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
  • [21] Polarimetric SAR urban classification using the Touzi target scattering decomposition
    Bhattacharya, A.
    Touzi, R.
    CANADIAN JOURNAL OF REMOTE SENSING, 2011, 37 (04) : 323 - 332
  • [22] Monte Carlo Evaluation of Multi-Look Effect on Entropy/Alpha/Anisotropy Parameters of Polarimetric Target Decomposition
    Lee, Jong-Sen
    Ainsworth, Thomas L.
    Grunes, Mitchell R.
    Lopez-Martinez, Carlos
    2006 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, 2006, : 52 - +
  • [23] SAR Image Target Recognition Based on Improved Residual Attention Network
    Shi Baodai
    Zhang Qin
    Li Yao
    Li Yuhuan
    LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (08)
  • [24] Novel features for polarimetric SAR image classification by neural network
    Khan, KU
    Yang, J
    PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 165 - 170
  • [25] An entropy based classification scheme for land applications of polarimetric SAR
    Cloude, SR
    Pottier, E
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1997, 35 (01): : 68 - 78
  • [26] CLASSIFICATION OF POLARIMETRIC SAR IMAGE BASED ON THE SUBSPACE METHOD
    Xu Juan
    Li Zhen
    Tian Bangsen
    Chen Quan
    Zhang Ping
    3RD ISPRS IWIDF 2013, 2013, 40-7-W1 : 145 - 148
  • [27] Polarimetric SAR Image Classification Based on Feature Enhanced Superpixel Hypergraph Neural Network
    Geng, Jie
    Wang, Ru
    Jiang, Wen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [28] Effect of Different Target Decomposition Techniques on Classification Accuracy for Polarimetric SAR Data
    Turkar, Varsha
    Rao, Y. S.
    TECHNOLOGY SYSTEMS AND MANAGEMENT, 2011, 145 : 138 - 145
  • [29] PolSARNet: A Deep Fully Convolutional Network for Polarimetric SAR Image Classification
    Mullissa, Adugna G.
    Persello, Claudio
    Stein, Alfred
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2019, 12 (12) : 5300 - 5309
  • [30] Identification of Snow Using Fully Polarimetric SAR Data Based On Entropy and Anisotropy
    Varade, Divyesh
    Singh, Gulab
    Dikshit, Onkar
    Manickam, Surendar
    WATER RESOURCES RESEARCH, 2020, 56 (02)