LAND COVER CLASIFFICATION OVER EUROPE USING SAR IMAGING: INNOVATIVE METHODOLOGIES AND TECHNIQUES

摘要

There is an increasingly growing interest in observing the Earth’s surface from space. This can be done in several ways, such as using visible and radar imaging - the latter significantly less popular amongst members of the international scientific community. The purpose of this study is the exploitation of the advantages of radar satellite data, namely independence from cloud cover and solar illumination, for land cover classification. The properties of the recorded radar data heavily depend on the type of land cover, season and weather conditions. Therefore, it is possible to utilize the variability of these factors, in order to develop various methodologies and innovative techniques that can be used for classifying land surfaces. Although the study focuses on four main land cover types in Europe (urban, mountainous, agricultural-low vegetation and forested areas), the same principles can be extended worldwide, concluding to useful results for designing future satellite missions or as a guideline for researchers interested in an indepth studying of a specific land cover type.