Cross Validation and Segment Support for Stereo Belief Propagation

Murray Evans; James Ferryman

doi:10.1109/ICPR.2006.422

Cross Validation and Segment Support for Stereo Belief Propagation

University of Reading

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Abstract

Typically, algorithms for generating stereo disparity maps have been developed to minimise the energy equation of a single image. This paper proposes a method for implementing cross validation in a belief propagation optimisation. When tested using the Middlebury online stereo evaluation, the cross validation improves upon the results of standard belief propagation. Furthermore, it has been shown that regions of homogeneous colour within the images can be used for enforcing the so-called "segment constraint". Developing from this, segment support is introduced to boost belief between pixels of the same image region and improve propagation into textureless regions

Original language	English
Title of host publication	18th International Conference on Pattern Recognition, 2006
Subtitle of host publication	ICPR 2006
Publisher	IEEE
ISBN (Print)	0-7695-2521-0
DOIs	https://doi.org/10.1109/ICPR.2006.422
Publication status	Published - Sept 2006

Access to Document

10.1109/ICPR.2006.422

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D. (PI), Bilzon, J. (CoI), Campbell, N. (CoI), Cazzola, D. (CoI), Colyer, S. (CoI), Fincham Haines, T. (CoI), Hall, P. (CoI), Kim, K. I. (CoI), Lutteroth, C. (CoI), McGuigan, P. (CoI), O'Neill, E. (CoI), Richardt, C. (CoI), Salo, A. (CoI), Seminati, E. (CoI), Tabor, A. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council

Cite this

@inproceedings{253e2fa926004857920a9b03437b8f20,

title = "Cross Validation and Segment Support for Stereo Belief Propagation",

abstract = "Typically, algorithms for generating stereo disparity maps have been developed to minimise the energy equation of a single image. This paper proposes a method for implementing cross validation in a belief propagation optimisation. When tested using the Middlebury online stereo evaluation, the cross validation improves upon the results of standard belief propagation. Furthermore, it has been shown that regions of homogeneous colour within the images can be used for enforcing the so-called {"}segment constraint{"}. Developing from this, segment support is introduced to boost belief between pixels of the same image region and improve propagation into textureless regions",

author = "Murray Evans and James Ferryman",

year = "2006",

month = sep,

doi = "10.1109/ICPR.2006.422",

language = "English",

isbn = "0-7695-2521-0",

booktitle = "18th International Conference on Pattern Recognition, 2006",

publisher = "IEEE",

address = "USA United States",

}

TY - GEN

T1 - Cross Validation and Segment Support for Stereo Belief Propagation

AU - Evans, Murray

AU - Ferryman, James

PY - 2006/9

Y1 - 2006/9

N2 - Typically, algorithms for generating stereo disparity maps have been developed to minimise the energy equation of a single image. This paper proposes a method for implementing cross validation in a belief propagation optimisation. When tested using the Middlebury online stereo evaluation, the cross validation improves upon the results of standard belief propagation. Furthermore, it has been shown that regions of homogeneous colour within the images can be used for enforcing the so-called "segment constraint". Developing from this, segment support is introduced to boost belief between pixels of the same image region and improve propagation into textureless regions

AB - Typically, algorithms for generating stereo disparity maps have been developed to minimise the energy equation of a single image. This paper proposes a method for implementing cross validation in a belief propagation optimisation. When tested using the Middlebury online stereo evaluation, the cross validation improves upon the results of standard belief propagation. Furthermore, it has been shown that regions of homogeneous colour within the images can be used for enforcing the so-called "segment constraint". Developing from this, segment support is introduced to boost belief between pixels of the same image region and improve propagation into textureless regions

U2 - 10.1109/ICPR.2006.422

DO - 10.1109/ICPR.2006.422

M3 - Chapter in a published conference proceeding

SN - 0-7695-2521-0

BT - 18th International Conference on Pattern Recognition, 2006

PB - IEEE

ER -

Cross Validation and Segment Support for Stereo Belief Propagation

Abstract

Access to Document

Fingerprint

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

Cite this