UM
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
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionUniversity of Macau
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
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo, Huiwu]'s Articles
[Tang, Yuan Yan]'s Articles
[Wang, Yulong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo, Huiwu]'s Articles
[Tang, Yuan Yan]'s Articles
[Wang, Yulong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo, Huiwu]'s Articles
[Tang, Yuan Yan]'s Articles
[Wang, Yulong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.