Abstract
We describe two alternative approaches of how to extract knowledge from high- and medium-resolution Synthetic Aperture Radar (SAR) images of the European Sentinel-1 satellites. To this end, we selected two basic types of images, namely images depicting arctic shipping routes with icebergs, and - in contrast - coastal areas with various types of land use and human-made facilities. In both cases, the extracted knowledge is delivered as (semantic) categories (i.e., local content labels) of adjacent image patches from big SAR images. Then, machine learning strategies helped us design and validate two automated knowledge extraction systems that can be extended for the understanding of multispectral satellite images.
Highlights
In this paper, we describe the pros and cons of two alternative knowledge extraction approaches for space-borne Synthetic Aperture Radar (SAR) imagers [1]
We describe two alternative approaches of how to extract knowledge from high- and medium-resolution Synthetic Aperture Radar (SAR) images of the European Sentinel-1 satellites
In this paper, we describe the pros and cons of two alternative knowledge extraction approaches for space-borne SAR imagers [1]
Summary
We describe the pros and cons of two alternative knowledge extraction approaches for space-borne SAR imagers [1]. We describe two alternative approaches of how to extract knowledge from high- and medium-resolution Synthetic Aperture Radar (SAR) images of the European Sentinel-1 satellites. We selected two basic types of images, namely images depicting arctic shipping routes with icebergs, and - in contrast - coastal areas with various types of land use and human-made facilities.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
