Blind separation of spectral signatures in hyperspectral imagery

Author

Tu, T.-M. ; Huang, P.S. ; Chen, P.-Y.

Author_Institution

Dept. of Electr. Eng., Chung Cheng Inst. of Technol., Taoyuan, Taiwan

Volume

148

Issue

4

fYear

2001

fDate

8/1/2001 12:00:00 AM

Firstpage

217

Lastpage

226

Abstract

For the purpose of material identification, methods for exploring hyperspectral images with minimal human intervention have been investigated. Without any prior knowledge, it is extremely difficult to identify or determine how many endmembers in a scene. To tackle this problem, a new spectral unmixing technique, the spectral data explorer (SDE), is presented. SDE is a hybrid approach combining the optimal parts of fast independent component analysis (FastICA) and noise-adjusted principal components analysis (NAPCA). Experimental results show that SDE is highly efficient for separating significant signatures of hyperspectral images in a blind environment

Keywords

image processing; infrared imaging; noise; principal component analysis; remote sensing; spectral analysis; FastICA; NASA/JPL AVIRIS; NRL HYDICE; airborne visible/infra-red imaging spectrometer; blind separation; fast independent component analysis; hybrid approach; hyperspectral imagery; material identification; noise-adjusted principal components analysis; spectral data explorer; spectral signatures; spectral unmixing technique;

fLanguage

English

Journal_Title

Vision, Image and Signal Processing, IEE Proceedings -

Publisher

iet

ISSN

1350-245X

Type

jour

DOI

10.1049/ip-vis:20010314

Filename

955425