Auto-segmentation based on graphcut and template

  • Zhang Hong*
  • , Zuo Wei
  • , Mu Ying
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, the main idea is to use the prior knowledge to guide the segmentation. Firstly the continuity among adjacent frames is used to create a motion template according to the Displaced Frame Difference's (DFD) higher character [1]. And then the color template is established by using the k-means clustering. Based upon the information derived from the previous two templates, the segmentation image is defined as foreground, background and boundary regions. Then, the segmentation problem is formulated as an energy minimization problem. The hard edge of foreground is then obtained by implementing graph-cut algorithm. Experimental results demonstrate the effectiveness of proposed algorithm.

Original languageEnglish
Title of host publicationMIPPR 2007
Subtitle of host publicationAutomatic Target Recognition and Image Analysis; and Multispectral Image Acquisition
DOIs
StatePublished - 2007
EventMIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition - Wuhan, China
Duration: 15 Nov 200717 Nov 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6786
ISSN (Print)0277-786X

Conference

ConferenceMIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition
Country/TerritoryChina
CityWuhan
Period15/11/0717/11/07

Keywords

  • Automatic video segmentation
  • Graph-cut algorithm
  • Template
  • Video object

Fingerprint

Dive into the research topics of 'Auto-segmentation based on graphcut and template'. Together they form a unique fingerprint.

Cite this