Classification of polarimetric SAR imagery using unsupervised H/α and extended H/α schemes to detect anomalies on earthen levees

Abstract

Fully polarimetric Synthetic Aperture Radar (polSAR) data analysis has wide applications for terrain and ground cover classification. SAR technology, due to its high spatial resolution and soil penetration capability, is a good choice to identify problematic areas on earthen levees. In this paper, using the entropy (H), alpha angle (α), and eigenvalue parameters (λ), we implemented several unsupervised classification algorithms for the identification of anomalies on levees. The classification techniques applied here are: H/α classification and extended H/α (H/α/λ) classification. In this work, the effectiveness of the algorithms was demonstrated using quad-polarimetric L-band SAR imagery from the NASA Jet Propulsion Laboratory's (JPL's) Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR).