UM  > 科技學院  > 電腦及資訊科學系
Hyperspectral image classification using One Dimensional Manifold Embedding with Spectral-Spatial based affinity metric
Luo, Huiwu1; Tang, Yuan Yan1; Wang, Yulong1; Li, Chunli1; Wang, Jianzhong2; Hu, Tingbo3; Li, Hong4
2017-07-07
Conference Name2nd IEEE International Conference on Cybernetics, CYBCONF 2015
Source PublicationProceedings - 2015 IEEE 2nd International Conference on Cybernetics, CYBCONF 2015
Pages394-398
Conference Date6 24, 2015 - 6 26, 2015
Conference PlaceGdynia, Poland
CountryPoland
Author of SourceInstitute of Electrical and Electronics Engineers Inc.
PublisherIEEE
Abstract

In this paper, a novel classification paradigm, termed Spectral-Spatial One Dimensional Manifold Embedding (SS1DME), is proposed for classification of hyperspectral imagery (HSI). The proposed paradigm integrates the spectral affinity and spatial information into a uniform metric framework. In SS1DME, a spectral-spatial affinity metric is utilized to learn the similarity of HSI pixels. Moreover, a pixel sorted based classification scheme, called 1-Dimensional Manifold Embedding (1DME), which is an extension of smooth ordering, is introduced for objective classification. Four main steps are involved in SS1DME. First, for a high dimensional data set, the proposed paradigm employed the spectral-spatial affinity metric to calculate pixelwise affinity. Next, we embed the whole data set into multiple 1-dimensional manifolds so that connected points have the shortest distance. Then, using the spinning average technique and self-learning scheme, a feasible confident set is constructed from the unlabeled set, where data points in feasible confident set are added to the labeled set in proportion. Finally, we use the extended labeled set to learn the interpolated function, which will lead to classification of unlabeled points. This approach is experimentally superior to some traditional alternatives in terms of classification performance indicators. 

KeywordFeature Extraction 1-dimensional Manifold Embedding Smooth Ordering Pixel Sorting Spectral-spatial Information Self-learning Hyperspectral Image Classification
DOIhttps://doi.org/10.1109/CYBConf.2015.7175966
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Cybernetics
WOS IDWOS:000373207200069
全文获取链接
引用统计
被引频次[WOS]:2   [WOS记录]     [WOS相关记录]
Document TypeConference paper
专题DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.University of Macau, China;
2.Sam Houston State University, Huntsville; TX; 77341, United States;
3.National University of Defense Technology, Changsha, Hunan; 410073, China;
4.Huazhong University of Science and Technology, Wuhan; 430074, China
First Author AffilicationUniversity of Macau
推荐引用方式
GB/T 7714
Luo, Huiwu,Tang, Yuan Yan,Wang, Yulong,et al. Hyperspectral image classification using One Dimensional Manifold Embedding with Spectral-Spatial based affinity metric[C]//Institute of Electrical and Electronics Engineers Inc.:IEEE,2017:394-398.
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
Google Scholar
中相似的文章 Google Scholar
[Luo, Huiwu]的文章
[Tang, Yuan Yan]的文章
[Wang, Yulong]的文章
Baidu academic
中相似的文章 Baidu academic
[Luo, Huiwu]的文章
[Tang, Yuan Yan]的文章
[Wang, Yulong]的文章
Bing Scholar
中相似的文章 Bing Scholar
[Luo, Huiwu]的文章
[Tang, Yuan Yan]的文章
[Wang, Yulong]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。