A Novel Deep Fully Convolutional Network for PolSAR Image Classification

Yangyang Li,Guangyuan Liu,Licheng Jiao,Yanqiao Chen

doi:10.3390/rs10121984

Abstract

Polarimetric synthetic aperture radar (PolSAR) image classification has become more and more popular in recent years. As we all know, PolSAR image classification is actually a dense prediction problem. Fortunately, the recently proposed fully convolutional network (FCN) model can be used to solve the dense prediction problem, which means that FCN has great potential in PolSAR image classification. However, there are some problems to be solved in PolSAR image classification by FCN. Therefore, we propose sliding window fully convolutional network and sparse coding (SFCN-SC) for PolSAR image classification. The merit of our method is twofold: (1) Compared with convolutional neural network (CNN), SFCN-SC can avoid repeated calculation and memory occupation; (2) Sparse coding is used to reduce the computation burden and memory occupation, and meanwhile the image integrity can be maintained in the maximum extent. We use three PolSAR images to test the performance of SFCN-SC. Compared with several state-of-the-art methods, SFCN-SC achieves promising results in PolSAR image classification.

Highlights

Polarimetric synthetic aperture radar (PolSAR), which can utilize SAR complex images in different polarimetric channels to recognize the orientation, geometric shape, configuration and composition of targets [1], has become one of the most advanced technologies [2]
In order to provide a general solution to the problems aforementioned above, we propose sliding window fully convolutional network (SFCN)
Based on SFCN and sparse coding, we propose sliding window fully convolutional network and sparse coding (SFCN-SC) for PolSAR image classification, which can obtain excellent classification results while reducing the computational burden and memory occupation

Summary

Introduction

Polarimetric synthetic aperture radar (PolSAR), which can utilize SAR complex images in different polarimetric channels to recognize the orientation, geometric shape, configuration and composition of targets [1], has become one of the most advanced technologies [2]. The studies on the applications of PolSAR data, especially PolSAR image classification, have attracted more and more attention [4,5]. Some researchers thought the statistical distribution of PolSAR data could be used for PolSAR image classification [14,15]. Based on the complex Wishart distributions of the covariance matrix and coherency matrix, Lee et al [15,16] proposed Wishart distance to classify the PolSAR images. Many machine learning methods, such as k-nearest neighbor (KNN) [17], sparse representation [18], support vector machine (SVM) [19,20,21], Bayes [22] and neural network [23,24,25], have been applied in PolSAR image classification. Ayhan et al [29] demonstrated that image fusion is helpful to pixel clustering and anomaly detection in multispectral image, which is instructive for PolSAR image classification

Methods

Results

Discussion

Conclusion