Mixed-pixel classification for hyperspectral images based on multichannel singular spectrum analysis

Cheng Tan Tung; Din Chang Tseng; Yeou Long Tsai

Mixed-pixel classification for hyperspectral images based on multichannel singular spectrum analysis

Cheng Tan Tung, Din Chang Tseng, Yeou Long Tsai

Department of Computer Science and Information Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper, a spectral unmixing technique based on multichannel singular spectrum analysis (MSSA) is applied to derive quantitative information about general land-cover types whose spectra can be determined from the image. The proposed approach can tolerate white noise in the linear model; moreover, we also provide an automatic mechanism to eliminate the undesired singular values as many as possible to get better results. Several experiments for hyperspectral images were conducted to validate the spectral unmixing procedure. Comparisons with the LSOSP approach were also given.

Original language	English
Pages	2370-2372
Number of pages	3
State	Published - 2001
Event	2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001) - Sydney, NSW, Australia Duration: 9 Jul 2001 → 13 Jul 2001

Conference

Conference	2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001)
Country/Territory	Australia
City	Sydney, NSW
Period	9/07/01 → 13/07/01

Cite this

@conference{1b2ff71f10ee475b91ad90bb92493b09,

title = "Mixed-pixel classification for hyperspectral images based on multichannel singular spectrum analysis",

abstract = "In this paper, a spectral unmixing technique based on multichannel singular spectrum analysis (MSSA) is applied to derive quantitative information about general land-cover types whose spectra can be determined from the image. The proposed approach can tolerate white noise in the linear model; moreover, we also provide an automatic mechanism to eliminate the undesired singular values as many as possible to get better results. Several experiments for hyperspectral images were conducted to validate the spectral unmixing procedure. Comparisons with the LSOSP approach were also given.",

author = "Tung, {Cheng Tan} and Tseng, {Din Chang} and Tsai, {Yeou Long}",

year = "2001",

language = "???core.languages.en_GB???",

pages = "2370--2372",

note = "null ; Conference date: 09-07-2001 Through 13-07-2001",

}

TY - CONF

T1 - Mixed-pixel classification for hyperspectral images based on multichannel singular spectrum analysis

AU - Tung, Cheng Tan

AU - Tseng, Din Chang

AU - Tsai, Yeou Long

PY - 2001

Y1 - 2001

N2 - In this paper, a spectral unmixing technique based on multichannel singular spectrum analysis (MSSA) is applied to derive quantitative information about general land-cover types whose spectra can be determined from the image. The proposed approach can tolerate white noise in the linear model; moreover, we also provide an automatic mechanism to eliminate the undesired singular values as many as possible to get better results. Several experiments for hyperspectral images were conducted to validate the spectral unmixing procedure. Comparisons with the LSOSP approach were also given.

AB - In this paper, a spectral unmixing technique based on multichannel singular spectrum analysis (MSSA) is applied to derive quantitative information about general land-cover types whose spectra can be determined from the image. The proposed approach can tolerate white noise in the linear model; moreover, we also provide an automatic mechanism to eliminate the undesired singular values as many as possible to get better results. Several experiments for hyperspectral images were conducted to validate the spectral unmixing procedure. Comparisons with the LSOSP approach were also given.

UR - http://www.scopus.com/inward/record.url?scp=0035572223&partnerID=8YFLogxK

M3 - 會議論文

AN - SCOPUS:0035572223

SP - 2370

EP - 2372

Y2 - 9 July 2001 through 13 July 2001

ER -

Mixed-pixel classification for hyperspectral images based on multichannel singular spectrum analysis

Abstract

Conference

Fingerprint

Cite this