Joint supervised-unsupervised nonlinear unmixing of hyperspectral images using kernel method

Hong Xiao, Hui Liu, Jie Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In hyper spectral images pixels are mixtures of spectral components associated to pure materials. Nonlinear unmixing of observed pixels is a challenging task in hyper spectral imagery. In this paper, a joint supervised unsupervised nonlinear unmixing scheme is proposed based on the recent advance of kernel based regression and analysis techniques. The proposed scheme takes advantage of high quality training data from the unsupervised kernel algorithm and fast learning and inference speed of the supervised learning algorithm. Experiments on synthetic and real data show the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings - 2014 5th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages582-585
Number of pages4
ISBN (Electronic)9781479942619
DOIs
StatePublished - 4 Dec 2014
Externally publishedYes
Event2014 5th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2014 - Zhangjiajie, Hunan, China
Duration: 15 Jun 201416 Jun 2014

Publication series

NameProceedings - 2014 5th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2014

Conference

Conference2014 5th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2014
Country/TerritoryChina
CityZhangjiajie, Hunan
Period15/06/1416/06/14

Keywords

  • Coherence Criterion
  • Hyperspctral Image
  • Joint Supervised-unspervised Method
  • Kernel Method
  • Nonlinear Unmixing

Fingerprint

Dive into the research topics of 'Joint supervised-unsupervised nonlinear unmixing of hyperspectral images using kernel method'. Together they form a unique fingerprint.

Cite this