Multiscale Superpixel-Level Subspace-Based Support Vector Machines for Hyperspectral Image Classification

被引:77
|
作者
Yu, Haoyang [1 ,2 ]
Gao, Lianru [3 ]
Liao, Wenzhi [4 ]
Zhang, Bing [1 ,2 ]
Pizurica, Aleksandra [4 ]
Philips, Wilfried [4 ]
机构
[1] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China
[2] Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
[3] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China
[4] Univ Ghent, TELIN, IMEC, Dept Telecommun & Informat Proc, B-9000 Ghent, Belgium
基金
中国国家自然科学基金;
关键词
Hyperspectral image classification; multiscale superpixel segmentation; subspace projection; support vector machines (SVM); SPECTRAL-SPATIAL CLASSIFICATION;
D O I
10.1109/LGRS.2017.2755061
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
This letter introduces a new spectral-spatial classification method for hyperspectral images. A multiscale superpixel segmentation is first used to model the distribution of classes based on spatial information. In this context, the original hyperspectral image is integrated with segmentation maps via a feature fusion process in different scales such that the pixel-level data can be represented by multiscale superpixel-level (MSP) data sets. Then, a subspace-based support vector machine (SVMsub) is adopted to obtain the classification maps with multiscale inputs. Finally, the classification result is achieved via a decision fusion process. The resulting method, called MSP-SVMsub, makes use of the spatial and spectral coherences, and contributes to better feature characterization. Experimental results based on two real hyperspectral data sets indicate that the MSP-SVMsub exhibits good performance compared with other related methods.
引用
收藏
页码:2142 / 2146
页数:5
相关论文
共 50 条
  • [1] Subspace-Based Support Vector Machines for Hyperspectral Image Classification
    Gao, Lianru
    Li, Jun
    Khodadadzadeh, Mahdi
    Plaza, Antonio
    Zhang, Bing
    He, Zhijian
    Yan, Huiming
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (02) : 349 - 353
  • [2] Hyperspectral Imagery Classification Based on Multiscale Superpixel-Level Constraint Representation
    Yu, Haoyang
    Zhang, Xiao
    Song, Meiping
    Hu, Jiaochan
    Guo, Qiandong
    Gao, Lianru
    [J]. REMOTE SENSING, 2020, 12 (20) : 1 - 21
  • [3] PSASL: Pixel-Level and Superpixel-Level Aware Subspace Learning for Hyperspectral Image Classification
    Mei, Jie
    Wang, Yuebin
    Zhang, Liqiang
    Zhang, Bing
    Liu, Suhong
    Zhu, Panpan
    Ren, Yingchao
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (07): : 4278 - 4293
  • [4] Subspace-based support vector machines for pattern classification
    Kitamura, Takuya
    Takeuchi, Syogo
    Abe, Shigeo
    Fukui, Kazuhiro
    [J]. NEURAL NETWORKS, 2009, 22 (5-6) : 558 - 567
  • [5] Superpixel-Level Weighted Label Propagation for Hyperspectral Image Classification
    Jia, Sen
    Deng, Xianglong
    Xu, Meng
    Zhou, Jun
    Jia, Xiuping
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (07): : 5077 - 5091
  • [6] Probabilistic Fusion of Pixel-Level and Superpixel-Level Hyperspectral Image Classification
    Li, Shutao
    Lu, Ting
    Fang, Leyuan
    Jia, Xiuping
    Benediktsson, Jon Atli
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (12): : 7416 - 7430
  • [7] Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields
    Yu, Haoyang
    Gao, Lianru
    Li, Jun
    Li, Shan Shan
    Zhang, Bing
    Benediktsson, Jon Atli
    [J]. REMOTE SENSING, 2016, 8 (04)
  • [8] Flexible Gabor-Based Superpixel-Level Unsupervised LDA for Hyperspectral Image Classification
    Jia, Sen
    Zhao, Qingqing
    Zhuang, Jiayue
    Tang, Dingding
    Long, Yaqian
    Xu, Meng
    Zhou, Jun
    Li, Qingquan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (12): : 10394 - 10409
  • [9] SUPERPIXEL-LEVEL CONSTRAINT REPRESENTATION FOR HYPERSPECTRAL IMAGERY CLASSIFICATION
    Yu, Haoyang
    Zhang, Xiao
    Song, Meiping
    Hue, Jiaochan
    Gao, Lianru
    [J]. IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 56 - 59
  • [10] Efficient Superpixel-Level Multitask Joint Sparse Representation for Hyperspectral Image Classification
    Li, Jiayi
    Zhang, Hongyan
    Zhang, Liangpei
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (10): : 5338 - 5351