CNN-based InSAR Denoising and Coherence Metric
This addresses noise reduction in InSAR data for remote sensing applications, representing an incremental improvement by applying existing CNN methods to a new domain.
The paper tackled denoising and coherence estimation in InSAR imagery, a remote sensing technique for ground movement, by introducing CNN-based autoencoders that learn filters without clean ground truth, showing superiority over four established methods.
Interferometric Synthetic Aperture Radar (InSAR) imagery for estimating ground movement, based on microwaves reflected off ground targets is gaining increasing importance in remote sensing. However, noise corrupts microwave reflections received at satellite and contaminates the signal's wrapped phase. We introduce Convolutional Neural Networks (CNNs) to this problem domain and show the effectiveness of autoencoder CNN architectures to learn InSAR image denoising filters in the absence of clean ground truth images, and for artefact reduction in estimated coherence through intelligent preprocessing of training data. We compare our results with four established methods to illustrate superiority of proposed method.