Noisy SAR image target recognition method based on wavelet denoising threshold self-learning

Abstract

The invention relates to a noisy SAR image target recognition method based on wavelet denoising threshold self-learning, and belongs to the technical field of radar target recognition. Based on a threshold-learnable wavelet speckle suppression network and a compression-excitation convolutional neural network, the threshold-learnable wavelet speckle suppression network comprises a wavelet transformation module, a threshold-learnable module and an inverse wavelet transformation module. The wavelet speckle suppression network capable of learning the threshold extracts an image high-frequency component through DWT, puts the image high-frequency component into a convolution and full connection layer, adaptively carries out soft threshold processing on the high-frequency component, combines the high-frequency component with a low-frequency component, and obtains a denoised image through IWT; therefore, the threshold value of wavelet denoising is supervised and learned through a training set label, features are extracted from an image output by a wavelet speckle suppression network capable of learning the threshold value through network automatic layering, and a compression-excitation module is added to balance the contribution degree of a feature map from an original image and a denoising branch. The method has the advantages of high identification capability and high test precision.

Description

technical field [0001] The present invention relates to a noisy SAR image target recognition method based on wavelet denoising threshold self-learning, in particular to a wavelet denoising network with learnable threshold under speckle noise pollution and a synthetic aperture radar (Convolutional Neural Network) of compressed excitation convolutional neural network (SENet). Network; SAR) target recognition method, which belongs to the field of pattern recognition and radar target recognition technology based on deep learning. Background technique [0002] SAR target recognition is an important topic of radar high-resolution image interpretation. Image target recognition technology has important application value in military and homeland security, such as friend or foe identification, battlefield surveillance and disaster relief. In recent years, deep learning technology represented by convolutional neural network (CNN) has made great achievements in the field of image recogn...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem of SAR image target recognition under the influence of speckle noise, which requires additional preprocessing and the filtering threshold is set by experience and deteriorates the recognition performance, and proposes a noisy SAR image target based on wavelet denoising threshold self-learning Recognition method, which relies on an end-to-end neural network wavelet denoising threshold self-learning network for noisy SAR image target recognition for noisy synthetic aperture radar image target recognition, that is, wavelet speckle suppression compression excitation network Wavelet- SR-SENet

Images