Visualization and unsupervised classification of changes in multispectral satellite imagery

被引：43

作者：

Canty, Morton J. ^{[1
]}

Nielsen, Allan A.

机构：

[1] Forschungszentrum Julich, D-52425 Julich, Germany

[2] Tech Univ Denmark, DK-2800 Lyngby, Denmark

来源：

INTERNATIONAL JOURNAL OF REMOTE SENSING | 2006年 / 27卷 / 18期

关键词：

15;

D O I：

10.1080/01431160500222608

中图分类号：

TP7 [遥感技术];

学科分类号：

081102 ; 0816 ; 081602 ; 083002 ; 1404 ;

摘要：

The statistical techniques of multivariate alteration detection, minimum/maximum autocorrelation factors transformation, expectation maximization and probabilistic label relaxation are combined in a unified scheme to visualize and to classify changes in multispectral satellite data. The methods are demonstrated with an example involving bitemporal LANDSAT TM imagery.

引用

页码：3961 / 3975

页数：15

共 15 条

[1]

Anderson TW., 2003, INTRO MULTIVARIATE S

[2]

Bishop C. M., 1996, Neural networks for pattern recognition

[3] Automatic analysis of the difference image for unsupervised change detection [J].