DocumentCode :
2671861
Title :
Unsupervised classification of polarimetric SAR data using graph cut optimization
Author :
Jäger, M. ; Reigber, A. ; Hellwich, O.
Author_Institution :
Berlin Univ. of Technol. (TUB), Berlin
fYear :
2007
fDate :
23-28 July 2007
Firstpage :
2232
Lastpage :
2235
Abstract :
The paper presents a new framework for the classification of polarimetric SAR data. The underlying model introduces cyclic conditional dependencies among the class labels assigned to neighboring observations as a mechanism to regulate the spatial homogeneity of classification results. Classification is posed as an inference problem, and is solved by coherently integrating expectation maximization and graph cut optimization. Results based on real SAR data are presented.
Keywords :
expectation-maximisation algorithm; geophysical signal processing; optimisation; pattern classification; radar polarimetry; radar signal processing; remote sensing by radar; synthetic aperture radar; class label cyclic conditional interdependency; classification spatial homogeneity; expectation maximization; graph cut optimization; inference problem; unsupervised polarimetric SAR data classification; Computational modeling; Computer vision; Electronic mail; Graphical models; Inference algorithms; Iterative algorithms; Probability; Remote sensing; Simulated annealing; Synthetic aperture radar;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-1211-2
Electronic_ISBN :
978-1-4244-1212-9
Type :
conf
DOI :
10.1109/IGARSS.2007.4423283
Filename :
4423283
Link To Document :
بازگشت