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
N1 - Funding Information:
One of us (F.S.d.M.) wish to thank the financial support of CAPES under project number BEX-240106/1 as well as the hospitality provided in the Courant Institute (New York University) where this work was performed.
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
SN - 0010-4655
VL - 180
SP - 664
EP - 668
JO - Computer Physics Communications
JF - Computer Physics Communications
IS - 4
ER -