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 2009

Fingerprint

Stereo vision

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

Forward-backward study of the stereo vision problem. / de Menezes, Fortunato Silva; Geiger, Davi; Abreu e Silva, Ricardo Martins; Distler, George; Hu, Arefin.

In: Computer Physics Communications, Vol. 180, No. 4, 04.2009, p. 664-668.

Research output: Contribution to journalArticle

de Menezes, FS, Geiger, D, Abreu e Silva, RM, Distler, G & Hu, A 2009, 'Forward-backward study of the stereo vision problem', Computer Physics Communications, vol. 180, no. 4, pp. 664-668. https://doi.org/10.1016/j.cpc.2009.01.016
de Menezes, Fortunato Silva ; Geiger, Davi ; Abreu e Silva, Ricardo Martins ; Distler, George ; Hu, Arefin. / Forward-backward study of the stereo vision problem. In: Computer Physics Communications. 2009 ; Vol. 180, No. 4. pp. 664-668.
@article{4f422234374d452eba2e4864fa65ee77,
title = "Forward-backward study of the stereo vision problem",
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.",
keywords = "Forward-Backward algorithm, Hidden Markov models",
author = "{de Menezes}, {Fortunato Silva} and Davi Geiger and {Abreu e Silva}, {Ricardo Martins} and George Distler and Arefin Hu",
year = "2009",
month = "4",
doi = "10.1016/j.cpc.2009.01.016",
language = "English (US)",
volume = "180",
pages = "664--668",
journal = "Computer Physics Communications",
issn = "0010-4655",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - Forward-backward study of the stereo vision problem

AU - de Menezes, Fortunato Silva

AU - Geiger, Davi

AU - Abreu e Silva, Ricardo Martins

AU - Distler, George

AU - Hu, Arefin

PY - 2009/4

Y1 - 2009/4

N2 - 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.

AB - 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.

KW - Forward-Backward algorithm

KW - Hidden Markov models

UR - http://www.scopus.com/inward/record.url?scp=61649088366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61649088366&partnerID=8YFLogxK

U2 - 10.1016/j.cpc.2009.01.016

DO - 10.1016/j.cpc.2009.01.016

M3 - Article

AN - SCOPUS:61649088366

VL - 180

SP - 664

EP - 668

JO - Computer Physics Communications

JF - Computer Physics Communications

SN - 0010-4655

IS - 4

ER -