Statistical Analysis of the LMS Algorithm Applied to Super-Resolution Image Reconstruction

Author

Costa, Guilherme Holsbach ; Bermudez, José Carlos Moreira

Author_Institution

Dept. of Electr. Eng., Univ. Fed. de Santa Catarina, Florianopolis

Volume

55

Issue

5

fYear

2007

fDate

5/1/2007 12:00:00 AM

Firstpage

2084

Lastpage

2095

Abstract

Super resolution reconstruction of image sequences is highly dependent on quality of the motion estimation between successive frames. This work presents a statistical analysis of the least mean square (LMS) algorithm applied to super resolution reconstruction of an image sequence with translational global motion. Deterministic recursions are derived for the mean and mean square behaviors of the reconstruction error as functions of the registration errors. The new model describes the behavior of the algorithm in realistic situations, and significantly improves the accuracy of a simple model available in the literature. Monte Carlo simulations show very good agreement between actual and predicted behaviors

Keywords

Monte Carlo methods; image reconstruction; image registration; image resolution; image sequences; least mean squares methods; motion estimation; statistical analysis; LMS algorithm; Monte Carlo simulations; image sequences; least mean square algorithm; motion estimation; registration errors; statistical analysis; super-resolution image reconstruction; translational global motion; Filtering algorithms; Image reconstruction; Image resolution; Image sequences; Kalman filters; Least squares approximation; Motion estimation; Signal processing algorithms; Signal resolution; Statistical analysis; Adaptive filtering; least mean square (LMS); registration error; statistical analysis; super resolution;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/TSP.2007.892704

Filename

4156369