The self-aware matching measure for stereo

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

27 Citations (Scopus)

Abstract

We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.

Original languageEnglish (US)
Title of host publication2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
Pages1841-1848
Number of pages8
DOIs
StatePublished - Dec 1 2009
Event12th International Conference on Computer Vision, ICCV 2009 - Kyoto, Japan
Duration: Sep 29 2009Oct 2 2009

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other12th International Conference on Computer Vision, ICCV 2009
CountryJapan
CityKyoto
Period9/29/0910/2/09

Fingerprint

Pixels
Binoculars
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Mordohai, P. (2009). The self-aware matching measure for stereo. In 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009 (pp. 1841-1848). [5459409] (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2009.5459409
Mordohai, Philippos. / The self-aware matching measure for stereo. 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. pp. 1841-1848 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{dbfd6f69fcb44dd6b63f122689addaad,
title = "The self-aware matching measure for stereo",
abstract = "We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.",
author = "Philippos Mordohai",
year = "2009",
month = "12",
day = "1",
doi = "https://doi.org/10.1109/ICCV.2009.5459409",
language = "English (US)",
isbn = "9781424444205",
series = "Proceedings of the IEEE International Conference on Computer Vision",
pages = "1841--1848",
booktitle = "2009 IEEE 12th International Conference on Computer Vision, ICCV 2009",

}

Mordohai, P 2009, The self-aware matching measure for stereo. in 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009., 5459409, Proceedings of the IEEE International Conference on Computer Vision, pp. 1841-1848, 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, 9/29/09. https://doi.org/10.1109/ICCV.2009.5459409

The self-aware matching measure for stereo. / Mordohai, Philippos.

2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. p. 1841-1848 5459409 (Proceedings of the IEEE International Conference on Computer Vision).

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

TY - GEN

T1 - The self-aware matching measure for stereo

AU - Mordohai, Philippos

PY - 2009/12/1

Y1 - 2009/12/1

N2 - We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.

AB - We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.

UR - http://www.scopus.com/inward/record.url?scp=77953227246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953227246&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/ICCV.2009.5459409

DO - https://doi.org/10.1109/ICCV.2009.5459409

M3 - Conference contribution

SN - 9781424444205

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1841

EP - 1848

BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009

ER -

Mordohai P. The self-aware matching measure for stereo. In 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009. 2009. p. 1841-1848. 5459409. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2009.5459409