PROJECT TITLE :

A General Framework for Urban Area Extraction Exploiting Multiresolution SAR Data Fusion

ABSTRACT:

This work is devoted to the presentation of a general framework for multiresolution synthetic aperture radar (SAR) knowledge fusion for the aim of urban space extraction. Among this framework, conditions for a cheap analysis of SAR knowledge from different sensors and spatial resolutions in addition as the state of the art of fusion techniques are mentioned. Furthermore, several fusion approaches on the pixel, feature, and decision level are applied on multiscale SAR information sets in a very uniform experimental setup over four test sites: 1)  Sao Paulo (Brazil); 2)  Beijing; 3)  Guangzhou; and 4)  Shanghai (People’s Republic of China). The accuracy of the resulting urban maps is assessed quantitatively via comparison against manually generated reference information sets. Furthermore, blessings and disadvantages of the applied fusion methods are evaluated.