A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas
This addresses the need for efficient SAR tomography in forestry applications, offering a faster alternative to iterative methods, though it is incremental as it builds on existing inversion techniques with neural networks.
The paper tackles the problem of slow 3D reflectivity reconstruction in forested areas from synthetic aperture radar data by proposing a light-weight neural network that performs tomographic inversion in a single feed-forward pass, achieving fast reconstructions suitable for future large-scale missions like BIOMASS.
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.