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.
Year
DOI
Venue
2009
10.1016/j.cpc.2009.01.016
Computer Physics Communications
Keywords
Field
DocType
02.50.Tt,02.60.Pn,95.75.Mn,95.75.Pq
Computer vision,Graph,Forward–backward algorithm,Pattern recognition,Stereopsis,Artificial intelligence,Hidden Markov model,Mathematics,Computer stereo vision,Bayesian probability
Journal
Volume
Issue
ISSN
180
4
0010-4655
Citations 
PageRank 
References 
0
0.34
2
Authors
5
Name
Order
Citations
PageRank
Fortunato S. De Menezes192.00
Davi Geiger21050353.66
Ricardo Martins Abreu e Silva300.34
George Distler400.34
Arefin Hu500.34