Science Service System
You are here : Home : Proposals_Summary

Summary of Proposal LAN3293

TitleDetection of flooded areas in a time series of high resolution Synthetic Aperture Radar images using Curvelet transform and unsupervised classification.
Investigator Ajadi, Olaniyi - University of Alaska Fairbanks, Geology and Geophysics
Team Member
Dr Meyer, Franz - University of Alaska Fairbanks, Department of Geosciences
SummaryDespite the significant progress that was achievedthroughout the recent years, to this day, automatic change detection andclassification from synthetic aperture radar (SAR) images remains a difficulttask. This is, in large part, due to (a) the high level of speckle noise thatis inherent to SAR data; (b) the complex scattering response of SAR even forrather homogeneous targets; and (c) the typically limited performance of SAR indelineating the exact boundary of changed regions. With this paper we present apromising change detection method that utilizes SAR images and providessolutions for these previously mentioned difficulties. We will show that thepresented approach enables automatic and high-performance change detectionacross a wide range of spatial scales (resolution levels). The developed method follows a three-step approach of (i)initial pre-processing; (ii) data enhancement/filtering using curvelettransform; and (iii) wavelet-based, multi-scale change detection. The data that I will be using will be TerraSAR-X and thisproject is been funded by the department of transportation.

Back to list of proposals

DLR 2004-2016