Pauli decomposition and depth residual network-based polarimetric SAR image classification method

Abstract

The invention discloses a Pauli decomposition and depth residual network-based polarimetric SAR image classification method. The method mainly solves the problems in the prior art that the classification accuracy is low and the neural network cannot be increased more deeply. According to the technical scheme of the invention, the method comprises the steps of inputting a to-be-classified polarimetric SAR image, subjecting a polarization scattering matrix S to Pauli decomposition, and forming a pixel-based feature matrix F; representing an original element value by 28*28 blocks around each element in the feature matrix F and forming an image block-based feature matrix; constructing a training data set D; subjecting the image to super-pixel treatment after the Pauli decomposition treatment and forming a data set T1; constructing a classification model based on a depth residual network; training the classification model by using the training data set so as to obtain a well trained model; inputting the data set T1 into the well trained model to classify the data set T1 and then obtaining a predictive label matrix T2 of the entire image; removing the pixels of the training data set from the matrix T2 and then calculating the accuracy. The method of the invention adopts the depth residual network, so that network layers are increased. Meanwhile, the image is processed by adopting super pixels, so that the features of the image are effectively learnt. The classification accuracy of polarimetric SAR images is improved. The method can be used for target recognition.

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 change detection and target recognition. Background technique [0002] Synthetic aperture radar is a high-resolution imaging radar. Because microwaves have penetrating properties and are not affected by light intensity, they have all-day and all-weather working capabilities. Compared with other sensors, it can show more details and can better distinguish the characteristics of nearby objects. As an important means of remote sensing image acquisition, it has a wide range of applications. Polarized synthetic aperture radar (polarized SAR) describes the observed land cover and targets by transmitting and receiving polarized radar waves, and can obtain richer target information. It has wide application and research value. Compared with traditional single-polarization SAR, multi-polarization...

AI Technical Summary

Problems solved by technology

However, since the speckle noise of the polarimetric SAR image is very large, and the Cameron decomposition is based on the operation of a single pixel, the obtained results are not necessarily reliable

[0005] In 2004, Lee et al. proposed a feature extraction method based on Freeman decomposition. This method can maintain various polarization scattering characteristics, but the classification results are easily affected by the performance of Freeman decomposition. For polarization data of different bands, the algorithm poor universality

[0006] In 1998, Yann LeCun proposed the LeNet-5 convolutional neural network, using the idea of ​​local receptive field and weight sharing for image classification, and proposed a new feature extraction method, but this method still causes feature loss and affects classification The problem with the result

[0007] These feature extraction methods will lead to relatively strong loss of image features, so it is difficult to obtain high classification accuracy for polarimetric SAR images with complex backgrounds.

Images