Residual network based on entropy-anisotropy-alpha target decomposition for polarimetric SAR image classification

被引:3
|
作者
Ghazvinizadeh, Amir Hossein [1 ]
Imani, Maryam [1 ]
Ghassemian, Hassan [1 ]
机构
[1] Tarbiat Modares Univ, Fac Elect & Comp Engn, Image Proc & Informat Anal Lab, Tehran, Iran
关键词
Target decomposition; Convolutional network; Residual learning; Polarimetric SAR; Feature extraction; CONVOLUTIONAL NEURAL-NETWORK; SIGNATURES; FEATURES; DOMAIN;
D O I
10.1007/s12145-023-00944-6
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Convolutional residual networks have shown great success for classification of polarimetric synthetic aperture radar (PolSAR) images especially when the depth of network is increased and limited training samples are available. But, the ability of convolutional kernels is in extraction of spatial features from neighboring pixels. They may not sufficiently able to extract the radar's physical features from the PolSAR images. To deal with this difficulty, a residual network is proposed in this work. In addition to the feature maps extracted by convolutional kernels of previous layers, the proposed network injects the physical feature maps extracted by the H-A-alpha\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathrm{\alpha }$$\end{document} decomposition to each addition layer. Moreover, the use of a convolutional autoencoder behind the residual blocks is proposed to reduce the speckle noise. The proposed method provides more accurate classification maps compared to conventional residual networks and several state-of-the-art methods. However, it needs more running time for implementation.
引用
收藏
页码:357 / 366
页数:10
相关论文
共 50 条
  • [31] POLARIMETRIC SAR IMAGE CLASSIFICATION BASED ON CONTEXTUAL SPARSE REPRESENTATION
    Zhang, Lamei
    Sun, Liangjie
    Moon, Wooil M.
    2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 1837 - 1840
  • [32] A novel measure of target scattering randomness with application to polarimetric SAR image classification
    Zhao, Lingjun
    Kuang, Gangyao
    Zhou, Xiaoguang
    Wang, Na
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2012, 33 (02) : 534 - 551
  • [33] A residual convolutional neural network for polarimetric SAR image super-resolution
    Shen, Huanfeng
    Lin, Liupeng
    Li, Jie
    Yuan, Qiangqiang
    Zhao, Lingli
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2020, 161 (161) : 90 - 108
  • [34] Polarimetric SAR Image Classification based on Kernel Sparse Representation
    Wang, Xiao
    Zhang, Lamei
    BinZou
    Qiao, Zhijun
    COMPRESSIVE SENSING VII: FROM DIVERSE MODALITIES TO BIG DATA ANALYTICS, 2018, 10658
  • [35] Classification of Polarimetric SAR Image based on Improved Fuzzy Clustering
    Cheng, Zheng
    Han, Ping
    Han, Binbin
    Sun, Jiahui
    2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 584 - 589
  • [36] Model-Based Target Scattering Decomposition of Polarimetric SAR Tomography
    Aghababaee, Hossein
    Sahebi, Mahmod Reza
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (02): : 972 - 983
  • [37] Stochastic configuration network-based SAR image target classification approach
    Wang, Yan P.
    Zhang, Yi B.
    Zhang, Yuan
    Fang, Jun
    Qu, Hong Q.
    JOURNAL OF ENGINEERING-JOE, 2019, 2019 (21): : 8121 - 8124
  • [38] Polarimetric SAR Sea Ice Classification Based on Target Decompositional Features
    Zhao Q.
    Guo S.
    Li X.
    Li Y.
    Cehui Xuebao/Acta Geodaetica et Cartographica Sinica, 2018, 47 (12): : 1609 - 1620
  • [39] Polarimetric SAR Image Classification Using Radial Basis Function Neural Network
    Ince, Turker
    PIERS 2010 CAMBRIDGE: PROGRESS IN ELECTROMAGNETICS RESEARCH SYMPOSIUM PROCEEDINGS, VOLS 1 AND 2, 2010, : 60 - 65
  • [40] Image processing in polarimetric SAR images using a hybrid Entropy Decomposition and Maximum Likelihood (EDML)
    Tan, Chue Poh
    Lim, Ka Sing
    Ewe, Hong Tat
    PROCEEDINGS OF THE 5TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS, 2007, : 418 - 422