A Method for Hyperspectral Images Classification using Spectral Correlation

被引：0
|
作者：
Jing, Luo [1 ,2 ]
Fei, Hu [1 ,2 ]
Li Yun-lei [1 ,2 ]
Yue, Liu [1 ,2 ]
机构：
[1] Key Lab Adv Elect Engn & Energy Technol, Tianjin 300387, Peoples R China
[2] Tianjin Polytech Univ, Coll Elect Engn & Automat, Tianjin 300387, Peoples R China
来源：
2018 37TH CHINESE CONTROL CONFERENCE (CCC) | 2018年
基金：
中国国家自然科学基金;
关键词：
hyperspectral images classification; band correlation coefficient selection (BCCS); spectral correlation; Spectral Correlation(SC); ALGORITHM;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
To reduce the effects of information redundancy caused by noise and band correlation on the hyperspectral image analysis, a method for hyperspectral images classification using Spectral Correlation(HCSC) is proposed. Firstly, the hyperspectral images are preprocessed. Secondly, band selection algorithm based on correlation coefficient(BCCS) is proposed to reduce the information redundancy caused by adjacent bands. Thirdly, The spatial pixel purity index(SPPI) is used to extract the pure pixel and end-member extraction is accomplished. The experiments have been done on AVIRIS database. The experimental results have shown the proposed algorithm(HCSC) can improve the efficiency in the pure pixel extraction and classification, and the classification accuracy is 86.4%.
引用
收藏
页码：9067 / 9072
页数：6
相关论文
共 50 条
  • [41] A Pre-processing framework for spectral classification of hyperspectral images
    Singh, Simranjit
    Kasana, Singara Singh
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (01) : 243 - 261
  • [42] Spectral Unmixing for the Classification of Hyperspectral Images at a Finer Spatial Resolution
    Villa, Alberto
    Chanussot, Jocelyn
    Benediktsson, Jon Atli
    Jutten, Christian
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2011, 5 (03) : 521 - 533
  • [43] A multiscale modified minimum spanning forest method for spatial-spectral hyperspectral images classification
    Poorahangaryan, Fereshteh
    Ghassemian, Hassan
    EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2017,
  • [44] Phase correlation based supervised classification of hyperspectral images using multiple class representatives
    Demir, Begum
    Erturk, Sarp
    IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET, 2007, : 2822 - 2824
  • [45] Hyperspectral Image Spatial‑Spectral Classification Using Capsule Network Based Method
    Gao K.
    Yu X.
    Zhang P.
    Tan X.
    Liu B.
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2022, 47 (03): : 428 - 437
  • [46] Hyperspectral image classification using a spectral-spatial random walker method
    Ghasrodashti, Elham Kordi
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2019, 40 (10) : 3948 - 3967
  • [47] Research of spectral curvature correction method for hyperspectral images
    Shanghai Institute of Technical Physics, Chinese Academy of Science, Shanghai, 200083, China
    Proc SPIE Int Soc Opt Eng,
  • [48] Research of Spectral Curvature Correction Method for Hyperspectral Images
    Li, Lin
    Hu, Yong
    Wang, Yueming
    INTERNATIONAL SYMPOSIUM ON PHOTOELECTRONIC DETECTION AND IMAGING 2011: ADVANCES IN INFRARED IMAGING AND APPLICATIONS, 2011, 8193
  • [49] Hyperspectral Classification Using Spectral Magnitude and Gradient
    Zhang, Xiya
    Xu, Haiqing
    Li, Peijun
    2012 4TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING (WHISPERS), 2012,
  • [50] Classification of hyperspectral images via weighted spatial correlation representation
    Tu, Bing
    Li, Nanying
    Fang, Leyuan
    Fei, Hongyan
    He, Danbing
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 56 : 160 - 166
12345