Semi-automatic depth map extraction method for stereo video conversion

Tsung Han Tsai, Chen Shuo Fan, Chih Chi Huang

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

3 Scopus citations

Abstract

This paper present a semi-automatic method aimedto generate stereoscopic views estimating depth information from a single input video frame and decrease computation resources. Firstly, background modeling divides a 2D video into static background scene and moving object. By the viewer's acquired monocular depth cue, the user-defined points in the static scene are used to extract vanishing line. Then, the background depth map is determined and the moving objects are assigned depth values according to their position in the static scene. Finally, the motion based depth map and the geometry based map are integrated into one depth map by a depth fusion algorithm. Combining the depth map from this work and original 2D video can produce vivid 3D video.

Original languageEnglish
Title of host publicationProceedings - 2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012
Pages340-343
Number of pages4
DOIs
StatePublished - 2012
Event2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012 - Kitakyushu, Japan
Duration: 25 Aug 201228 Aug 2012

Publication series

NameProceedings - 2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012

Conference

Conference2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012
Country/TerritoryJapan
CityKitakyushu
Period25/08/1228/08/12

Keywords

  • 2d to 3d conversion
  • Depth estimation
  • Foreground detection

Fingerprint

Dive into the research topics of 'Semi-automatic depth map extraction method for stereo video conversion'. Together they form a unique fingerprint.

Cite this