Modeling The New Three Step Search Algorithm For Motion Estimation In Image Sequence In Matlab

Leng, Huey Ley (2006) Modeling The New Three Step Search Algorithm For Motion Estimation In Image Sequence In Matlab. Project Report. UTeM, Melaka, Malaysia. (Submitted)

	PDF (24 Pages) Modeling_The_New_Three_Step_Search_-_24_Pages.pdf - Submitted Version Download (1MB)
	PDF (Full Text) Modeling_The_New_Three_Step_Search.pdf - Submitted Version Restricted to Registered users only Download (4MB)

Abstract

This thesis focusing on a Motion Estimation that play an important role in motion compensated image sequence coding. Due to the huge computation demand of the conventional full search method, investigation of fast motion estimation algorithms has been a focus of research. There are few types of fast motion estimation algorithms - Three Step Search {TSS), New Three Step Search (NTSS), Full Search (FS) and the Diamond Search (DS). The New Three Step Search (NTSS) Algorithm has been proposed for the study in this project. The features of this algorithm are that it employs a center-biased checking point pattern in the first step, which is derived by making the search adaptive to the motion vector distribution, and a halfway-stop technique to reduce the computation cost. Implementation and performance analysis of New Three Step Search (NTSS) is done by using MATLAB.

Actions (login required)

View Item