Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
VIDEO OBJECT SEGMENTATION BASED ON OBJECT ENHANCEMENT AND REGION MERGING
 

Summary: VIDEO OBJECT SEGMENTATION BASED ON OBJECT ENHANCEMENT AND
REGION MERGING
Ken Ryan and Aishy Amer
Concordia University,
Electrical & Computer Engineering
Montreal, Quebec, Canada
{kenne ry, amer}@ece.concordia.ca
Langis Gagnon
Computer Research Institute of Montreal (CRIM)
Montreal, Quebec, Canada
langis.gagnon@crim.ca
ABSTRACT
This paper proposes a number of improvements to existing
work in off line video object segmentation. Object color and
motion variance, and histogram-based merging are used to
improve the initial segmentation. Segmentation quality mea-
sures taken from throughout the clip are used to enhance video
objects. Cumulative histogram-based merging, occlusion han-
dling, and island detection are used to help group regions
into meaningful objects. Objective and subjective tests were

  

Source: Amer, Aishy - Department of Electrical and Computer Engineering, Concordia University

 

Collections: Engineering