A local iterative refinement method for adaptive support-weight stereo matching

Eric T. Psota, Jȩdrzej Kowalczuk, Jay Carlson, Lance C Perez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

A new stereo matching algorithm is introduced that performs iterative refinement on the results of adaptive support-weight stereo matching. During each iteration of disparity refinement, adaptive support-weights are used by the algorithm to penalize disparity differences within local windows. Analytical results show that the addition of iterative refinement to adaptive support-weight stereo matching does not significantly increase complexity. In addition, this new algorithm does not rely on image segmentation or plane fitting, which are used by the majority of the most accurate stereo matching algorithms. As a result, this algorithm has lower complexity, is more suitable for parallel implementation, and does not force locally planar surfaces within the scene. When compared to other algorithms that do not rely on image segmentation or plane fitting, results show that the new stereo matching algorithm is one of the most accurate listed on the Middlebury performance benchmark.

Original languageEnglish (US)
Title of host publicationProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Pages271-277
Number of pages7
StatePublished - Dec 1 2011
Event2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 - Las Vegas, NV, United States
Duration: Jul 18 2011Jul 21 2011

Publication series

NameProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Volume1

Other

Other2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
CountryUnited States
CityLas Vegas, NV
Period7/18/117/21/11

Fingerprint

Image segmentation

Keywords

  • Adaptive support weights
  • Iterative stereo
  • Stereo correspondence
  • Stereo matching

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Psota, E. T., Kowalczuk, J., Carlson, J., & Perez, L. C. (2011). A local iterative refinement method for adaptive support-weight stereo matching. In Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 (pp. 271-277). (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011; Vol. 1).

A local iterative refinement method for adaptive support-weight stereo matching. / Psota, Eric T.; Kowalczuk, Jȩdrzej; Carlson, Jay; Perez, Lance C.

Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. p. 271-277 (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Psota, ET, Kowalczuk, J, Carlson, J & Perez, LC 2011, A local iterative refinement method for adaptive support-weight stereo matching. in Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011, vol. 1, pp. 271-277, 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011, Las Vegas, NV, United States, 7/18/11.
Psota ET, Kowalczuk J, Carlson J, Perez LC. A local iterative refinement method for adaptive support-weight stereo matching. In Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. p. 271-277. (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011).
Psota, Eric T. ; Kowalczuk, Jȩdrzej ; Carlson, Jay ; Perez, Lance C. / A local iterative refinement method for adaptive support-weight stereo matching. Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. pp. 271-277 (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011).
@inproceedings{8c517e995b8f43c58a65111e97d20606,
title = "A local iterative refinement method for adaptive support-weight stereo matching",
abstract = "A new stereo matching algorithm is introduced that performs iterative refinement on the results of adaptive support-weight stereo matching. During each iteration of disparity refinement, adaptive support-weights are used by the algorithm to penalize disparity differences within local windows. Analytical results show that the addition of iterative refinement to adaptive support-weight stereo matching does not significantly increase complexity. In addition, this new algorithm does not rely on image segmentation or plane fitting, which are used by the majority of the most accurate stereo matching algorithms. As a result, this algorithm has lower complexity, is more suitable for parallel implementation, and does not force locally planar surfaces within the scene. When compared to other algorithms that do not rely on image segmentation or plane fitting, results show that the new stereo matching algorithm is one of the most accurate listed on the Middlebury performance benchmark.",
keywords = "Adaptive support weights, Iterative stereo, Stereo correspondence, Stereo matching",
author = "Psota, {Eric T.} and Jȩdrzej Kowalczuk and Jay Carlson and Perez, {Lance C}",
year = "2011",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781601321916",
series = "Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011",
pages = "271--277",
booktitle = "Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011",

}

TY - GEN

T1 - A local iterative refinement method for adaptive support-weight stereo matching

AU - Psota, Eric T.

AU - Kowalczuk, Jȩdrzej

AU - Carlson, Jay

AU - Perez, Lance C

PY - 2011/12/1

Y1 - 2011/12/1

N2 - A new stereo matching algorithm is introduced that performs iterative refinement on the results of adaptive support-weight stereo matching. During each iteration of disparity refinement, adaptive support-weights are used by the algorithm to penalize disparity differences within local windows. Analytical results show that the addition of iterative refinement to adaptive support-weight stereo matching does not significantly increase complexity. In addition, this new algorithm does not rely on image segmentation or plane fitting, which are used by the majority of the most accurate stereo matching algorithms. As a result, this algorithm has lower complexity, is more suitable for parallel implementation, and does not force locally planar surfaces within the scene. When compared to other algorithms that do not rely on image segmentation or plane fitting, results show that the new stereo matching algorithm is one of the most accurate listed on the Middlebury performance benchmark.

AB - A new stereo matching algorithm is introduced that performs iterative refinement on the results of adaptive support-weight stereo matching. During each iteration of disparity refinement, adaptive support-weights are used by the algorithm to penalize disparity differences within local windows. Analytical results show that the addition of iterative refinement to adaptive support-weight stereo matching does not significantly increase complexity. In addition, this new algorithm does not rely on image segmentation or plane fitting, which are used by the majority of the most accurate stereo matching algorithms. As a result, this algorithm has lower complexity, is more suitable for parallel implementation, and does not force locally planar surfaces within the scene. When compared to other algorithms that do not rely on image segmentation or plane fitting, results show that the new stereo matching algorithm is one of the most accurate listed on the Middlebury performance benchmark.

KW - Adaptive support weights

KW - Iterative stereo

KW - Stereo correspondence

KW - Stereo matching

UR - http://www.scopus.com/inward/record.url?scp=84864924184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864924184&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781601321916

T3 - Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011

SP - 271

EP - 277

BT - Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011

ER -