An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation

Phase filtering and pixel quality (coherence) estimation is critical in producing digital elevation models (DEMs) from interferometric synthetic aperture radar (InSAR) images, as it removes spatial inconsistencies (residues) and immensely improves the subsequent unwrapping. Large amount of InSAR dat...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2021-11, Vol.18 (11), p.1971-1975
Main Authors: Mukherjee, Subhayan, Zimmer, Aaron, Sun, Xinyao, Ghuman, Parwant, Cheng, Irene
Format: Article
Language:English
Subjects:
Artificial neural networks
Coherence
Computer architecture
Digital Elevation Models
Digital imaging
Filtration
Human performance
Image filtering
Interferometric synthetic aperture radar
Methods
Monitoring
Neural networks
Noise measurement
Pattern recognition
Radar imaging
radar interferometry
Residues
S phase
SAR (radar)
Satellite imagery
Satellites
Synthetic aperture radar
synthetic aperture radar (SAR)
Synthetic aperture radar interferometry
Training
unsupervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Phase filtering and pixel quality (coherence) estimation is critical in producing digital elevation models (DEMs) from interferometric synthetic aperture radar (InSAR) images, as it removes spatial inconsistencies (residues) and immensely improves the subsequent unwrapping. Large amount of InSAR data facilitates wide area monitoring (WAM) over geographical regions. Advances in parallel computing have accelerated convolutional neural networks (CNNs), giving them advantages over human performance on visual pattern recognition, which makes CNNs a good choice for WAM. Nevertheless, this research is largely unexplored. We thus propose "GenInSAR," a CNN-based generative model for joint phase filtering and coherence estimation that directly learns the InSAR data distribution. GenInSAR's unsupervised training on satellite and simulated noisy InSAR images outperforms other five related methods in total residue reduction (over 16(1/2)% better on average) with less over-smoothing/artifacts around branch cuts. GenInSAR's phase and coherence root-mean-squared-error and phase cosine error have average improvements of 0.54, 0.07, and 0.05, respectively compared to the related methods.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2020.3010504