Kernel Joint Sparse Representation Based on Self-Paced Learning for Hyperspectral Image Classification

被引:5
|
作者
Hu, Sixiu [1 ]
Peng, Jiangtao [1 ]
Fu, Yingxiong [1 ]
Li, Luoqing [1 ]
机构
[1] Hubei Univ, Fac Math & Stat, Hubei Key Lab Appl Math, Wuhan 430062, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
hyperspectral image classification; self-paced learning; kernel; joint sparse representation; SPATIAL CLASSIFICATION;
D O I
10.3390/rs11091114
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Self-Paced Joint Sparse Representation for the Classification of Hyperspectral Images
    Peng, Jiangtao
    Sun, Weiwei
    Du, Qian
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (02): : 1183 - 1194
  • [2] SELF-PACED LEARNING WITH SUPERPIXELWISE FEATURES FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Tai, Xiaoxiao
    Wang, Guangxing
    Han, Lirong
    Zhang, Xiaoyu
    Ren, Peng
    IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 60 - 63
  • [3] Weighted Kernel joint sparse representation for hyperspectral image classification
    Hu, Sixiu
    Xu, Chunhua
    Peng, Jiangtao
    Xu, Yan
    Tian, Long
    IET IMAGE PROCESSING, 2019, 13 (02) : 254 - 260
  • [4] Euler Kernel Mapping for Hyperspectral Image Clustering via Self-Paced Learning
    Zhang, Fenggan
    Yan, Hao
    Zhao, Jianwei
    Hu, Haojie
    REMOTE SENSING, 2024, 16 (21)
  • [5] Self-Paced Learning-Based Probability Subspace Projection for Hyperspectral Image Classification
    Yang, Shuyuan
    Feng, Zhixi
    Wang, Min
    Zhang, Kai
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (02) : 630 - 635
  • [6] Adaptive kernel sparse representation based on multiple feature learning for hyperspectral image classification
    Li, Dan
    Wang, Qiang
    Kong, Fanqiang
    NEUROCOMPUTING, 2020, 400 : 97 - 112
  • [7] Weighted multifeature hyperspectral image classification via kernel joint sparse representation
    Zhang, Erlei
    Zhang, Xiangrong
    Jiao, Licheng
    Liu, Hongying
    Wang, Shuang
    Hou, Biao
    NEUROCOMPUTING, 2016, 178 : 71 - 86
  • [8] Local Matrix Feature-Based Kernel Joint Sparse Representation for Hyperspectral Image Classification
    Chen, Xiang
    Chen, Na
    Peng, Jiangtao
    Sun, Weiwei
    REMOTE SENSING, 2022, 14 (17)
  • [9] Hyperspectral image classification via nonlocal joint kernel sparse representation based on local covariance
    Li, Dan
    Kong, Fanqiang
    Wang, Qiang
    Signal Processing, 2021, 180
  • [10] Log-Euclidean Kernel-Based Joint Sparse Representation for Hyperspectral Image Classification
    Yang, Weidong
    Peng, Jiangtao
    Sun, Weiwei
    Du, Qian
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2019, 12 (12) : 5023 - 5034