Polarimetric SAR image classification using 3D generative adversarial network

Lu Liu,Guobao Feng

doi:10.1051/matecconf/202133608012

Abstract

In this paper, a new architecture of three-dimensional deep convolutional generative adversarial network(3D-DCGAN) is specially defined to solve the unstable training problem of GAN and make full use of the information involved in polarimetric data. Firstly, a data cube with nine components of polarimetric coherency matrix are directly used as the input features of DCGAN. After that, a 3D convolutional model is designed as the components of generator and discriminator to construct the 3D-DCGAN, which considers the effective feature extraction capability of 3D convolutional neural network(CNN). Finally parameters of the network are fine-tuned to realize the polarimetric SAR image classification. The experiments results show the feasibility and efficiency of the proposed method.

Highlights

Polarimetric SAR(PolSAR) data has more characteristics of polarimetric, phase and space, providing reliable data resources for precise land cover classification
Many kinds of classification methods based deep neural network have been used in the field of PolSAR image classification, such as Deep Belief Network (DBN) [3], Convolutional Neural Network (CNN)[4] and Generative Adversarial Network (GAN) [5], etc
A data cube with nine components of polarimetric coherency matrix are directly used as the input features of DCGAN

Summary

Introduction

Polarimetric SAR(PolSAR) data has more characteristics of polarimetric, phase and space, providing reliable data resources for precise land cover classification. Many kinds of classification methods based deep neural network have been used in the field of PolSAR image classification, such as Deep Belief Network (DBN) [3], Convolutional Neural Network (CNN)[4] and Generative Adversarial Network (GAN) [5], etc. The training process of GAN[6] is unstable and falling to the local optimum, various various variants of GAN have been proposed to solve the problem, such as Deep Convolutional GAN(DCGAN)[7], Conditional GAN(CGAN)[8], Wasserstein GAN[9], etc. A new type of three-dimensional(3D) DCGAN is specially defined to solve the unstable training problem of GAN and make full use of the information involved in polarimetric data. The experiments results show the feasibility and efficiency of the proposed method

Deep Convolutional GAN

Proposed Method

Experiments

Methods

Findings

Conclusions