Feature extraction of hyperspectral data using the Best Wavelet Packet Basis

Author

Hsu, Pai-Hui ; Tseng, Yi-Hsing

Author_Institution

Dept. of Surveying Eng., Nat. Cheng Kung Univ., Tainan, Taiwan

Volume

3

fYear

2002

fDate

24-28 June 2002

Firstpage

1667

Abstract

An adaptive wavelet decomposition algorithm called the Best Wavelet Packet Basis is used to extract the most useful spectral features from the original hyperspectral data for classification applications. Tested on a set of AVIRIS data, the novel feature extraction method is evaluated and compared with some contemporary feature extraction methods.

Keywords

adaptive signal processing; feature extraction; geophysical signal processing; geophysical techniques; image classification; multidimensional signal processing; remote sensing; terrain mapping; vegetation mapping; wavelet transforms; AVIRIS; Best Wavelet Packet Basis; IR; adaptive wavelet decomposition algorithm; best wavelet packet basis; feature extraction; geophysical measurement technique; hyperspectral remote sensing; image classification; image processing; infrared; land surface; multispectral remote sensing; spectral features; terrain mapping; vegetation mapping; visible; Cost function; Data mining; Feature extraction; Fourier transforms; Hyperspectral imaging; Hyperspectral sensors; Libraries; Time frequency analysis; Wavelet packets; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International

Print_ISBN

0-7803-7536-X

Type

conf

DOI

10.1109/IGARSS.2002.1026215

Filename

1026215