Disparity search range estimation based on dense stereo matching

Rueihung Li, Bumsub Ham, Changjae Oh, Kwanghoon Sohn

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

7 Citations (Scopus)

Abstract

This paper presents a scheme for estimating disparity search range based on hierarchical stereo matching. It is important to specify a proper range of search space, since it prevents the solution from being trapped in local minima, and saves a lot of time for estimating disparity maps. Conventionally, it has been estimated by finding a sparse set of the correspondences via feature matching techniques. Instead, we address this problem by considering how the dense correspondences, the ultimate goal of estimating search range, can be estimated without search range. First, we estimate the dense correspondences by adapting a simple local stereo matching technique with an arbitrary search range. The hierarchical scheme is leveraged for reducing computational costs and memory usages. Then, reliable checking techniques are performed for eliminating unreliable correspondences. Finally, the range of search space is estimated by observing the distribution of the reliable correspondences. For the quantitative evaluation, a new error metric, biased root mean squared error (B-RMSE), is proposed, which differentiates the estimated search range whether it is narrower or wider than true disparity range. The experimental results show that the proposed method gives more accurate search range compared to the conventional method.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013
Pages753-759
Number of pages7
DOIs
Publication statusPublished - 2013 Aug 19
Event2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 - Melbourne, VIC, Australia
Duration: 2013 Jun 192013 Jun 21

Other

Other2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013
CountryAustralia
CityMelbourne, VIC
Period13/6/1913/6/21

Fingerprint

Data storage equipment
Costs

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Li, R., Ham, B., Oh, C., & Sohn, K. (2013). Disparity search range estimation based on dense stereo matching. In Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 (pp. 753-759). [6566468] https://doi.org/10.1109/ICIEA.2013.6566468
Li, Rueihung ; Ham, Bumsub ; Oh, Changjae ; Sohn, Kwanghoon. / Disparity search range estimation based on dense stereo matching. Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013. 2013. pp. 753-759
@inproceedings{7ad6dbf721a2448faa304566d2f2bba2,
title = "Disparity search range estimation based on dense stereo matching",
abstract = "This paper presents a scheme for estimating disparity search range based on hierarchical stereo matching. It is important to specify a proper range of search space, since it prevents the solution from being trapped in local minima, and saves a lot of time for estimating disparity maps. Conventionally, it has been estimated by finding a sparse set of the correspondences via feature matching techniques. Instead, we address this problem by considering how the dense correspondences, the ultimate goal of estimating search range, can be estimated without search range. First, we estimate the dense correspondences by adapting a simple local stereo matching technique with an arbitrary search range. The hierarchical scheme is leveraged for reducing computational costs and memory usages. Then, reliable checking techniques are performed for eliminating unreliable correspondences. Finally, the range of search space is estimated by observing the distribution of the reliable correspondences. For the quantitative evaluation, a new error metric, biased root mean squared error (B-RMSE), is proposed, which differentiates the estimated search range whether it is narrower or wider than true disparity range. The experimental results show that the proposed method gives more accurate search range compared to the conventional method.",
author = "Rueihung Li and Bumsub Ham and Changjae Oh and Kwanghoon Sohn",
year = "2013",
month = "8",
day = "19",
doi = "10.1109/ICIEA.2013.6566468",
language = "English",
isbn = "9781467363211",
pages = "753--759",
booktitle = "Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013",

}

Li, R, Ham, B, Oh, C & Sohn, K 2013, Disparity search range estimation based on dense stereo matching. in Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013., 6566468, pp. 753-759, 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013, Melbourne, VIC, Australia, 13/6/19. https://doi.org/10.1109/ICIEA.2013.6566468

Disparity search range estimation based on dense stereo matching. / Li, Rueihung; Ham, Bumsub; Oh, Changjae; Sohn, Kwanghoon.

Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013. 2013. p. 753-759 6566468.

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

TY - GEN

T1 - Disparity search range estimation based on dense stereo matching

AU - Li, Rueihung

AU - Ham, Bumsub

AU - Oh, Changjae

AU - Sohn, Kwanghoon

PY - 2013/8/19

Y1 - 2013/8/19

N2 - This paper presents a scheme for estimating disparity search range based on hierarchical stereo matching. It is important to specify a proper range of search space, since it prevents the solution from being trapped in local minima, and saves a lot of time for estimating disparity maps. Conventionally, it has been estimated by finding a sparse set of the correspondences via feature matching techniques. Instead, we address this problem by considering how the dense correspondences, the ultimate goal of estimating search range, can be estimated without search range. First, we estimate the dense correspondences by adapting a simple local stereo matching technique with an arbitrary search range. The hierarchical scheme is leveraged for reducing computational costs and memory usages. Then, reliable checking techniques are performed for eliminating unreliable correspondences. Finally, the range of search space is estimated by observing the distribution of the reliable correspondences. For the quantitative evaluation, a new error metric, biased root mean squared error (B-RMSE), is proposed, which differentiates the estimated search range whether it is narrower or wider than true disparity range. The experimental results show that the proposed method gives more accurate search range compared to the conventional method.

AB - This paper presents a scheme for estimating disparity search range based on hierarchical stereo matching. It is important to specify a proper range of search space, since it prevents the solution from being trapped in local minima, and saves a lot of time for estimating disparity maps. Conventionally, it has been estimated by finding a sparse set of the correspondences via feature matching techniques. Instead, we address this problem by considering how the dense correspondences, the ultimate goal of estimating search range, can be estimated without search range. First, we estimate the dense correspondences by adapting a simple local stereo matching technique with an arbitrary search range. The hierarchical scheme is leveraged for reducing computational costs and memory usages. Then, reliable checking techniques are performed for eliminating unreliable correspondences. Finally, the range of search space is estimated by observing the distribution of the reliable correspondences. For the quantitative evaluation, a new error metric, biased root mean squared error (B-RMSE), is proposed, which differentiates the estimated search range whether it is narrower or wider than true disparity range. The experimental results show that the proposed method gives more accurate search range compared to the conventional method.

UR - http://www.scopus.com/inward/record.url?scp=84881442491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881442491&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2013.6566468

DO - 10.1109/ICIEA.2013.6566468

M3 - Conference contribution

SN - 9781467363211

SP - 753

EP - 759

BT - Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013

ER -

Li R, Ham B, Oh C, Sohn K. Disparity search range estimation based on dense stereo matching. In Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013. 2013. p. 753-759. 6566468 https://doi.org/10.1109/ICIEA.2013.6566468