Classification of hyperspectral images based on two-channel convolutional neural network combined with support vector machine algorithm

被引:5
|
作者
Zhao, Wei [1 ]
Mu, Taoyang [1 ]
Li, Dan [1 ]
机构
[1] Northeast Forestry Univ, Informat & Comp Engn Coll, Harbin, Peoples R China
关键词
remote sensing; hyperspectral image; artificial intelligence; SPECTRAL-SPATIAL CLASSIFICATION; SYSTEM;
D O I
10.1117/1.JRS.14.024514
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Our study uses artificial intelligence and machine learning methods for dimensionality reduction, feature extraction, and classification of hyperspectral remote sensing images to detect subtle differences between different spectra. Our study also used hyperspectral remote sensing image data gathered by airborne visible infrared imaging spectrometer over the Indian Pines and Salinas test sites. Based on experimental analysis and comparison of mainstream classifiers and advanced algorithms, we propose a new classification mode for the hyperspectral image based on a two-channel fusion of convolutional neural network-support vector machine (CNN-SVM). This model gives full play to the advantages of CNN in feature extraction and the advantages of SVM in the classification. It also maximizes the generalization and accuracy of classification. The CNN is based on two-channel feature extraction, including spatial features and spectral features, which utilizes the characteristics of hyperspectral remote sensing images for classification. Experimental results show that the research is both theoretically and practically significant for improving the quality and accuracy of identification and classification. (C) 2020 Society of Photo Optical Instrumentation Engineers (SPIE)
引用
收藏
页数:16
相关论文
共 50 条
  • [31] Support vector machine and neural network for enhanced classification algorithm in ecological data
    B R.P.
    Hussain M.A.
    K S.
    CosioBorda R.F.
    C G.
    Measurement: Sensors, 2023, 27
  • [32] Classification of Hyperspectral Images based on Intrinsic Image Decomposition and Deep Convolutional Neural Network
    Beirami, Behnam Asghari
    Mokhtarzade, Mehdi
    2020 6TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2020,
  • [33] BRANCH AND BOUND BASED FEATURE ELIMINATION FOR SUPPORT VECTOR MACHINE BASED CLASSIFICATION OF HYPERSPECTRAL IMAGES
    Samiappan, Sathishkumar
    Prasad, Saurabh
    Bruce, Lori M.
    Hansen, Eric A.
    2011 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2011, : 2523 - 2526
  • [34] A Classification Algorithm of Hyperspectral Images Based on Double Channel Temporal Dense Network
    Zhang F.
    Zhang J.
    Pei C.
    Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University, 2020, 54 (04): : 126 - 132
  • [35] CONVOLUTIONAL NEURAL NETWORK BASED CLASSIFICATION FOR HYPERSPECTRAL DATA
    Jia, Peiyuan
    Zhang, Miao
    Yu, Wenbo
    Shen, Fei
    Shen, Yi
    2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 5075 - 5078
  • [36] Classification of Microscopic Hyperspectral Images of Blood Cells Based on Lightweight Convolutional Neural Network
    Fang, Jinghui
    ELECTRONICS, 2024, 13 (08)
  • [37] Mathematical Variable Detection based on Convolutional Neural Network and Support Vector Machine
    Bui Hai Phong
    Thang Manh Hoang
    Thi-Lan Le
    2019 INTERNATIONAL CONFERENCE ON MULTIMEDIA ANALYSIS AND PATTERN RECOGNITION (MAPR), 2019,
  • [38] Depth Map Super-Resolution Based on Two-Channel Convolutional Neural Network
    Li Sumei
    Lei Guoqing
    Fan Ru
    ACTA OPTICA SINICA, 2018, 38 (10)
  • [39] Deep proximal support vector machine classifiers for hyperspectral images classification
    Ganesan Kalaiarasi
    Sureshbabu Maheswari
    Neural Computing and Applications, 2021, 33 : 13391 - 13415
  • [40] Deep proximal support vector machine classifiers for hyperspectral images classification
    Kalaiarasi, Ganesan
    Maheswari, Sureshbabu
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (20): : 13391 - 13415