denis, Loïc
Tupin, Florence
Ferro-Famil, Laurent
Huang, Yue
author_facet Berenger, Zoé
Denis, Loïc
Tupin, Florence
Ferro-Famil, Laurent
Huang, Yue
contents Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration. In forest areas, a large number of elements backscatter the radar signal within each resolution cell. To reconstruct the vertical reflectivity profile, state-of-the-art techniques perform a regularized inversion implemented in the form of iterative minimization algorithms. We show that light-weight neural networks can be trained to perform the tomographic inversion with a single feed-forward pass, leading to fast reconstructions that could better scale to the amount of data provided by the future BIOMASS mission. We train our encoder-decoder network using simulated data and validate our technique on real L-band and P-band data.
format Preprint
id arxiv_https___arxiv_org_abs_2301_08605
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas
Berenger, Zoé
Denis, Loïc
Tupin, Florence
Ferro-Famil, Laurent
Huang, Yue
Image and Video Processing
Computer Vision and Pattern Recognition
Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration. In forest areas, a large number of elements backscatter the radar signal within each resolution cell. To reconstruct the vertical reflectivity profile, state-of-the-art techniques perform a regularized inversion implemented in the form of iterative minimization algorithms. We show that light-weight neural networks can be trained to perform the tomographic inversion with a single feed-forward pass, leading to fast reconstructions that could better scale to the amount of data provided by the future BIOMASS mission. We train our encoder-decoder network using simulated data and validate our technique on real L-band and P-band data.
title A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2301.08605