Polarization SAR image classification based on CNN and SVM

Abstract

The invention discloses a polarization SAR image classification method based on CNN and SVM, and mainly aims to solve the problem of the existing polarization SAR image classification method that the classification precision is low. The method comprises the steps as follows: (1) inputting a to-be-classified polarization SAR image after filtering; extracting and normalizing the original feature of each pixel point based on a polarization coherence matrix and by taking the neighborhood into consideration; training an AE network, and obtaining the parameter of a CNN convolution layer through softmax fine-tuning; setting a CNN pooling layer as average pooling, and determining the parameter of the CNN pooling layer; and sending the features of CNN learning to an SVM for classification to obtain the classification result of the polarization SAR image. Compared with the existing methods, the spatial correlation of the image is fully considered, a new neighborhood processing method is proposed based on CNN, features more conductive to polarization SAR image classification can be extracted, the classification accuracy is obviously improved, and the method can be used for polarization SAR image surface feature classification and object identification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to classification of polarimetric SAR images, in particular to a method for classification of polarimetric SAR images based on CNN and SVM, which can be used for object classification and target recognition of polarimetric SAR images. Background technique [0002] Polarization SAR is a high-resolution active coherent multi-channel microwave remote sensing imaging radar. It is an important branch of SAR. It has the advantages of all-weather, all-time, high resolution, and side-view imaging. It is widely used in military and agriculture. , navigation, geographic surveillance and many other fields. Polarimetric SAR can obtain richer target information, and is highly valued in the field of international remote sensing. Therefore, polarimetric SAR image classification has become an important research direction of polarimetric SAR information processing. [0003] The existi...

AI Technical Summary

Problems solved by technology

[0005] Unsupervised classification methods include: H / α unsupervised classification proposed by Cloude et al., which obtains scattering entropy H and average scattering angle α characteristic parameters through Cloude target decomposition, and performs eight classifications on targets according to the range of these two parameters. In this method, the classification boundary is fixed and the division of regions is too arbitrary, and only the two parameters H and α are used, and the polarization information is not fully utilized, resulting in low classification accuracy; Lee et al. proposed the H method based on Cloude target decomposition and Wishart classifier. / α-Wishart unsupervised classification method, which adds Wishart iteration on the basis of the original H / α classification, which makes up for the defects of the fixed boundary of H / α classification, but this method cannot well maintain all kinds of polarization scattering Characteristics; Lee et al. proposed a polarimetric SAR image classification method based on Freeman decomposition, which mainly divides the polarization data according to the size of plane scattering power, dihedral scattering power and volume scattering power obtained by Freeman decomposition, and the initial Classification is performed to merge categories, and finally the Wishart classifier is used to reclassify. This method maintains the scattering characteristics of various types, but there are multi-category divisions and mergers, and the computational complexity is high.

[0006] Since the above method extracts features based on the original data of the polarimetric SAR image, the number of features obtained in this way is relatively small, and the polarization information and spatial correlation information of the polarimetric SAR image are not fully combined, and the information extraction of the polarimetric SAR image is not sufficient. , and finally classify directly, resulting in low classification accuracy of polarimetric SAR images

Images