Polarization SAR image classification method based on complex contour wave convolution neural network

Abstract

The invention discloses a polarization SAR image classification method based on a complex contour wave convolution neural network, and a problem of low classification accuracy in the prior art is mainly solved. The method comprises the steps of (1) inputting and normalizing a polarization coherent matrix T of a polarization SAR image to be classified, (2) according to the normalized matrix, constructing characteristic matrixes of a training data set and a test data set, (3) constructing a complex convolution neural network, and thus obtaining a complex contour wave convolution neural network, (4) training the complex contour wave convolution neural network by using the training data set, and obtaining a trained model, and (5) inputting the characteristic matrix of a test data set into the trained model to carry out classification, and obtaining a classification result. According to the method, the convolution neural network is extended to a complex domain to carry out operation and extract image characteristics of multiple scales, multiple directions and multiple resolution characteristics, the classification precision of the polarization SAR image is effectively improved, and the method can be used for target detection and identification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a polarimetric SAR image classification method, which can be used for target detection and recognition. Background technique [0002] Polarization SAR is a multi-channel coherent microwave imaging system and an extended system of single-polarization SAR. It uses vector measurement method to obtain ground object information, including amplitude and phase components. The prerequisite for the correct classification of polarimetric SAR images is to extract sufficient features from the polarimetric SAR images to characterize the attributes of ground objects in the images. [0003] Existing target feature extraction methods based on scattering characteristics mainly include Cloude decomposition, Freeman decomposition and so on. [0004] In 1997, Cloude et al. proposed the H / α classification method, which divides each pixel into the corresponding category based on ...

AI Technical Summary

Problems solved by technology

[0006] However, these feature extraction methods do not take into account the phase information and multi-scale, multi-direction, and multi-resolution characteristics of polarimetric SAR images, so it is difficult to achieve high classification accuracy for polarimetric SAR images with complex backgrounds.

Images