Extracting key moving objects in video

Dong Xu, Zheng Kai Liu, Yuan Yuan, Xuelong Li

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

Abstract

This paper presents a novel scheme for extracting the key moving objects in picture in picture news video. In this kind of video, some moving objects undergo the static camera while the others do not. Actually it is very difficult for computer to distinguish whether the motion is caused by the moving objects themselves or the moving camera by the frame difference only. So in the paper, the fast, automatic and robust anchorperson extraction is achieved by the simple anchorperson model. The experimental results demonstrate good performances.

Original languageEnglish
Title of host publication6th International Conference on Advanced Communication Technology
Subtitle of host publicationBroadband Convergence Network Infrastructure
Pages984-987
Number of pages4
StatePublished - 2004
Externally publishedYes
Event6th International Conference on Advanced Communication Technology: Broadband Convergence Network Infrastructure - Phoenix Park, Korea, Republic of
Duration: 9 Feb 200411 Feb 2004

Publication series

Name6th International Conference on Advanced Communication Technology: Broadband Convergence Network Infrastructure
Volume2

Conference

Conference6th International Conference on Advanced Communication Technology: Broadband Convergence Network Infrastructure
Country/TerritoryKorea, Republic of
CityPhoenix Park
Period9/02/0411/02/04

Keywords

  • Key moving objects extraction
  • Multiple motion video
  • Video segmentation

Fingerprint

Dive into the research topics of 'Extracting key moving objects in video'. Together they form a unique fingerprint.

Cite this