Please use this identifier to cite or link to this item:
Title: Video segmentation by level set.
Keywords: video,segmentation,level,set,graph,cut
Issue Date: 31-Mar-2014
Citation: WANG PEI-LIN (2014-03-31). Video segmentation by level set.. ScholarBank@NUS Repository.
Abstract: Video segmentation is a process that partitions a video into multiple segments frame by frame. The goal of segmentation is to simplify the representation of the video into something that is more meaningful and easier to analyze. Different from image segmentation, it is more difficult to cut out an object from video sequences than from one still image. Because in a video, there are many more frames to be segmented. It is possible to propagate the segmentation from the first frame to the later frames by analyzing the motion information, while motion estimation is often fragile especially at occlusion boundaries or motion blurred regions. Extensive research has been done in video segmentation in recent years since it is fundamentally important and useful. This thesis develops a novel interactive video segmentation algorithm.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
WangPL.pdf1.5 MBAdobe PDF



Page view(s)

checked on Sep 21, 2018


checked on Sep 21, 2018

Google ScholarTM


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