An accurate and robust stereo matching algorithm with variable windows for 3D measurements

Gyung Bum Kim, Sung Chong Chung

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

This paper describes the application of a stereo algorithm with novel variable windows to the measurement of three-dimensional (3D) shapes. Due to heavy variations of disparities within a rectangular window, previous area-based stereo algorithms have given rise to relatively large matching errors around depth discontinuities. In this paper, a new correlation function based on a robust estimator is formulated to improve matching accuracy in the area with depth discontinuities. Four-direction line mask including a rectangular window is devised not only to reduce noise effects but also to improve matching accuracy. The connectivity of match candidates selected by the correlation function is investigated to include the physical sense that disparities near an interested pixel are constant, and then integer disparities are estimated by finding the disparity plane with maximum connected match candidates. A novel variable window derived from a set of maximum connected candidates with positive intensity-gradient based similarity is used to minimize matching ambiguity of existing area-based methods. In addition, sub-pixel disparity estimation is performed to reduce local deformation effects of the variable windows resulting from projective distortion. Experiments confirm that the proposed method estimates accurate and robust results in the vicinity of depth discontinuities as well as in continuously smooth areas.

Original languageEnglish
Pages (from-to)715-735
Number of pages21
JournalMechatronics
Volume14
Issue number6
DOIs
StatePublished - 2004 Jul 1

Fingerprint

Pixels
Masks
Experiments

Keywords

  • Depth discontinuity
  • Disparity
  • Intensity-gradient based similarity
  • Local deformation
  • Match candidate point
  • Robust estimator
  • Stereo matching
  • Variable window

Cite this

@article{cb87ead7fe1d4e7389151ea50a2812fc,
title = "An accurate and robust stereo matching algorithm with variable windows for 3D measurements",
abstract = "This paper describes the application of a stereo algorithm with novel variable windows to the measurement of three-dimensional (3D) shapes. Due to heavy variations of disparities within a rectangular window, previous area-based stereo algorithms have given rise to relatively large matching errors around depth discontinuities. In this paper, a new correlation function based on a robust estimator is formulated to improve matching accuracy in the area with depth discontinuities. Four-direction line mask including a rectangular window is devised not only to reduce noise effects but also to improve matching accuracy. The connectivity of match candidates selected by the correlation function is investigated to include the physical sense that disparities near an interested pixel are constant, and then integer disparities are estimated by finding the disparity plane with maximum connected match candidates. A novel variable window derived from a set of maximum connected candidates with positive intensity-gradient based similarity is used to minimize matching ambiguity of existing area-based methods. In addition, sub-pixel disparity estimation is performed to reduce local deformation effects of the variable windows resulting from projective distortion. Experiments confirm that the proposed method estimates accurate and robust results in the vicinity of depth discontinuities as well as in continuously smooth areas.",
keywords = "Depth discontinuity, Disparity, Intensity-gradient based similarity, Local deformation, Match candidate point, Robust estimator, Stereo matching, Variable window",
author = "Kim, {Gyung Bum} and Chung, {Sung Chong}",
year = "2004",
month = "7",
day = "1",
doi = "10.1016/j.mechatronics.2004.01.004",
language = "English",
volume = "14",
pages = "715--735",
journal = "Mechatronics",
issn = "0957-4158",
number = "6",

}

An accurate and robust stereo matching algorithm with variable windows for 3D measurements. / Kim, Gyung Bum; Chung, Sung Chong.

In: Mechatronics, Vol. 14, No. 6, 01.07.2004, p. 715-735.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An accurate and robust stereo matching algorithm with variable windows for 3D measurements

AU - Kim, Gyung Bum

AU - Chung, Sung Chong

PY - 2004/7/1

Y1 - 2004/7/1

N2 - This paper describes the application of a stereo algorithm with novel variable windows to the measurement of three-dimensional (3D) shapes. Due to heavy variations of disparities within a rectangular window, previous area-based stereo algorithms have given rise to relatively large matching errors around depth discontinuities. In this paper, a new correlation function based on a robust estimator is formulated to improve matching accuracy in the area with depth discontinuities. Four-direction line mask including a rectangular window is devised not only to reduce noise effects but also to improve matching accuracy. The connectivity of match candidates selected by the correlation function is investigated to include the physical sense that disparities near an interested pixel are constant, and then integer disparities are estimated by finding the disparity plane with maximum connected match candidates. A novel variable window derived from a set of maximum connected candidates with positive intensity-gradient based similarity is used to minimize matching ambiguity of existing area-based methods. In addition, sub-pixel disparity estimation is performed to reduce local deformation effects of the variable windows resulting from projective distortion. Experiments confirm that the proposed method estimates accurate and robust results in the vicinity of depth discontinuities as well as in continuously smooth areas.

AB - This paper describes the application of a stereo algorithm with novel variable windows to the measurement of three-dimensional (3D) shapes. Due to heavy variations of disparities within a rectangular window, previous area-based stereo algorithms have given rise to relatively large matching errors around depth discontinuities. In this paper, a new correlation function based on a robust estimator is formulated to improve matching accuracy in the area with depth discontinuities. Four-direction line mask including a rectangular window is devised not only to reduce noise effects but also to improve matching accuracy. The connectivity of match candidates selected by the correlation function is investigated to include the physical sense that disparities near an interested pixel are constant, and then integer disparities are estimated by finding the disparity plane with maximum connected match candidates. A novel variable window derived from a set of maximum connected candidates with positive intensity-gradient based similarity is used to minimize matching ambiguity of existing area-based methods. In addition, sub-pixel disparity estimation is performed to reduce local deformation effects of the variable windows resulting from projective distortion. Experiments confirm that the proposed method estimates accurate and robust results in the vicinity of depth discontinuities as well as in continuously smooth areas.

KW - Depth discontinuity

KW - Disparity

KW - Intensity-gradient based similarity

KW - Local deformation

KW - Match candidate point

KW - Robust estimator

KW - Stereo matching

KW - Variable window

UR - http://www.scopus.com/inward/record.url?scp=1842611829&partnerID=8YFLogxK

U2 - 10.1016/j.mechatronics.2004.01.004

DO - 10.1016/j.mechatronics.2004.01.004

M3 - Article

AN - SCOPUS:1842611829

VL - 14

SP - 715

EP - 735

JO - Mechatronics

JF - Mechatronics

SN - 0957-4158

IS - 6

ER -