Investigation on Unsupervised Classification of Compact PolInSAR Data

Conference: EUSAR 2012 - 9th European Conference on Synthetic Aperture Radar
04/23/2012 - 04/26/2012 at Nuremberg, Germany

Proceedings: EUSAR 2012

Pages: 4Language: englishTyp: PDF

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

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.