loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
First International Symposium on 3D Data Processing Visualization and Transmission (3DPVT'02)
Using the Expectation-Maximization Algorithm for Depth Estimation and Segmentation of Multi-view Images
Padova, Italy
June 19-June 21
ISBN: 0-7695-1521-5
ASCII Text
x 
 
N. Grammalidis, L. Bleris, Michael G. Strintzis, "Using the Expectation-Maximization Algorithm for Depth Estimation and Segmentation of Multi-view Images," 3D Data Processing Visualization and Transmission, International Symposium on, pp. 686, First International Symposium on 3D Data Processing Visualization and Transmission (3DPVT'02), 2002.
 
 
BibTex
x
 
@article{ 10.1109/TDPVT.2002.1024141,
author = {N. Grammalidis and L. Bleris and Michael G. Strintzis},
title = {Using the Expectation-Maximization Algorithm for Depth Estimation and Segmentation of Multi-view Images},
journal ={3D Data Processing Visualization and Transmission, International Symposium on},
volume = {0},
year = {2002},
isbn = {0-7695-1521-5},
pages = {686},
doi = {http://doi.ieeecomputersociety.org/10.1109/TDPVT.2002.1024141},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - 3D Data Processing Visualization and Transmission, International Symposium on
TI - Using the Expectation-Maximization Algorithm for Depth Estimation and Segmentation of Multi-view Images
SN - 0-7695-1521-5
SP
EP
A1 - N. Grammalidis,
A1 - L. Bleris,
A1 - Michael G. Strintzis,
PY - 2002
KW - null
VL - 0
JA - 3D Data Processing Visualization and Transmission, International Symposium on
ER -
 
N. Grammalidis, University of Thessaloniki
L. Bleris, University of Thessaloniki
Michael G. Strintzis, University of Thessaloniki
An algorithm for joint depth estimation and segmentation from multi-view images is presented.The distribution of the luminance of each image pixel is modeled as a random variable,which is approximated by a "mixture of Gaussians model". After recovering 3-D motion, a reference image is segmented into a fixed number of regions, each characterized by a distinct affine depth model with three parameters. The estimated depth parameters and segmentation masks are iteratively estimated using an Expectation-Maximization algorithm, similar to that proposed in [1 ]. In addition, the proposed algorithm is extended for cases where more than two images are available.
Citation:
N. Grammalidis, L. Bleris, Michael G. Strintzis, "Using the Expectation-Maximization Algorithm for Depth Estimation and Segmentation of Multi-view Images," 3dpvt, pp.686, First International Symposium on 3D Data Processing Visualization and Transmission (3DPVT'02), 2002
Usage of this product signifies your acceptance of the Terms of Use.