Saved in:
Bibliographic Details
Main Authors: Kerfa, Djoudi, Ghorbel, Faouzi, MHIRI, Slim
Format: Recurso digital
Language:
Published: Zenodo 2023
Online Access:https://doi.org/10.5281/zenodo.15586706
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901405623648256
author Kerfa, Djoudi
Ghorbel, Faouzi
MHIRI, Slim
author_facet Kerfa, Djoudi
Ghorbel, Faouzi
MHIRI, Slim
contents <p>In this paper, a two-step block matching approach for motion estimation is proposed. To<br>reduce the complexity of the algorithm, the static and dynamic blocks are identified using the<br>unsupervised Bayesian classifier and the Gaussian Expectation of Maximization algorithm, and<br>the final position of the dynamic blocks is found using the bloc matching algorithm and the Star<br>Diamond Pattern. Based on a comparison with existing methods, the proposed method can<br>produce faster calculation with good PSNR values.<br>Key words Motion estimation, Block matching algorithm, Bootstrap Gaussian Expectation<br>Maximization Algorithm, Unsupervised Bayesian Classifier</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15586706
institution Zenodo
language
publishDate 2023
publisher Zenodo
record_format zenodo
spellingShingle An efficient algorithm for fast block matching using unsupervised bayesian classifier with bootstrap gaussian expectation maximization algorithm
Kerfa, Djoudi
Ghorbel, Faouzi
MHIRI, Slim
<p>In this paper, a two-step block matching approach for motion estimation is proposed. To<br>reduce the complexity of the algorithm, the static and dynamic blocks are identified using the<br>unsupervised Bayesian classifier and the Gaussian Expectation of Maximization algorithm, and<br>the final position of the dynamic blocks is found using the bloc matching algorithm and the Star<br>Diamond Pattern. Based on a comparison with existing methods, the proposed method can<br>produce faster calculation with good PSNR values.<br>Key words Motion estimation, Block matching algorithm, Bootstrap Gaussian Expectation<br>Maximization Algorithm, Unsupervised Bayesian Classifier</p>
title An efficient algorithm for fast block matching using unsupervised bayesian classifier with bootstrap gaussian expectation maximization algorithm
url https://doi.org/10.5281/zenodo.15586706