Sparse depth estimation using multi-view 3D modeling

Jinjin Li, Lina Karam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth using the estimated scale factor. Results are presented to illustrate the performance of the developed system. It is shown that the implemented 2D to 3D conversion system results in a reconstructed depth map that matches the ground-truth depth data.

Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings
Pages151-154
Number of pages4
DOIs
StatePublished - 2012
Event2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Las Vegas, NV, United States
Duration: Jan 12 2011Jan 14 2011

Publication series

Name2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings

Other

Other2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012
Country/TerritoryUnited States
CityLas Vegas, NV
Period1/12/111/14/11

Keywords

  • 3D reconstruction
  • Depth estimation
  • Euclidean reconstruction
  • Multi-view
  • Sparse depth map

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Sparse depth estimation using multi-view 3D modeling'. Together they form a unique fingerprint.

Cite this