back to author index
   
title:
 
Head-Shoulder Moving Object Contour Tracking using Shape Model
publication:
 
JCIS-2006 Proceedings
part of series:
  Advances in Intelligent Systems Research
ISBN:
  978-90-78677-01-7
ISSN:
  1951-6851
DOI:
  doi:10.2991/jcis.2006.266 (how to use a DOI)
author(s):
 
Yong-Ren Huang, Chung-Ming Kuo, Chaur-Heh Hsieh
corresponding author:
 
Yong-Ren Huang
publication date:
 
October 2006
keywords:
 
moving object contour tracking, shape model,
abstract:
 
This paper proposes a new approach for tracking the contour of moving object for head-shoulder video sequence using initial shape model. First, we can utilize manual process or some segmentation approach to obtain the initial shape model. Then, we detect the changing ratio of intensity outside the bounding box in background area. And, the OR operation is employed to obtain a combined shape which is composed of initial shape model and mesh-based temporal segmentation result by motion activity. Finally, we propose a new iterative pixel-based erosion algorithm for obtaining exact object shape using local gradient along the boundary of combined shape in a counting window.
copyright:
 
© Atlantis Press. This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
full text: