This paper compares different similarity measures for theudmatching of very-high-resolution SAR and optical imagesudover urban areas. It is meant to provide guidance aboutudthe performance of both signal-based and descriptor-basedudsimilarity measures in the context of this non-trivial case ofudmulti-sensor correspondence matching. Using an automatically generated training dataset, thresholds for the distinction between correct matches and wrong matches are determined.udIt is shown that descriptor-based similarity measures outperform signal-based similarity measures significantly.
展开▼