Open AccessA FUZZY LOGIC-BASED APPROACH FOR THE DETECTION OF FLOODED VEGETATION BY MEANS OF SYNTHETIC APERTURE RADAR DATA
Author(s) -
V. Tsyganskaya,
Sandro Martinis,
André Twele,
W. Cao,
Andreas Schmitt,
Philip Marzahn,
R. Ludwig
Publication year - 2016
Publication title -
the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 71
eISSN - 1682-1777
pISSN - 1682-1750
DOI - 10.5194/isprsarchives-xli-b7-371-2016
Subject(s) - synthetic aperture radar , vegetation (pathology) , fuzzy logic , remote sensing , flood myth , vegetation cover , computer science , data mining , geography , artificial intelligence , land use , engineering , civil engineering , medicine , archaeology , pathology
In this paper an algorithm designed to map flooded vegetation from synthetic aperture radar (SAR) imagery is introduced. The approach is based on fuzzy logic which enables to deal with the ambiguity of SAR data and to integrate multiple ancillary data containing topographical information, simple hydraulic considerations and land cover information. This allows the exclusion of image elements with a backscatter value similar to flooded vegetation, to significantly reduce misclassification errors. The flooded vegetation mapping procedure is tested on a flood event that occurred in Germany over parts of the Saale catchment on January 2011 using a time series of high resolution TerraSAR-X data covering the time interval from 2009 to 2015. The results show that the analysis of multi-temporal X-band data combined with ancillary data using a fuzzy logic-based approach permits the detection of flooded vegetation areas.