Segmentation and fusion of building features based on InSAR and optical data

Abstract

The new generation of space borne SAR sensors provides geometric resolution of one meter, airborne systems even higher. In this high resolution data many features of urban objects become visible, which were beyond the scope of radar remote sensing only a few years ago. Focusing on elevated objects (e.g., urban area), layover, and occlusion issues inevitably arise because of the side-looking SAR sensor principle. In order to support interpretation, SAR data are often analyzed using additional information provided by maps or other remote sensing imagery. The focus of this paper is on building extraction in urban scenes by means of combined InSAR data and optical aerial imagery

Διερεύνηση Συνδυασμένης Χρήσης Δεδομένων SAR Με Ετερογενή Τοπογραφικά Δεδομένα Μέσω Συνταύτισης Μη Συναρτησιακών Καμπυλών

“…The synergistic use of heterogeneous data sets offers enhanced capabilities for extracting information and optimised data updating, compared to the use of a single data type (Butenuth et al [2007]). The synergistic use of SAR data with heterogenous data has been, and is still being investigated for applications such as the detection and height estimation of buildings (Wegner et al [2009], Thiele et al [2009b], and Wegner [2011]), the extraction of building outlines (Tupin and Roux [2003] and Sportouche et al [2011]), the building change detection (Vidal and Moreno [2011]), the earthquake damage detection (Stramondo et al [2006] and Brunner et al [2010] and Chini et al [2009]), the floodplain inundation (Townsend and Walsh [1998]), the mapping of wetlands (Li and Chen [2005]), the monitoring of surface water quality (Zhang et al [2002]), the stem volume estimation in boreal forest area / estimation of forest variables (Fransson et al [2001], Holmström and Fransson [2003] and Moghaddam et al [2002]), the crop management-identification (Moran et al [1997], Blaes et al [2005] and Okamoto and Kawashima [1999]), the snow and glaciers monitoring (Koskinen et al [1999] and Trouve et al [2007]) and the planetary mapping (Soderblom et al [2007]), just to name a few. Wegner [2011] classifies the ways to co-process (fuse) SAR data and heterogeneous data sets to:…”