An unbiased and computationally efficient LS estimation method for identifying parameters of 2D noncausal SAR models

Author

Zhao, Ping-Ya ; Yu, Dao-Rong

Volume

41

Issue

2

fYear

1993

fDate

2/1/1993 12:00:00 AM

Firstpage

849

Lastpage

857

Abstract

An unbiased and computationally efficient modified least squares (LS) estimation method for identifying parameters of two-dimensional noncausal simultaneous autoregressive models is presented. Some intuitive and mathematical proof of the unbiasedness of the method are given, and a recursive in-order fast algorithm to implement it is introduced. Computer simulation results are given to sustain the theoretical analysis. Both the theoretical analysis and the computer simulation show that the method possesses much higher estimation accuracy and lower computational complexity than the conventional LS estimation method. Compared to the approximate maximum-likelihood method of Kashyap and Chellappa (1983), the scheme is much faster, has the same estimation accuracy, and is parallelizable

Keywords

computational complexity; image processing; least squares approximations; parameter estimation; statistical analysis; computational complexity; computationally efficient LS estimation method; computer simulation; estimation accuracy; image processing; modified least squares method; parallelizable scheme; parameter identification; recursive in-order fast algorithm; theoretical analysis; two-dimensional noncausal simultaneous autoregressive models; unbiasedness; Algorithm design and analysis; Computational complexity; Computational modeling; Computer simulation; Image analysis; Least squares approximation; Maximum likelihood estimation; Parameter estimation; Predictive models; Recursive estimation; Signal processing algorithms; Two dimensional displays;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.193222

Filename

193222