Fuzzy texture characterization of urban environments by SAR data

Abstract

In this paper we present a texture-base approach to the classification of SAR images recorded over urban environments. In particular, we explore the use of some co-occurrence measures and the wavelet frame decomposition, to investigate if there is an advantage, and where, in using these tools. We found that the correct classification rates are only partially increased by using these additional information, with a slight preference for texture analysis through the co-occurence matrix. These considerations are validated by analyzing polarimetric SAR images recorded over Los Angeles by the AIRSAR sensor.