A BP Training Fitting Method about Multivariate BRDF Based on B-spline Function

Author

Jun Yu ; Weina Tu ; Zhan Wang

Author_Institution

Dept. of Appl. Math., Nanjing Univ. of Sci. & Technol., Nanjing, China

fYear

2012

fDate

24-25 July 2012

Firstpage

30

Lastpage

32

Abstract

For a large number of experimental data, the BRDF surface fitting method based on B-spline function and least squares theory, the ill-conditioned normal equations, the low accuracy of the results and long CPU time may be appeared. Thereby, in this paper by using the BP learning method, combined with the training process of L-M algorithm, an improved method is presented. And the method is applied to the BDRF data processing, the result shows that this method is effective, and has greatly improved in accuracy and reduced running time.

Keywords

backpropagation; data handling; geophysics computing; least squares approximations; neural nets; remote sensing; splines (mathematics); surface fitting; B-spline function; BDRF data processing; BP learning method; BP training fitting method; BRDF surface fitting method; L-M algorithm; Levenberg-Marquardt algorithm; backpropagation; bidirectional reflectance distribution functions; least squares theory; multivariate BRDF; remote sensing application; Accuracy; Algorithm design and analysis; Fitting; Mathematical model; Neural networks; Splines (mathematics); Surface fitting; B spline function; BP algorithm; numerical analysis; surface fitting;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Computing Science (ICIC), 2012 Fifth International Conference on

Conference_Location

Liverpool

ISSN

2160-7443

Print_ISBN

978-1-4673-1985-0

Type

conf

DOI

10.1109/ICIC.2012.2

Filename

6258063