Spectral-Locational-Spatial Manifold Learning for Hyperspectral Images Dimensionality Reduction

被引:7
|
作者
Li, Na [1 ]
Zhou, Deyun [1 ]
Shi, Jiao [1 ]
Wu, Tao [1 ]
Gong, Maoguo [2 ]
机构
[1] Northwestern Polytech Univ, Sch Elect & Informat, 127 West Youyi Rd, Xian 710072, Peoples R China
[2] Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Minist Educ, Xian 710071, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
dimensionality reduction; hyperspectral images; manifold learning; classification; spectral-locational-spatial; LAPLACIAN EIGENMAPS; CLASSIFICATION;
D O I
10.3390/rs13142752
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Dimensionality reduction (DR) plays an important role in hyperspectral image (HSI) classification. Unsupervised DR (uDR) is more practical due to the difficulty of obtaining class labels and their scarcity for HSIs. However, many existing uDR algorithms lack the comprehensive exploration of spectral-locational-spatial (SLS) information, which is of great significance for uDR in view of the complex intrinsic structure in HSIs. To address this issue, two uDR methods called SLS structure preserving projection (SLSSPP) and SLS reconstruction preserving embedding (SLSRPE) are proposed. Firstly, to facilitate the extraction of SLS information, a weighted spectral-locational (wSL) datum is generated to break the locality of spatial information extraction. Then, a new SLS distance (SLSD) excavating the SLS relationships among samples is designed to select effective SLS neighbors. In SLSSPP, a new uDR model that includes a SLS adjacency graph based on SLSD and a cluster centroid adjacency graph based on wSL data is proposed, which compresses intraclass samples and approximately separates interclass samples in an unsupervised manner. Meanwhile, in SLSRPE, for preserving the SLS relationship among target pixels and their nearest neighbors, a new SLS reconstruction weight was defined to obtain the more discriminative projection. Experimental results on the Indian Pines, Pavia University and Salinas datasets demonstrate that, through KNN and SVM classifiers with different classification conditions, the classification accuracies of SLSSPP and SLSRPE are approximately 4.88%, 4.15%, 2.51%, and 2.30%, 5.31%, 2.41% higher than that of the state-of-the-art DR algorithms.
引用
收藏
页数:25
相关论文
共 50 条
  • [1] Dimensionality Reduction of Hyperspectral Imagery Based on Spatial-Spectral Manifold Learning
    Huang, Hong
    Shi, Guangyao
    He, Haibo
    Duan, Yule
    Luo, Fulin
    IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (06) : 2604 - 2616
  • [2] SSMD: Dimensionality Reduction and Classification of Hyperspectral Images Based on Spatial-Spectral Manifold Distance Metric Learning
    Jin, Yao
    Dong, Yanni
    Zhang, Yuxiang
    Hu, Xiangyun
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [3] Dimensionality Reduction of Hyperspectral Images Based on Improved Spatial-Spectral Weight Manifold Embedding
    Liu, Hong
    Xia, Kewen
    Li, Tiejun
    Ma, Jie
    Owoola, Eunice
    SENSORS, 2020, 20 (16) : 1 - 25
  • [4] A Semisupervised Spatial Spectral Regularized Manifold Local Scaling Cut With HGF for Dimensionality Reduction of Hyperspectral Images
    Mohanty, Ramanarayan
    Happy, S. L.
    Routray, Aurobinda
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (06): : 3423 - 3435
  • [5] THE MANIFOLD LEARNING FOR DIMENSIONALITY REDUCTION WITH HYPERSPECTRAL IMAGE
    Zheng, Zezhong
    Chen, Pengxu
    Zhu, Mingcang
    Huang, Zhiqin
    He, Yong
    Feng, Yicong
    Lu, Yufeng
    Yu, Zhenlu
    Yu, Shijie
    Wang, Shengli
    Li, Jiang
    2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 2757 - 2760
  • [6] Spatial-Spectral Multiple Manifold Discriminant Analysis for Dimensionality Reduction of Hyperspectral Imagery
    Shi, Guangyao
    Huang, Hong
    Liu, Jiamin
    Li, Zhengying
    Wang, Lihua
    REMOTE SENSING, 2019, 11 (20)
  • [7] Hyperspectral image classification based on manifold spectral dimensionality reduction and deep learning method
    Shi Y.
    Ma D.
    Lyu J.
    Li J.
    Shi J.
    Lyu, Jie (rsxust@163.com), 1600, Chinese Society of Agricultural Engineering (36): : 151 - 160
  • [8] Hybrid Dimensionality Reduction Technique for Hyperspectral Images Using Random Projection and Manifold Learning
    Mohan, Alkha
    Venkatesan, M.
    TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING, 2020, 12237 : 116 - 127
  • [9] An Optimization Technique for Linear Manifold Learning-Based Dimensionality Reduction: Evaluations on Hyperspectral Images
    Ozturk, Umit
    Yilmaz, Atinc
    APPLIED SCIENCES-BASEL, 2021, 11 (19):
  • [10] Learning a Robust Local Manifold Representation for Hyperspectral Dimensionality Reduction
    Hong, Danfeng
    Yokoya, Naoto
    Zhu, Xiao Xiang
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2017, 10 (06) : 2960 - 2975