DocumentCode
1681036
Title
Texture and color based cloud detection
Author
Baseski, Emre ; Cenaras, Caglar
Author_Institution
HAVELSAN A.S., Ankara, Turkey
fYear
2015
Firstpage
311
Lastpage
315
Abstract
With the increasing number of aerial and satellite image sources, automated interpretation algorithms are becoming more and more crucial. Automatically determining the cloud coverage reduces image preprocessing time and aids automatic image exploitation algorithms about where to look. The proposed method makes use of both color and texture characteristics of cloud regions. The image is divided into subimages in order to perform initial color and edge analysis. Further analysis is done by classifying patches as cloud and non-cloud with respect to texture based features.
Keywords
clouds; geophysical image processing; image colour analysis; image texture; remote sensing; aerial image source; automated interpretation algorithm; automatic image exploitation algorithm; cloud color characteristics; cloud coverage; cloud texture characteristics; color-based cloud detection; edge analysis; image preprocessing time reduction; initial color analysis; satellite image source; texture-based cloud detection; texture-based feature; Classification algorithms; Clouds; Image color analysis; Image edge detection; Remote sensing; Satellites; Support vector machines; cloud detection; homogoneos texture descriptor; remote sensing; svm;
fLanguage
English
Publisher
ieee
Conference_Titel
Recent Advances in Space Technologies (RAST), 2015 7th International Conference on
Conference_Location
Istanbul
Print_ISBN
978-1-4673-7760-7
Type
conf
DOI
10.1109/RAST.2015.7208361
Filename
7208361
Link To Document