Depth map generation from geometry and motion

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

1 Scopus citations

Abstract

As the demand for 3DTV keep increasing these years, the conversion from exist 2D videos to 3D ones becomes a new area of research. Depth map generation plays a key point in the process. Two most important clues of depth are geometry of the scene and motion vector. This paper presents an algorithm of depth map generation, which intends to get the depth map combines two aspects of information. Compared to the previous work, our method is improved in finding vanishing point, detect motion vectors, and depth map generation.

Original languageEnglish
Title of host publicationFifth International Conference on Digital Image Processing, ICDIP 2013
DOIs
StatePublished - 2013
Event5th International Conference on Digital Image Processing, ICDIP 2013 - Beijing, China
Duration: 21 Apr 201322 Apr 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8878
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference5th International Conference on Digital Image Processing, ICDIP 2013
Country/TerritoryChina
CityBeijing
Period21/04/1322/04/13

Keywords

  • 2d to 3d conversion
  • depth map
  • motion detect
  • vanishing point

Fingerprint

Dive into the research topics of 'Depth map generation from geometry and motion'. Together they form a unique fingerprint.

Cite this