Approach to Quasi-Optimal Projection Direction of Sequential Projection Pursuit for Polarimetric SAR Data Classification

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

Lin, Wei; Tian, Zheng; Duan, Jie (Northwestern Polytechnical University, 710072, Xi’an, China)
Tang, You-Guang (JiangXi Aviation Technical College, 330024, JiangXi, China)

The computation burden is a main problem for classification polarimetric SAR data using sequential projection pursuit (SPP) clustering model. For resolving this problem, the quasi-optimal projection direction of SPP is proposed in this paper. It is obtained through getting the bootstrap estimator of Hall index, and this estimator is the consistent with Hall index. The numerical analysis show this quasi-optimal projection direction are approximated to the optimal projection direction with sample size incresing. Meanwhile, making use of the quasi-optimal projection direction and the sequential projection pursuit-clustering model, we classify polarimetric SAR data. The problem of computation burden is resolved effectively.