Forward-backward study of the stereo vision problem

Fortunato Silva de Menezes, Davi Geiger, Ricardo Martins Abreu e Silva, George Distler, Arefin Hu

Research output: Contribution to journalArticle

Abstract

In stereo vision a pair of two-dimensional (2D) stereo images is given and the purpose is to find out the depth (disparity) of regions of the image in relation to the background, so that we can reconstruct the 3D structure of the image from the pair of 2D stereo images given. Using the Bayesian framework we implemented the Forward-Backward algorithm to unfold the disparity (depth) of a pair of stereo images. The results showed are very reasonable, but we point out there is room for improvement concerning the graph structure used.

Original languageEnglish (US)
Pages (from-to)664-668
Number of pages5
JournalComputer Physics Communications
Volume180
Issue number4
DOIs
StatePublished - Apr 1 2009

    Fingerprint

Keywords

  • Forward-Backward algorithm
  • Hidden Markov models

ASJC Scopus subject areas

  • Hardware and Architecture
  • Physics and Astronomy(all)

Cite this

de Menezes, F. S., Geiger, D., Abreu e Silva, R. M., Distler, G., & Hu, A. (2009). Forward-backward study of the stereo vision problem. Computer Physics Communications, 180(4), 664-668. https://doi.org/10.1016/j.cpc.2009.01.016