DocumentCode
2102602
Title
Automatic land-cover classification of a barrier island in the Virginia Coast Reserve using HYMAP imagery: an intercomparison of methods
Author
Bachmann, Charles M. ; Donato, Timothy F. ; Dubois, Kevin ; Fusina, Robert A. ; Bettenhausen, Michael ; Porter, John H. ; Truitt, Barry R.
Author_Institution
Remote Sensing Div., Naval Res. Lab., Washington, DC, USA
Volume
2
fYear
2001
fDate
2001
Firstpage
637
Abstract
Automatic land-cover maps were developed from HYMAP hyperspectral imagery acquired May 8, 2000 over Smith Island, VA in the Virginia Coast Reserve. Both unsupervised and supervised classification approaches were used to create these products. Ground surveys made by us in late October and early December, 2000 provided ground truth data for various land-cover types. We used GPS data from these surveys to extract spectral end-members used in supervised land-cover classification models. Both approaches to the classification problem produced consistent results for some categories such as Spartina alterniflora, although there were differences for other categories
Keywords
geophysical signal processing; geophysical techniques; image classification; terrain mapping; vegetation mapping; AD 2000 05 08; HYMAP; IR; Smith Island; Spartina alterniflora; USA; United States; Virginia; Virginia Coast Reserve; automatic land cover classification; barrier island; coast; geophysical measurement technique; hyperspectral imagery; hyperspectral remote sensing; image classification; infrared; land surface; multispectral remote sensing; remote sensing; vegetation mapping; visible; Atmospheric modeling; Cities and towns; Data mining; High performance computing; Hyperspectral imaging; Hyperspectral sensors; Laboratories; Layout; Remote sensing; Vegetation mapping;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location
Sydney, NSW
Print_ISBN
0-7803-7031-7
Type
conf
DOI
10.1109/IGARSS.2001.976576
Filename
976576
Link To Document