DocumentCode
2212637
Title
Using L-band SAR images to map coastal wetlands
Author
Storie, Joni ; Lawson, Andrew ; Storie, Christopher
Author_Institution
Dept. of Geogr., Univ. of Winnipeg, Winnipeg, MB, Canada
fYear
2012
fDate
22-27 July 2012
Firstpage
757
Lastpage
759
Abstract
The National Wetland Inventory (NWI) in the USA is required, by congress mandate, to map wetlands every ten years. The last time the wetlands were map was in the mid-1980s using labour intensive, aerial photograph analysis techniques. The goal of this project is to map wetlands, based on the US-FWS NWI coastal wetland classes, in North Carolina using ALOS 10 m polarimetric radar. Wishart unsupervised classification using Cloude decomposition images resulted in 78-94% classification accuracy of four of the ten wetland classes. Images from Freeman-Durden and Touzi decompositions will be incorporated into the classification to achieve good accuracies for the remaining six wetland classes.
Keywords
geophysical image processing; hydrological techniques; image classification; remote sensing by radar; synthetic aperture radar; ALOS polarimetric radar; Cloude decomposition images; Freeman-Durden decomposition images; L-band SAR images; National Wetland Inventory; North Carolina; Touzi decomposition images; US-FWS NWI coastal wetland classes; USA; Wishart unsupervised classification; aerial photograph analysis techniques; coastal wetland map; Accuracy; L-band; Radar imaging; Scattering; Sea measurements; Synthetic aperture radar;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International
Conference_Location
Munich
ISSN
2153-6996
Print_ISBN
978-1-4673-1160-1
Electronic_ISBN
2153-6996
Type
conf
DOI
10.1109/IGARSS.2012.6351454
Filename
6351454
Link To Document