Polarization SAR data classification method and system based on mixed classifier

Abstract

The invention discloses a polarization SAR data classification method and system based on a mixed classifier. The polarization SAR data classification method includes the steps of obtaining polarization SAR data initial polarization characteristics in different classes, adopting a decision tree classifier to select the polarization characteristics for classification from the initial polarization characteristics, being based on the polarization characteristics for classification, and adopting an SVM classifier to classify polarization SAR data. According to the polarization SAR data classification method and system, the advantages of the decision tree classifier and the advantages of the SVM classifier are synthesized, the classification accuracy reaches the level of the SVM classifier, the classification calculation efficiency is equivalent to that of the decision tree classifier, and the polarization SAR data classification method and system are of great significances in polarization SAR data classification.

Description

technical field [0001] The invention belongs to the field of radar data processing, in particular to a method and system for classifying polarimetric SAR data based on a hybrid classifier. Background technique [0002] The classification of polarimetric SAR data is an important part of SAR image interpretation, which generally includes several steps of constructing polarimetric features, constructing classifiers, and classifying. Among them, the selection of classifiers has a great impact on the accuracy of the final classification results. At present, there are many classifiers that can be used to classify polarimetric SAR data. Literature [1] uses the maximum likelihood criterion to classify polarimetric SAR data. The classification error probability of this criterion is small, but the classification result is greatly affected by subjective factors. Literature [2] uses the C-means algorithm to classify polarimetric SAR data. This algorithm can reflect the real situation of...

AI Technical Summary

Problems solved by technology

[0017] Aiming at the deficiency that the polarization SAR data classification in the prior art cannot achieve high classification accuracy and high classification efficiency at the same time, the present invention provides an extreme classification method that can not only achieve the classification accuracy of the SVM classifier, but also achieve the classification efficiency of the decision tree classifier. Chemical SAR data classification method and system

Images