A novel approach to polarimetric SAR data processing based on Nonlinear PCA

作者：

Highlights：

• Nonlinear PCA (NLPCA) applied to full polarimetric SAR images.

• NLPCA decomposes the original SAR data into five nonlinear components.

• The five nonlinear components can be associated to five main scattering mechanisms.

• Results are similar to those obtained with widely used decomposition techniques.

• NLPCA outperform classical linear transformation approaches.

摘要

Highlights•Nonlinear PCA (NLPCA) applied to full polarimetric SAR images.•NLPCA decomposes the original SAR data into five nonlinear components.•The five nonlinear components can be associated to five main scattering mechanisms.•Results are similar to those obtained with widely used decomposition techniques.•NLPCA outperform classical linear transformation approaches.

论文关键词：Nonlinear Principal Component Analysis,SAR polarimetry,Polarimetric decomposition,Classification

论文评审过程：Received 29 January 2013, Revised 11 October 2013, Accepted 7 November 2013, Available online 28 November 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.11.009