Stereoscopic video generation method using motion analysis

Donghyun Kim, Dongbo Min, Kwanghoon Sohn

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

21 Scopus citations

Abstract

Stereoscopic video generation method can produce stereo-scopic contents from conventional video filmed from monoscopic camera. We propose stereoscopic video generation method using motion-to-disparity conversion considering multi-user condition and characteristics of display device. Field of view, maximum and minimum values of disparity are calculated through initialization process in order to apply various types of 3D display. After motion estimation, we propose three cues to decide the scale factor of motion-to-disparity conversion which are magnitude of motion, camera movement and scene complexity. Subjective evaluation is performed by comparing videos captured from stereoscopic camera and generated from one view of stereoscopic video.

Original languageEnglish
Title of host publicationProceedings of 3DTV-CON
DOIs
StatePublished - 2007
Event1st International Conference on 3DTV, 3DTV-CON 2007 - Kos, Greece
Duration: 7 May 20079 May 2007

Publication series

NameProceedings of 3DTV-CON

Conference

Conference1st International Conference on 3DTV, 3DTV-CON 2007
Country/TerritoryGreece
CityKos
Period7/05/079/05/07

Keywords

  • Multimedia systems
  • Stereoscopic video generation

Fingerprint

Dive into the research topics of 'Stereoscopic video generation method using motion analysis'. Together they form a unique fingerprint.

Cite this