Robust Weighting Nearest Regularized Subspace Classifier for PolSAR Imagery

被引:14
|
作者
Ni, Jun [1 ]
Zhang, Fan [1 ]
Yin, Qiang [1 ]
Li, Heng-Chao [2 ]
机构
[1] Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
[2] Southwest Jiaotong Univ, Sichuan Prov Key Lab Informat Coding & Transmiss, Chengdu 610031, Sichuan, Peoples R China
基金
中国国家自然科学基金;
关键词
Polarimetric SAR; classification; NRS; robust statistics; COLLABORATIVE-REPRESENTATION; STATISTICS;
D O I
10.1109/LSP.2019.2937176
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Polarimetric synthetic aperture radar (PolSAR) imagery classification is an important part of SAR data interpretation. The number of available labeled samples limits the applications of supervised classifiers. In order to solve this issue, the representation based classification algorithms have been widely used. Usually, PolSAR image features are extracted by various methods, and their divergence is very significant. In the data representation based methods, the feature divergence is ignored in the distance metric, thus the different features have the same metric contributions. In this letter, we propose a robust weighting nearest regularized subspace (NRS) method, which introduces the robust statistics to construct the weights of distance metric according to the feature divergence. This method can increase the representation ability of the training samples by the weighted calculation of the biasing Tikhonov matrix. The experimental results show that the weighted distance metric can boost the original NRS classifier by 1.5%, and prove that the feature divergence should he taken into account in the data representation process.
引用
收藏
页码:1496 / 1500
页数:5
相关论文
共 50 条
  • [1] Nearest-Regularized Subspace Classification for PolSAR Imagery Using Polarimetric Feature Vector and Spatial Information
    Zhang, Fan
    Ni, Jun
    Yin, Qiang
    Li, Wei
    Li, Zheng
    Liu, Yifan
    Hong, Wen
    REMOTE SENSING, 2017, 9 (11)
  • [2] UNSUPERVISED NEAREST REGULARIZED SUBSPACE FOR ANOMALY DETECTION IN HYPERSPECTRAL IMAGERY
    Li, Wei
    Du, Qian
    2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, : 1055 - 1058
  • [3] Nonlinear Nearest Subspace Classifier
    Zhang, Li
    Zhou, Wei-Da
    Liu, Bing
    NEURAL INFORMATION PROCESSING, PT II, 2011, 7063 : 638 - +
  • [4] Nearest Regularized Subspace for Hyperspectral Classification
    Li, Wei
    Tramel, Eric W.
    Prasad, Saurabh
    Fowler, James E.
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (01): : 477 - 489
  • [5] Multi-GPU Implementation of Nearest-Regularized Subspace Classifier for Hyperspectral Image Classification
    Li, Zhixin
    Ni, Jun
    Zhang, Fan
    Li, Wei
    Zhou, Yongsheng
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 (13) : 3534 - 3544
  • [6] A robust subspace classifier
    Bischof, H
    Leonardis, A
    Pezzei, F
    FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 114 - 116
  • [7] Evolved feature weighting for random subspace classifier
    Nanni, Loris
    Lumini, Alessandra
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (02): : 363 - 366
  • [8] Regularized Class-Specific Subspace Classifier
    Zhang, Rui
    Nie, Feiping
    Li, Xuelong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (11) : 2738 - 2747
  • [9] Wavelet-based nearest-regularized subspace for noise-robust hyperspectral image classification
    Li, Wei
    Liu, Kui
    Su, Hongjun
    JOURNAL OF APPLIED REMOTE SENSING, 2014, 8
  • [10] k-NS: A Classifier by the Distance to the Nearest Subspace
    Liu, Yiguang
    Ge, Shuzhi Sam
    Li, Chunguang
    You, Zhisheng
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (08): : 1256 - 1268