Integrating Stereo with Shape-from-Shading derived Orientation Information

Tom Fincham Haines, Richard C Wilson

Research output: Contribution to conferencePaper

  • 8 Citations

Abstract

Binocular stereo has been extensively studied for extracting the shape of a scene. The challenge is in matching features between two images of a scene; this is the correspondence problem. Shape from shading (SfS) is another method of extracting shape. This models the interaction of light with the scene surface(s) for a single image. These two methods are very different; stereo uses surface features to deliver a depth-map, SfS uses shading, albedo and lighting information to infer the differential of the depth-map. In this paper we develop a framework for the integration of both depth and orientation information. Dedicated algorithms are used for initial estimates. A Gaussian-Markov random field then represents the depth-map, Gaussian belief propagation is used to approximate the MAP estimate of the depth-map. Integrating information from both stereo correspondences and surface normals allows fine surface details to be estimated.
LanguageEnglish
Pages1-10
Number of pages10
StatusPublished - 2007
EventBritish Machine Vision Conference (BMVC) -
Duration: 1 Jan 2007 → …

Conference

ConferenceBritish Machine Vision Conference (BMVC)
Period1/01/07 → …

Fingerprint

Binoculars
Lighting

Cite this

Fincham Haines, T., & Wilson, R. C. (2007). Integrating Stereo with Shape-from-Shading derived Orientation Information. 1-10. Paper presented at British Machine Vision Conference (BMVC), .

Integrating Stereo with Shape-from-Shading derived Orientation Information. / Fincham Haines, Tom; Wilson, Richard C.

2007. 1-10 Paper presented at British Machine Vision Conference (BMVC), .

Research output: Contribution to conferencePaper

Fincham Haines, T & Wilson, RC 2007, 'Integrating Stereo with Shape-from-Shading derived Orientation Information' Paper presented at British Machine Vision Conference (BMVC), 1/01/07, pp. 1-10.
Fincham Haines T, Wilson RC. Integrating Stereo with Shape-from-Shading derived Orientation Information. 2007. Paper presented at British Machine Vision Conference (BMVC), .
Fincham Haines, Tom ; Wilson, Richard C. / Integrating Stereo with Shape-from-Shading derived Orientation Information. Paper presented at British Machine Vision Conference (BMVC), .10 p.
@conference{d6cdc5237968415da6dfdc4fdcd68e52,
title = "Integrating Stereo with Shape-from-Shading derived Orientation Information",
abstract = "Binocular stereo has been extensively studied for extracting the shape of a scene. The challenge is in matching features between two images of a scene; this is the correspondence problem. Shape from shading (SfS) is another method of extracting shape. This models the interaction of light with the scene surface(s) for a single image. These two methods are very different; stereo uses surface features to deliver a depth-map, SfS uses shading, albedo and lighting information to infer the differential of the depth-map. In this paper we develop a framework for the integration of both depth and orientation information. Dedicated algorithms are used for initial estimates. A Gaussian-Markov random field then represents the depth-map, Gaussian belief propagation is used to approximate the MAP estimate of the depth-map. Integrating information from both stereo correspondences and surface normals allows fine surface details to be estimated.",
author = "{Fincham Haines}, Tom and Wilson, {Richard C}",
year = "2007",
language = "English",
pages = "1--10",
note = "British Machine Vision Conference (BMVC) ; Conference date: 01-01-2007",

}

TY - CONF

T1 - Integrating Stereo with Shape-from-Shading derived Orientation Information

AU - Fincham Haines,Tom

AU - Wilson,Richard C

PY - 2007

Y1 - 2007

N2 - Binocular stereo has been extensively studied for extracting the shape of a scene. The challenge is in matching features between two images of a scene; this is the correspondence problem. Shape from shading (SfS) is another method of extracting shape. This models the interaction of light with the scene surface(s) for a single image. These two methods are very different; stereo uses surface features to deliver a depth-map, SfS uses shading, albedo and lighting information to infer the differential of the depth-map. In this paper we develop a framework for the integration of both depth and orientation information. Dedicated algorithms are used for initial estimates. A Gaussian-Markov random field then represents the depth-map, Gaussian belief propagation is used to approximate the MAP estimate of the depth-map. Integrating information from both stereo correspondences and surface normals allows fine surface details to be estimated.

AB - Binocular stereo has been extensively studied for extracting the shape of a scene. The challenge is in matching features between two images of a scene; this is the correspondence problem. Shape from shading (SfS) is another method of extracting shape. This models the interaction of light with the scene surface(s) for a single image. These two methods are very different; stereo uses surface features to deliver a depth-map, SfS uses shading, albedo and lighting information to infer the differential of the depth-map. In this paper we develop a framework for the integration of both depth and orientation information. Dedicated algorithms are used for initial estimates. A Gaussian-Markov random field then represents the depth-map, Gaussian belief propagation is used to approximate the MAP estimate of the depth-map. Integrating information from both stereo correspondences and surface normals allows fine surface details to be estimated.

M3 - Paper

SP - 1

EP - 10

ER -