DocumentCode :
576587
Title :
Automatic detection and delineation of surface water bodies in airborne hyperspectral data
Author :
Bochow, Mathias ; Heim, Birgit ; Küster, Theres ; Rogass, Christian ; Bartsch, Inka ; Segl, Karl ; Kaufmann, Hermann
Author_Institution :
Helmholtz Centre Potsdam, GFZ German Res. Centre for Geosci., Potsdam, Germany
fYear :
2012
fDate :
22-27 July 2012
Firstpage :
5226
Lastpage :
5229
Abstract :
In this investigation we focused on the development of a new water detection algorithm based on VIS-NIR imaging spectroscopy data. By analyzing different images containing inland and ocean water types we found the slopes of the reflectance spectrum of water at specific spectral wavelengths within the VIS-NIR spectral region to be diagnostic features for surface water identification. However, the presence of these features depends on the spectral superimposition of water constituents and bottom coverage. This aspect has been considered in the development of a knowledge-based classifier. The results (probability of detection generally lies above 90%) indicate the great potential of the developed algorithm for surface water body detection and delineation within urban, rural and coastal scenes.
Keywords :
geophysical image processing; geophysical techniques; geophysics computing; image classification; VIS-NIR imaging spectroscopy data; VIS-NIR spectral region; airborne hyperspectral data; automatic delineation; automatic detection; knowledge-based classifier development; ocean water types; surface water bodies; surface water identification; water constituent superimposition; water detection algorithm development; water reflectance spectrum; Absorption; Accuracy; Reflectivity; Remote sensing; Sea surface; Vegetation mapping; Water; detection and delineation of surface water bodies; imaging spectroscopy; spectral differentiation between water bodies and shadow areas; spectral features; water absorption;
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.2012.6352431
Filename :
6352431
Link To Document :
بازگشت