Polarimetric SAR image classification method based on strip waves and convolution neural network

Abstract

The invention discloses a polarimetric SAR image classification method based on strip waves and a convolution neural network, and mainly solves a problem that a polarimetric SAR is low in image classification precision in the prior art. The method comprises the following specific steps: (1), inputting a polarimetric SAR image; (2), extracting Pauli decomposition features; (3), constructing a characteristic matrix; (4), selecting a training sample and a test sample; (5), building an initial matrix; (6), initializing the convolution neural network; (7), training the convolution neural network; (8), testing the convolution neural network; (9), carrying out the coloring; (10), outputting a classification result image. Compared with the prior art, the method effectively improves the classification precision of the polarimetric SAR image.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar based on bandelet (Bandelet) and convolutional neural network (CNN) in the technical field of polarization synthetic aperture radar image feature classification (Synthetic Aperture Radar, SAR) image classification method. The invention can be used to classify the ground objects of the polarimetric SAR image, and can effectively improve the classification accuracy of the polarimetric SAR image. Background technique [0002] Polarimetric SAR image classification is an important part of SAR image interpretation. The existing polarimetric SAR image classification methods include: [0003] Wuhan University proposed a polarization SAR data classification method based on a hybrid classifier in its patent application "Polarization SAR Data Classification Method and System Based on Hybrid Classifier" (patent application numbe...

AI Technical Summary

Problems solved by technology

This method combines the traditional decision tree classifier and SVM classifier. Although the problem of low computational efficiency of the polarization SAR image classification method is improved, the disadvantage of this method is that the method does not consider the polarization Spatial correlation of SAR images, resulting in poor regional consistency and low classification accuracy in polarimetric SAR image classification

This method uses the deep wavelet neural network to extract the deep high-dimensional features of the data. Although it avoids the problems of less number of features or insufficient and unreasonable feature learning in the existing classification technology, there are still shortcomings in this method. Yes, because this method directly uses the wavelet feature information of the polarimetric SAR image, it cannot preserve the direction information of the polarimetric SAR image

Images