The study of the proportion image of hyperspectral image

被引：1

作者：

Gong, YJ ^{[1
]}

Wu, JJ ^{[1
]}

Wu, ZS ^{[1
]}

Wang, XC ^{[1
]}

Yu, WY ^{[1
]}

Song, DC ^{[1
]}

机构：

[1] Xidian Univ, Sch Sci, Xian 710071, Peoples R China

来源：

Electronic Imaging and Multimedia Technology IV | 2005年 / 5637卷

关键词：

hyperspectral image; remote sensing; mixed pixel; proportion image; convex geometry; inherent proportion image; endmember proportions;

D O I：

10.1117/12.569856

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hyperspectral image can be analyzed by Convex Geometry Analysis(CGA) method. CGA method can unmix endmembers from hyperspectral image. The endmember proportions of mixed pixels can be calculated in inherent dimensional space, and a proportion image, which is called inherent proportion image, is obtained. The endmember proportions of mixed pixels can be calculated in n-space by the Constrained Least Squares, and a proportion image, which is called CLS proportion image, is obtained. In this paper, the inherent proportion image and CLS proportion image of a 30-band remote sensing image are obtained. The two proportion images are similar. The targets that are smaller than earth surface pixel can be identified by the inherent proportion image.

引用

页码：635 / 641

页数：7

共 13 条

[11] Automatic identification of end-members for the spectral decomposition of remotely sensed scenes [J].

Maselli, F ;

Pieri, M ;

Conese, C .

REMOTE SENSING FOR GEOGRAPHY, GEOLOGY, LAND PLANNING, AND CULTURAL HERITAGE, 1996, 2960 :104-109

[12] On independent component analysis applied to unmixing hyperspectral data [J].

Nascimento, JMP ;

Dias, JMB .

IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING IX, 2004, 5238 :306-315

[13] QUANTITATIVE-DETERMINATION OF MINERAL TYPES AND ABUNDANCES FROM REFLECTANCE SPECTRA USING PRINCIPAL COMPONENTS-ANALYSIS [J].

SMITH, MO ;

JOHNSON, PE ;

ADAMS, JB .

JOURNAL OF GEOPHYSICAL RESEARCH, 1985, 90 :C797-C804

← 1 2 →