Title :
Automatic water canal detection in multispectral satellite images
Author :
Gedik, Ekin ; Cinar, U. ; Karaman, Ekrem ; Yardimci, Yasemin ; Halici, Ugur ; Pakin, K. ; Ergezer, H.
Author_Institution :
Enformatik Enstitusu, Orta Dogu Teknik Univ., Ankara, Turkey
Abstract :
In this paper, a method for automatically detecting water regions and classifying water canals containing water in high resolution multispectral satellite images in a rule based manner is proposed. As water canals may be of different lengths and widths, indices employed in the literature and image gradients are used adaptively to classify water regions. The well known spatial properties of water canals are used to determine the water canals among the extracted water regions. The proposed algorithm is tested on high resolution multispectral satellite images covering large areas and satisfactory results are obtained.
Keywords :
canals; geophysical image processing; hyperspectral imaging; image classification; image resolution; object detection; structural engineering computing; automatic water canal detection; automatical water region detection; high resolution multispectral satellite images; image gradients; water canal classification; Bridges; Irrigation; Remote sensing; Satellites; Spatial resolution; Water; high resolution satellite images; spectral index; structural analysis; water canal extraction;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2013 21st
Conference_Location :
Haspolat
Print_ISBN :
978-1-4673-5562-9
Electronic_ISBN :
978-1-4673-5561-2
DOI :
10.1109/SIU.2013.6531535
