A dual-scale siamese densely connected network with MRF for SAR image classification. Issue 3 (4th March 2022)

• Record Type: Journal Article
• Authors: Cheng, Dongdong; Dong, Zhangyu; Wang, Jun; Yang, Xuezhi
• Is Part Of: Remote sensing letters. Volume 13:Issue 3(2022)
• Page Start: 247
• Page End: 257
• Publication Date: 2022-03-04
• Subjects: Remote sensing -- Periodicals; Remote sensing; Periodicals; 621.3678
• DOI: 10.1080/2150704X.2021.2018144
• Languages: English
• ISSNs: 2150-704X

Abstract

ABSTRACT: Recently, Convolutional Neural Network (CNN) has achieved some success in synthetic aperture radar (SAR) image classification. This outstanding performance mainly depends on a large number of training samples, but achieved satisfactory classification results with limited training samples remains a challenge. To address this problem, we propose a dual-scale Siamese densely connected network with Markov Random Fields (DS-SDCNet-MRF) for single-polarization SAR image classification. First, the Siamese densely connected network (SDCNet) is proposed to fully extract discriminative features under limited samples. Then, the proposed DS-SDCNet is constructed with two SDCNets of different scales to produce complementary classification results. Among them, the large-scale SDCNet has a better classification result in the homogeneous region, while the small-scale SDCNet tends to provide good detail preservation. Finally, an improved MRF model which combined the category probability information is proposed to further improve the classification performance. Experimental results on simulated and real single-polarization SAR data demonstrate that the proposed method achieves more encouraging classification performance than the current state-of-the-art classification methods with limited samples.