Unsupervised Classification of Polarimetric SAR Images based on Independent Component Analysis

Conference: EUSAR 2006 - 6th European Conference on Synthetic Aperture Radar
05/16/2006 - 05/18/2006 at Dresden, Germany

Proceedings: EUSAR 2006

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Xie, Yan; Fu, Yusheng; Pi, Yiming (University of Electronics Science and Technology of China, China)

In this paper, we propose a new method for unsupervised classification of POLarimetric Synthetic Aperture Radar (POLSAR) data. This technique is a combination of the Independent Component Analysis (ICA) and the unsupervised classification method based on fuzzy set theory. We use ICA to extract the features of the POLSAR data, and use the Fuzzy C-Means (FCM) clustering algorithm to classify the extracted Independent Component (IC) image. The results of these experiments indicate that the advantages of this algorithm are the automated classification, reducing classification errors caused by speckle, fast convergence and high stability. The effectiveness of this algorithm is demonstrated by using SIR-C/X-SAR (Spaceborne Imaging Radar-C and X-band Synthetic Aperture Radar) data.