Towards SAR Tomographic Inversion via Sparse Bayesian Learning

TL;DR

This paper introduces a sparse Bayesian learning approach for SAR tomographic inversion, demonstrating improved accuracy over KPCA-based methods and offering a promising data-driven alternative for high-precision large-area imaging.

Contribution

It presents a novel sparse Bayesian learning method for SAR tomography, outperforming existing KPCA-based techniques in estimating scatterer steering vectors.

Findings

Significantly better estimation accuracy than KPCA methods.

Potential for combining data-driven and model-driven approaches.

Effective on simulated data for large-area high-precision inversion.

Abstract

Existing SAR tomography (TomoSAR) algorithms are mostly based on an inversion of the SAR imaging model, which are often computationally expensive. Previous study showed perspective of using data-driven methods like KPCA to decompose the signal and reduce the computational complexity. This paper gives a preliminary demonstration of a new data-driven method based on sparse Bayesian learning. Experiments on simulated data show that the proposed method significantly outperforms KPCA methods in estimating the steering vectors of the scatterers. This gives a perspective of data-drive approach or combining it with model-driven approach for high precision tomographic inversion of large areas.