Anchorperson extraction for Picture in Picture news video

Dong Xu, Xuelong Li, Zhengkai Liu, Yuan Yuan

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Picture in Picture news video is one typical kind of video sequences, where some regions undergo the moving camera and the others undergo the static camera. Actually it is a very difficult for computer to distinguish whether the motion is caused by the moving objects themselves or the moving camera, thus extracting anchorperson from this kind of video becomes a challenging vision task. To our knowledge, it is the first time to address this kind of application. Change detection is implemented to achieve fast, automatic and robust anchorperson extraction with the aid of a simple anchorperson model, which is initialized once in the first frame. The experiment results demonstrate our performance.

Original languageEnglish
Pages (from-to)1587-1594
Number of pages8
JournalPattern Recognition Letters
Volume25
Issue number14
DOIs
StatePublished - 15 Oct 2004
Externally publishedYes

Keywords

  • Multiple motion video
  • Picture in Picture news video
  • Video segmentation

Fingerprint

Dive into the research topics of 'Anchorperson extraction for Picture in Picture news video'. Together they form a unique fingerprint.

Cite this