Comparative evaluation of signal-based and descriptor-based similarity measures for SAR-optical image matching

Abstract

This paper compares different similarity measures for the \nmatching of very-high-resolution SAR and optical images \nover urban areas. It is meant to provide guidance about \nthe performance of both signal-based and descriptor-based \nsimilarity measures in the context of this non-trivial case of \nmulti-sensor correspondence matching. Using an automatically generated training dataset, thresholds for the distinction between correct matches and wrong matches are determined. \nIt is shown that descriptor-based similarity measures outperform signal-based similarity measures significantly.