A fast two-stage classification method for high-dimensional remote sensing data

Author

Tu, Te-Ming ; Chen, Chin-Hsing ; Wu, Jiunn-Lin ; Chang, Chein-I

Author_Institution

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

Volume

36

Issue

1

fYear

1998

fDate

1/1/1998 12:00:00 AM

Firstpage

182

Lastpage

191

Abstract

Classification for high-dimensional remotely sensed data generally requires a large set of data samples and enormous processing time, particularly for hyperspectral image data. In this paper, the authors present a fast two-stage classification method composed of a band selection (BS) algorithm with feature extraction/selection (FSE) followed by a recursive maximum likelihood classifier (MLC). The first stage is to develop a BS algorithm coupled with FSE for data dimensionality reduction. The second stage is to design a fast recursive MLC (RMLC) so as to achieve computational efficiency. The experimental results show that the proposed recursive MLC, in conjunction with BS and FSE, reduces computing time significantly by a factor ranging from 30 to 145, as compared to the conventional MLC

Keywords

feature extraction; geophysical signal processing; geophysical techniques; image classification; remote sensing; band selection algorithm; computational efficiency; dimensionality reduction; feature extraction; feature selection; geophysical measurement technique; high-dimensional remote sensing; high-dimensional remotely sensed data; hyperspectral image; hyperspectral imaging; image classification; image processing; land surface; multidimensional signal processing; multispectral remote sensing; optical imaging; recursive maximum likelihood classifier; remote sensing; terrain mapping; two-stage classification method; vegetation mapping; Computational complexity; Computational efficiency; Feature extraction; Hyperspectral imaging; Hyperspectral sensors; Infrared imaging; Infrared spectra; Principal component analysis; Remote sensing; Spectroscopy;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.655328

Filename

655328