DocumentCode
411162
Title
D-ISMC: a distributed unsupervised classification algorithm for optical satellite imagery
Author
Bo, Liu ; Bretschneider, Timo
Author_Institution
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore
Volume
6
fYear
2003
fDate
21-25 July 2003
Firstpage
3413
Abstract
A distributed version of the Improved Split-and-Merge Clustering algorithm for ground cover classification is presented, whereby the focus is on the implementation on two different parallel architectures. The analysis of the algorithm presents the obtained speedup factors by the parallelisation and investigates the proposed changes for the improvement of the classification accuracy.
Keywords
artificial satellites; geophysical signal processing; geophysical techniques; image classification; remote sensing; D-ISMC; distributed unsupervised classification algorithm; ground cover classification; merge clustering algorithm; optical satellite imagery; parallelisation; speedup factors; split clustering algorithm; Application software; Classification algorithms; Clustering algorithms; Computer architecture; Computer networks; Concurrent computing; High speed optical techniques; Optical sensors; Parallel architectures; Satellites;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International
Print_ISBN
0-7803-7929-2
Type
conf
DOI
10.1109/IGARSS.2003.1294806
Filename
1294806
Link To Document