Bio-Inspired Neural Networks for Block Based Motion Estimation

In the multi-view video coding, both temporal and interview redundancies can be exploited by using standard block-based motion estimation technique. This paper describes a novel Bio-inspired neural networks model to enhance regions and extract contours of image for block-based motion estimation. We...

Full description

Saved in:
Bibliographic Details
Published inJournal of algorithms & computational technology Vol. 8; no. 4; pp. 471 - 482
Main Authors Yuan, Youwei, Xu, Weilei, Yuan, Xudong, Yan, Lamei, Deris, M. Mat
Format Journal Article
LanguageEnglish
Published London, England SAGE Publications 01.12.2014
SAGE Publishing
Subjects
Algorithms
Blocking
Computation
Computer simulation
Image enhancement
Mathematical models
Motion simulation
Neural networks
Peak signal-to-noise ratio (PSNR)
Bio-inspired neural networks (BINN)
Motion Estimation (ME)
Online AccessGet full text

Cover

More Information
Summary:In the multi-view video coding, both temporal and interview redundancies can be exploited by using standard block-based motion estimation technique. This paper describes a novel Bio-inspired neural networks model to enhance regions and extract contours of image for block-based motion estimation. We implements the optimized algorithm in the reference model of H.264 compiled by VC6.0, and chooses six typical video sequences for simulation comparison. Experiments performed show the good visual results which can reduces the computational complexity in a certain degree and enhances encoding efficiency with few changes in the reconstructed image quality and bit rate.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1748-3018
1748-3026
DOI:10.1260/1748-3018.8.4.471