Hierarchical disparity estimation with energy-based regularization
Hierarchical disparity estimation with energy-based regularization
We propose a hierarchical disparity estimation algorithm with energy-based regularization. Initial disparity vectors are obtained from downsampled stereo images using a feature-based region-dividing disparity estimation technique. Dense disparities are estimated from these initial vectors with shape-adaptive windows in full resolution images. Finally, the vector fields are regularized with the minimization of the energy functional which considers both fidelity and smoothness of the fields. The first two steps provide highly reliable disparity vectors, so that local minimum problem can be avoided in regularization step. The proposed algorithm generates accurate disparity map which is smooth inside objects while preserving its discontinuities in boundaries. Experimental results are presented to illustrate the capabilities of the proposed disparity estimation technique.
Algorithms, Data reduction, Optical resolving power, Vectors, Disparity estimation, Stereo images, Image processing
373-376
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sohn, K.
15547878-23a1-4428-90b5-64842ce10dff
2003
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sohn, K.
15547878-23a1-4428-90b5-64842ce10dff
Kim, H. and Sohn, K.
(2003)
Hierarchical disparity estimation with energy-based regularization.
IEEE International Conference on Image Processing.
.
(doi:10.1109/ICIP.2003.1246976).
Record type:
Conference or Workshop Item
(Paper)
Abstract
We propose a hierarchical disparity estimation algorithm with energy-based regularization. Initial disparity vectors are obtained from downsampled stereo images using a feature-based region-dividing disparity estimation technique. Dense disparities are estimated from these initial vectors with shape-adaptive windows in full resolution images. Finally, the vector fields are regularized with the minimization of the energy functional which considers both fidelity and smoothness of the fields. The first two steps provide highly reliable disparity vectors, so that local minimum problem can be avoided in regularization step. The proposed algorithm generates accurate disparity map which is smooth inside objects while preserving its discontinuities in boundaries. Experimental results are presented to illustrate the capabilities of the proposed disparity estimation technique.
This record has no associated files available for download.
More information
Published date: 2003
Additional Information:
Cited By :19
Export Date: 30 April 2020
CODEN: 85QTA
Venue - Dates:
IEEE International Conference on Image Processing, 2003-08-14
Keywords:
Algorithms, Data reduction, Optical resolving power, Vectors, Disparity estimation, Stereo images, Image processing
Identifiers
Local EPrints ID: 439823
URI: http://eprints.soton.ac.uk/id/eprint/439823
PURE UUID: af71f0d3-d982-43ea-97c6-77c17d1c3f99
Catalogue record
Date deposited: 05 May 2020 16:30
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
H. Kim
Author:
K. Sohn
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics