中文

Journal of Shanghai University（Natural Science Edition）

• Articles • Previous Articles     Next Articles

Stereo Video Object Segmentation Based on Disparity and Change Detection

GAO Xin1,AN Ping1,LIU Jia1,ZHANG Zhaoyang1,2   

  1. 1. School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China;
    2. Key Laboratory of Advanced Displays and System Application, Ministry of Education, Shanghai University, Shanghai 200072, China

  • Received:2005-05-25 Revised:1900-01-01 Online:1900-01-01 Published:1900-01-01
  • Contact: AN Ping1

Cited

7

Abstract:

Stereo video object segmentation is a key technology in the new generation video coding, video browsing, and Internet multimedia interacting, etc. In this paper, a stereo video object segmentation algorithm that combines various sources of information is proposed. Estimation of disparity based on edge character restriction is first adopted to obtain reliable disparity scene. The disparity information is used to initialize segmentation. Change detection information is then integrated to modify boundaries of disparity segmentation. Experimental results show effectiveness of the algorithm in the case of multiple object overlapping.

Key words: change detection

, disparity, object segmentation,

stereo video