Please use this identifier to cite or link to this item:
Main Title: Adaptive multi-pattern fast block-matching algorithm based on Motion Classification techniques
Author(s): González-Díaz, Iván
de-Frutos-López, Manuel
Sanz-Rodríguez, Sergio
Díaz-de-María, Fernando
Type: Conference Object
Language Code: en
Abstract: Motion estimation is the most time-consuming subsystem in a video codec. Thus, more efficient methods of motion estimation should be investigated. Real video sequences usually exhibit a wide-range of motion content as well as different degrees of detail, which become particularly difficult to manage by typical block-matching algorithms. Recent developments in the area of motion estimation have focused on the adaptation to video contents. Adaptive thresholds and multi-pattern search algorithms have shown to achieve good performance when they success to adjust to motion characteristics. This paper proposes an adaptive algorithm, called MCS, that makes use of an especially tailored classifier that detects some motion cues and chooses the search pattern that best fits to them. Specifically, a hierarchical structure of binary linear classifiers is proposed. Our experimental results show that MCS notably reduces the computational cost with respect to an state-of-the-art method while maintaining the quality.
Issue Date: 2007
Date Available: 9-Mar-2017
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): block-matching
binary linear classifier
motion classification
motion estimation
Proceedings Title: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing : ICASSP
Publisher: IEEE
Publisher Place: New York, NY [u.a.]
Volume: 1
Publisher DOI: 10.1109/ICASSP.2007.366123
Page Start: I-1177
Page End: I-1180
EISSN: 2379-190X
ISBN: 1-4244-0727-3
ISSN: 1520-6149
Appears in Collections:FG Architektur eingebetteter Systeme » Publications

Files in This Item:
File Description SizeFormat 
2007_GonzalezDiaz_et-al.pdf2.11 MBAdobe PDFThumbnail

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.