Parallel computing of covariance matrix and its application on hyperspectral data process

Author

Wang, Mao-zhi ; Wang, Da-ming ; Xu, Wen-xi ; Chen, Bin-yang ; Guo, Ke

Author_Institution

Geomathematics Key Lab. of Sichuan Province, Chengdu Univ. of Technol., Chengdu, China

fYear

2012

fDate

22-27 July 2012

Firstpage

4058

Lastpage

4061

Abstract

A parallel algorithm of covariance matrix, which is used to realize the dimensionality reduction process of hyperspectral image based on Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF), is proposed in this paper. The performance of the parallel algorithm according to the experiment under cluster circumstance with message passing interface (MPI) is discussed. The Gustafsun Law and Amdahl Law usually used to analyze the parallel algorithm results are also discussed in this experiment. At last, some further research areas and questions have been listed.

Keywords

covariance matrices; geophysical image processing; message passing; parallel processing; principal component analysis; Amdahl law; Gustafsun law; MNF; MPI; PCA; covariance matrix; dimensionality reduction process; hyperspectral data process; hyperspectral image; message passing interface; minimum noise fraction; parallel algorithm; parallel computing; principal component analysis; Colon; Covariance matrix; Hyperspectral imaging; Parallel algorithms; Principal component analysis; Random variables; covariance matrix; hyperspectral image; message passing interface; parallel algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International

Conference_Location

Munich

ISSN

2153-6996

Print_ISBN

978-1-4673-1160-1

Electronic_ISBN

2153-6996

Type

conf

DOI

10.1109/IGARSS.2012.6350518

Filename

6350518