Investigation on Unsupervised Classification of Compact PolInSAR Data

Konferenz: EUSAR 2012 - 9th European Conference on Synthetic Aperture Radar
23.04.2012 - 26.04.2012 in Nuremberg, Germany

Tagungsband: EUSAR 2012

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Tan, Lu-Iu; Dai, Da-hai (No. 38 Research Institute, Chinese Electronics Technology Group Corporation, China)
Huang, Ping-ping (College of Information Engineering, Inner Mongolia University of Technology, China)
Liu, Ai-jun (The Academy of Forestry, Beijing Forestry University, China)

A terrain classification method with compact polarimetric interferometric SAR data of π / 4 mode is proposed in this paper. The data is initially segmented with conformity coefficient. Then the initial classes are segmented into more subclasses with Shannon entropy parameter. The classification procedure is given. The proposed classification method is applied to the π / 4 mode compact PolInSAR data generated from L-band ESA PolInSAR data of Oberpfaffenhofen area. Experiment results confirm the validity of the proposed method.