A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas

TL;DR

This paper introduces a neural network-based method for rapid SAR tomographic imaging of forests, enabling efficient 3D reflectivity reconstruction from radar data, which is scalable for future large-scale missions.

Contribution

It presents a novel lightweight neural network approach for SAR tomography that outperforms traditional iterative methods in speed and scalability.

Findings

Neural networks can effectively reconstruct forest reflectivity profiles from SAR data.

The method achieves faster processing times compared to iterative algorithms.

Validation on real data confirms the approach's practical applicability.

Abstract

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.