A Deep Learning Classification Scheme for PolSAR Image Based on Polarimetric Features

被引:1
|
作者
Zhang, Shuaiying [1 ]
Cui, Lizhen [2 ]
Dong, Zhen [1 ]
An, Wentao [3 ]
机构
[1] Natl Univ Def Technol NUDT, Coll Elect Sci & Engn, Changsha 410073, Peoples R China
[2] Univ Chinese Acad Sci, Coll Life Sci, Beijing 100049, Peoples R China
[3] Natl Satellite Ocean Applicat Serv, Beijing 100081, Peoples R China
基金
国家重点研发计划;
关键词
polarimetric synthetic aperture radar (PolSAR); reflection symmetric decomposition (RSD); data input scheme; land classification; polarimetric scattering characteristics; SAR DATA; SCATTERING MODEL; DECOMPOSITION; ALGORITHM; NETWORK;
D O I
10.3390/rs16101676
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant back-scattering information about objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features input into the deep learning network are the power values of polarimetric channels and contain complete polarimetric information. The other two input data schemes are designed to compare the proposed method. The neural network can utilize the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of the power-based scheme. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has a clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] POLSAR IMAGE CLASSIFICATION BASED-ON SEMI-SUPERVISED POLARIMETRIC FEATURE SELECTION
    Huang, Xiayuan
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 196 - 200
  • [32] Attention-Based Polarimetric Feature Selection Convolutional Network for PolSAR Image Classification
    Dong, Hongwei
    Zhang, Lamei
    Lu, Da
    Zou, Bin
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [33] Composite Kernel Method for PolSAR Image Classification Based on Polarimetric-Spatial Information
    Wang, Xianyuan
    Cao, Zongjie
    Ding, Yao
    Feng, Jilan
    APPLIED SCIENCES-BASEL, 2017, 7 (06):
  • [34] An Unsupervised Classification of PolSAR Image Based on Polarimetric Scattering Similarity and Complex Wishart Classifier
    Li, Jiatong
    Li, Dong
    Zhang, Yunhua
    Yang, Jiefang
    Liang, Liting
    2022 PHOTONICS & ELECTROMAGNETICS RESEARCH SYMPOSIUM (PIERS 2022), 2022, : 812 - 817
  • [35] POLSAR IMAGE CLASSIFICATION BASED ON POLARIMETRIC SCATTERING CODING AND SPARSE SUPPORT MATRIX MACHINE
    Liu, Xu
    Jiao, Licheng
    Zhang, Dan
    Liu, Fang
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 3181 - 3184
  • [36] SUPERVISED POLSAR IMAGE CLASSIFICATION BY COMBININGMULTIPLE FEATURES
    Huang, Xiayuan
    Nie, Xiangli
    Qiao, Hong
    Zhang, Bo
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 634 - 638
  • [37] MLR-SimSiam: A Contrastive Pretraining Model Based on Polarimetric Jittering and Mutual Learning Regularizer for PolSAR Image Classification
    Zhang, Lamei
    Han, Fangzhou
    Li, Tong
    Dai, Haishan
    Zou, Bin
    Dong, Hongwei
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 : 1 - 5
  • [38] Kernel Extreme Learning Machines for PolSAR Image Classification using Spatial Features
    Gokdag, Unsal
    Ustuner, Mustafa
    Bilgin, Gokhan
    Sanli, Fusun Balik
    2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
  • [39] An Efficient Classification Method of Fully Polarimetric SAR Image Based on Polarimetric Features and Spatial Features
    Xue, Xiaorong
    Di, Liping
    Guo, Liying
    Lin, Li
    2015 FOURTH INTERNATIONAL CONFERENCE ON AGRO-GEOINFORMATICS, 2015,
  • [40] LEARNING DEEP FEATURES FOR IMAGE EMOTION CLASSIFICATION
    Chen, Ming
    Zhang, Lu
    Allebach, Jan P.
    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 4491 - 4495