Polarization image sorting method based on tensor decomposition and dimension reduction

Abstract

The invention belongs to the technical field of image processing, relates to the POLSAR image processing technology, and discloses a polarization image sorting method based on tensor decomposition and dimension reduction. According to the method, polarization data and a polarization characteristic quantity matrix are utilized for setting three-dimensional polarization characteristic tensor, low-dimension characteristic tensor is obtained according to the dimension reduction method based on tensor decomposition, training samples are selected from the low-dimension characteristic tensor for classification of an SVM, and on the basis of not destroying the space relation between the structure of the three-dimensional polarization characteristic tensor and adjacent pixels, redundancy between the characteristic quantities is removed, dimension disasters are avoided, the classification effect is well improved, and the efficiency and robustness of the algorithm are improved. The polarization image sorting method based on tensor decomposition and dimension reduction can be applied to classification of various complex terrains.

Description

technical field The invention belongs to the technical field of image processing, and relates to a polarimetric synthetic aperture radar (POLSAR) image processing technology, in particular to a polarization image classification method based on tensor decomposition and dimensionality reduction. Background technique The polarization characteristic quantity of the target describes the scattering characteristics of the target, and the analysis and processing of the polarization characteristic quantity will help to dig out the close relationship between the scattering mechanism of the target and the polarization characteristic characterization, so as to achieve more accurate polarization analysis. Image classification and interpretation. Target polarization decomposition is currently the most researched and most widely used analysis tool for target polarization scattering characteristics. The research on target polarization decomposition began in the 1970s. In 1970, Huynen put...

AI Technical Summary

Problems solved by technology

The Chinese invention patent application with the application publication number CN103365985A and the invention title "A Category-Adaptive Polarimetric SAR Classification Method" discloses a polarimetric SAR image classification method based on Freeman decomposition and the same polarization ratio. , combined with another self-polarization parameter, visual clustering trend estimation algorithm and black frame recognition algorithm to realize the self-adaptation of the number of categories, but this method only uses several polarization feature quantities, which cannot completely characterize the characteristics of the target, resulting in The classification results lose a lot of detailed information, and the computational complexity is high

Images