UM
Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework
Luo, Huiwu1; Tang, Yuan Yan1; Wang, Yulong1,2; Wang, Jianzhong3; Biuk-Aghai, Robert P.1; Pan, Jianjia1; Liu, Runzong4; Yang, Lina5
2017-05
Source PublicationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN1939-1404
Volume10Issue:5Pages:1987-2001
Abstract

Hyperspectral image (HSI) classification has become an active research area in the remote sensing field. In order to construct a simple and reliable classifier, learning an adequate distance metric from a given HSI dataset is still a critical and challenging task in many HSI applications. In this paper, a novel distance metric learning (DML) framework based on 1-D manifold embedding (1DME), named DL1DME, is proposed for HSI classification. The 1DME framework was developed by using the recently developed smooth ordering technique. This framework enables us to elaborately exploit the benefits of DML in the development of the 1DME algorithm. The core of the state-of-the-art DML is to learn aMahalanobis matrix from the given dataset that better describes the similarity between pixels. Largest margin nearest neighbors (LMNN) and information theoretic metric learning (ITML) are employed for the Mahalanobis matrix learning. Then, based on the affinity defined by the Mahalanobis matrix, the preclassifiers are constructed using the simple 1-D regularization on 1DME; and they predict the labels of the test data. By a voting rule, the pixels labeled in the same class by most of the preclassifiers are voted into the confidently predicted set, which are then merged with the current labeled set. The labeled set enlargement process is repeated if the original one has a very small size. The final classifier is then constructed in the 1DME framework again, but based on the enlarged labeled set. According to the aforementioned strategy, two novel DML-based 1DME classification algorithms, DL1DME-LMNN and DL1DME-ITML, are developed in this paper.

Keyword1-d Manifold Embedding (1dme) Hyperspectral Image (Hsi) Classification Metric Learning Smooth Ordering
DOIhttps://doi.org/10.1109/JSTARS.2017.2657600
URLView the original
Indexed BySCI
Language英语
WOS Research AreaEngineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS SubjectEngineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS IDWOS:000399682500026
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:6   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Corresponding AuthorLuo, Huiwu; Tang, Yuan Yan; Biuk-Aghai, Robert P.; Pan, Jianjia; Liu, Runzong; Yang, Lina
Affiliation1.Faculty of Science and Technology, University of Macau, 999078 Macau, China
2.school of Information Science and Engineering, Chengdu University, 610106 Chengdu China
3.Department of Mathematics and Statistics, Sam Houston State University, Huntsville, TX 77341 USA
4.College of Computer Science, Chongqing University, Chongqing 400030, China
5.e School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
First Author AffilicationFaculty of Science and Technology
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Luo, Huiwu,Tang, Yuan Yan,Wang, Yulong,et al. Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(5):1987-2001.
APA Luo, Huiwu.,Tang, Yuan Yan.,Wang, Yulong.,Wang, Jianzhong.,Biuk-Aghai, Robert P..,...&Yang, Lina.(2017).Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,10(5),1987-2001.
MLA Luo, Huiwu,et al."Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework".IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10.5(2017):1987-2001.
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.