Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification

被引:30
|
作者
Cui, Yuanhao [1 ]
Liu, Fang [1 ]
Jiao, Licheng [1 ]
Guo, Yuwei [1 ]
Liang, Xuefeng [1 ]
Li, Lingling [1 ]
Yang, Shuyuan [1 ]
Qian, Xiaoxue [1 ]
机构
[1] Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Sch Artificial Intelligence,Joint Int Res Lab Int, Minist Educ,Int Res Ctr Intelligent Percept & Com, Xian 710071, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2022年 / 60卷
基金
中国国家自然科学基金;
关键词
Scattering; Training; Feature extraction; Adaptation models; Deep learning; Radar polarimetry; Kernel; Classification; polarimetric multipath convolutional neural network (CNN) (PolMPCNN); polarimetric synthetic aperture radar (PolSAR); DECOMPOSITION;
D O I
10.1109/TGRS.2021.3071559
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Scatter targets of complex land covers in polarimetric synthetic aperture radar (PolSAR) images are often randomly oriented and cause randomly fluctuating echoes, which brings a challenge to PolSAR image classification. Therefore, many existing methods have alleviated this problem through orientation compensation. However, there are still two obstacles that limit the improvement of classification accuracy. On the one hand, generally, these methods process PolSAR images with fixed polarization rotation angles, which is experience-dependent and inflexible. On the other hand, for the different land covers of a PolSAR image, the existing methods do not consider these rotation angles separately. For the first obstacle, we design a group of convolution kernels called polarization rotation kernels (PRKs) and utilize them to build the polarimetric convolutional neural network (CNN) (PolCNN). The PolCNN is the base network of our final model, and it can learn polarization rotation angles adaptively. For the second obstacle, we extend the PolCNN into a multipath structure, the final model polarimetric multipath CNN (PolMPCNN). The polarization rotation angles of different land covers are directly related to the networks of different paths within the PolMPCNN. Furthermore, we also put forward the two-scale sampling and the stagewise training algorithm in order that our PolMPCNN can fit different scales of PolSAR targets and pays more attention to difficult training samples. Experiments on real PolSAR images show that the proposed model achieves the best classification results with an extremely low sampling rate of 0.1%.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] A Quantum Convolutional Neural Network for Image Classification
    Lu, Yanxuan
    Gao, Qing
    Lu, Jinhu
    Ogorzalek, Maciej
    Zheng, Jin
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 6329 - 6334
  • [32] A Convolutional Fuzzy Neural Network for Image Classification
    Korshunova, Kseniya P.
    PROCEEDINGS OF THE 2018 3RD RUSSIAN-PACIFIC CONFERENCE ON COMPUTER TECHNOLOGY AND APPLICATIONS (RPC), 2018,
  • [33] Simple Convolutional Neural Network on Image Classification
    Guo, Tianmei
    Dong, Jiwen
    Li, Henjian
    Gao, Yunxing
    2017 IEEE 2ND INTERNATIONAL CONFERENCE ON BIG DATA ANALYSIS (ICBDA), 2017, : 721 - 724
  • [34] Quantum convolutional neural network for image classification
    Chen, Guoming
    Chen, Qiang
    Long, Shun
    Zhu, Weiheng
    Yuan, Zeduo
    Wu, Yilin
    PATTERN ANALYSIS AND APPLICATIONS, 2023, 26 (02) : 655 - 667
  • [35] Shallow convolutional neural network for image classification
    Lei, Fangyuan
    Liu, Xun
    Dai, Qingyun
    Ling, Bingo Wing-Kuen
    SN APPLIED SCIENCES, 2020, 2 (01):
  • [36] Food Image Classification with Convolutional Neural Network
    Islam, Md Tohidul
    Siddique, B. M. Nafiz Karim
    Rahman, Sagidur
    Jabid, Taskeed
    2018 INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATICS AND BIOMEDICAL SCIENCES (ICIIBMS), 2018, : 257 - +
  • [37] Image Classification Based on Convolutional Neural Network
    Prassanna, P. Lakshmi
    Sandeep, S.
    Rao, Kantha
    Sasidhar, T.
    Lavanya, D. Ragava
    Deepthi, G.
    SriLakshmi, N. Vijaya
    Mounika, P.
    Govardhani, U.
    SUSTAINABLE COMMUNICATION NETWORKS AND APPLICATION, ICSCN 2021, 2022, 93 : 833 - 842
  • [38] Medical Image Classification with Convolutional Neural Network
    Li, Qing
    Cai, Weidong
    Wang, Xiaogang
    Zhou, Yun
    Feng, David Dagan
    Chen, Mei
    2014 13TH INTERNATIONAL CONFERENCE ON CONTROL AUTOMATION ROBOTICS & VISION (ICARCV), 2014, : 844 - 848
  • [39] Quantum convolutional neural network for image classification
    Guoming Chen
    Qiang Chen
    Shun Long
    Weiheng Zhu
    Zeduo Yuan
    Yilin Wu
    Pattern Analysis and Applications, 2023, 26 : 655 - 667
  • [40] Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks
    Zhou, Yu
    Wang, Haipeng
    Xu, Feng
    Jin, Ya-Qiu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (12) : 1935 - 1939