Combining shape-from-shading and stereo using Gaussian-Markov random fields

Tom Fincham Haines, Richard C Wilson

Research output: Contribution to conferencePaper

5 Citations (Scopus)
57 Downloads (Pure)

Abstract

In this paper we present a method of combining stereo and shape-from-shading information, taking account of the local reliability of each shape estimate. Local estimates of disparity and orientation are modelled using Gaussian distributions. A Gaussian-Markov random field is used to represent the disparity-map, taking into account interactions between disparity measurements and surface orientation, and the MAP estimate found using belief propagation. Local estimates of the precision of disparities and surface normals are found and used to control the process so that the most accurate data source is used in each region. We assess the performance of our approach using both synthetic and real stereo pairs, and compare against ground truth.
Original languageEnglish
Number of pages4
Publication statusPublished - 2008
Event19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL, USA United States
Duration: 8 Dec 200811 Dec 2008

Conference

Conference19th International Conference on Pattern Recognition, ICPR 2008
CountryUSA United States
CityTampa, FL
Period8/12/0811/12/08

Fingerprint

shading
distribution
method

Cite this

Fincham Haines, T., & Wilson, R. C. (2008). Combining shape-from-shading and stereo using Gaussian-Markov random fields. Paper presented at 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA United States.

Combining shape-from-shading and stereo using Gaussian-Markov random fields. / Fincham Haines, Tom; Wilson, Richard C.

2008. Paper presented at 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA United States.

Research output: Contribution to conferencePaper

Fincham Haines, T & Wilson, RC 2008, 'Combining shape-from-shading and stereo using Gaussian-Markov random fields' Paper presented at 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA United States, 8/12/08 - 11/12/08, .
Fincham Haines T, Wilson RC. Combining shape-from-shading and stereo using Gaussian-Markov random fields. 2008. Paper presented at 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA United States.
Fincham Haines, Tom ; Wilson, Richard C. / Combining shape-from-shading and stereo using Gaussian-Markov random fields. Paper presented at 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA United States.4 p.
@conference{f4a6b47c14d2410aa2c6477f57c1b1bf,
title = "Combining shape-from-shading and stereo using Gaussian-Markov random fields",
abstract = "In this paper we present a method of combining stereo and shape-from-shading information, taking account of the local reliability of each shape estimate. Local estimates of disparity and orientation are modelled using Gaussian distributions. A Gaussian-Markov random field is used to represent the disparity-map, taking into account interactions between disparity measurements and surface orientation, and the MAP estimate found using belief propagation. Local estimates of the precision of disparities and surface normals are found and used to control the process so that the most accurate data source is used in each region. We assess the performance of our approach using both synthetic and real stereo pairs, and compare against ground truth.",
author = "{Fincham Haines}, Tom and Wilson, {Richard C}",
year = "2008",
language = "English",
note = "19th International Conference on Pattern Recognition, ICPR 2008 ; Conference date: 08-12-2008 Through 11-12-2008",

}

TY - CONF

T1 - Combining shape-from-shading and stereo using Gaussian-Markov random fields

AU - Fincham Haines, Tom

AU - Wilson, Richard C

PY - 2008

Y1 - 2008

N2 - In this paper we present a method of combining stereo and shape-from-shading information, taking account of the local reliability of each shape estimate. Local estimates of disparity and orientation are modelled using Gaussian distributions. A Gaussian-Markov random field is used to represent the disparity-map, taking into account interactions between disparity measurements and surface orientation, and the MAP estimate found using belief propagation. Local estimates of the precision of disparities and surface normals are found and used to control the process so that the most accurate data source is used in each region. We assess the performance of our approach using both synthetic and real stereo pairs, and compare against ground truth.

AB - In this paper we present a method of combining stereo and shape-from-shading information, taking account of the local reliability of each shape estimate. Local estimates of disparity and orientation are modelled using Gaussian distributions. A Gaussian-Markov random field is used to represent the disparity-map, taking into account interactions between disparity measurements and surface orientation, and the MAP estimate found using belief propagation. Local estimates of the precision of disparities and surface normals are found and used to control the process so that the most accurate data source is used in each region. We assess the performance of our approach using both synthetic and real stereo pairs, and compare against ground truth.

M3 - Paper

ER -