Investigations into the X and C band Quad-Pol Features for Sea Ice Classification

Conference: EUSAR 2016 - 11th European Conference on Synthetic Aperture Radar
06/06/2016 - 06/09/2016 at Hamburg, Germany

Proceedings: EUSAR 2016

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Ressel, Rudolf; Singha, Suman; Lehner, Susanne (Maritime Security Lab, German Aerospace Center (DLR), Germany)

Abstract:
This paper explores the possibilities of quad polarimetric SAR data for the purpose of sea ice classification. We propose an array of polarimetric features derived from the Pauli and lexicographic basis scattering matrices. On a dataset of near-coincident TerraSAR-X (TS-X) and RADARSAT-2 (RS-2) acquisitions we perform a feature analysis in terms of relevance and redundancy for sea ice classification. Among the most useful features for classification are matrix invariant based features (Geometric Intensity, Scattering Diversity, Surface Scattering Fraction). The first step of the proposed classification algorithm comprises a feature extraction, the results of which are ingested into a neural network classifier in the second step. The neural network based classifier manages to produce similar results for all C and X-band acquisitions. In particular, the overlapping image portions exhibit a reasonable congruence of detected ice types.