跳到主要导航 跳到搜索 跳到主要内容

Semi-supervised hyperspectral image classification with multiscale kernels

  • Beihang University
  • Beijing Institute of Remote Sensing Information
  • China Aerospace Science and Technology Corporation

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this letter, we propose a novel Laplacian least squares support vector machine in sum space (Lap-LS-SVM-SS) for semi-supervised HIC with multiscale kernels, which can simultaneously deal with the high- and low- frequency components of the target classification function with small and large scale kernels, respectively. The proposed method can solve the multi-class problem of hyperspectral dataset directly. The experimental results on AVIRIS Indian Pines dataset demonstrate that Lap-LS-SVM-SS yields superior classification performance over the conventional semi-supervised classifiers (e.g., LapSVM) in challenging small training labeled samples and a large amount of unlabeled samples.

源语言英语
主期刊名International Conference on Civil, Mechanical and Material Engineering, ICCMME 2018
编辑Jongwon Jung, Dongkeon Kim
出版商American Institute of Physics Inc.
ISBN(电子版)9780735416802
DOI
出版状态已出版 - 4 6月 2018
活动2018 International Conference on Civil, Mechanical and Material Engineering, ICCMME 2018 - Jeju Island, 韩国
期限: 16 3月 201818 3月 2018

出版系列

姓名AIP Conference Proceedings
1973
ISSN(印刷版)0094-243X
ISSN(电子版)1551-7616

会议

会议2018 International Conference on Civil, Mechanical and Material Engineering, ICCMME 2018
国家/地区韩国
Jeju Island
时期16/03/1818/03/18

指纹

探究 'Semi-supervised hyperspectral image classification with multiscale kernels' 的科研主题。它们共同构成独一无二的指纹。

引用此