Fast and Efficient Urban Extent Extraction Using ASAR Wide Swath Mode Data

摘要

This paper aims at introducing a fast and efficient approach able to extract human settlement extents using ASAR Wide Swath Mode data. The proposed approach exploits the spatial features characterizing human settlements in SAR data at a spatial resolution around 100 m, i.e., long term coherence and large backscattered power values. The joint use of multi-temporal filtering and averaging and the homogeneously high SAR return from built-up structures is the key to extract quickly and robustly human settlement extents. Although prone to commission errors in mountainous areas, the procedure proposed in this paper proved to be able to extract consistently more accurate results than existing global data sets including Globcover 2009. This was assessed by running a series of tests in different geographical areas and comparing the new and the existing products with independently extracted “urban” and “non-urban” points. The results show that ASAR data have no fewer potential than optical ones for global mapping of human settlements. Properly processed, instead, SAR data are able to provide an effective solution to the need of a global map of human settlement, useful for risk computations, climate change model inputs and population mapping, among other applications.