Multi-scale feature selection in stereo

Research output: Chapter in Book/Report/Conference proceedingChapter

5 Citations (Scopus)

Abstract

In binocular stereo matching, points in left and right images are matched according to features that characterize each point and identify pairs of points. When one tries to use multiple features, a difficult problem is which feature, or combination of features, to use. Moreover, features are difficult to cross-normalize and so comparisons must take into account not only their output, but also their distribution (their output for different parameters). We present a new approach that uses geometric constraints on the matching surface to select optimal feature or combination of features from multiscale-edge and intensity features. The approach requires the cyclopean coordinate system to set mutually exclusive matching choices. To obtain the matching surface, we solve a global optimization problem on an energy functional that models occlusions, discontinuities, and inter-epipolar-line interactions.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
Pages132-137
Number of pages6
Volume1
Publication statusPublished - 1999
Externally publishedYes
EventProceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Fort Collins, CO, USA
Duration: 1999 Jun 231999 Jun 25

Other

OtherProceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99)
CityFort Collins, CO, USA
Period99/6/2399/6/25

Fingerprint

Feature extraction
Binoculars
Global optimization

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Ishikawa, H. (1999). Multi-scale feature selection in stereo. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. 132-137). IEEE.

Multi-scale feature selection in stereo. / Ishikawa, Hiroshi.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1 IEEE, 1999. p. 132-137.

Research output: Chapter in Book/Report/Conference proceedingChapter

Ishikawa, H 1999, Multi-scale feature selection in stereo. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 1, IEEE, pp. 132-137, Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99), Fort Collins, CO, USA, 99/6/23.
Ishikawa H. Multi-scale feature selection in stereo. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1. IEEE. 1999. p. 132-137
Ishikawa, Hiroshi. / Multi-scale feature selection in stereo. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1 IEEE, 1999. pp. 132-137
@inbook{29f705e286bf4db2a0f823cf123a2231,
title = "Multi-scale feature selection in stereo",
abstract = "In binocular stereo matching, points in left and right images are matched according to features that characterize each point and identify pairs of points. When one tries to use multiple features, a difficult problem is which feature, or combination of features, to use. Moreover, features are difficult to cross-normalize and so comparisons must take into account not only their output, but also their distribution (their output for different parameters). We present a new approach that uses geometric constraints on the matching surface to select optimal feature or combination of features from multiscale-edge and intensity features. The approach requires the cyclopean coordinate system to set mutually exclusive matching choices. To obtain the matching surface, we solve a global optimization problem on an energy functional that models occlusions, discontinuities, and inter-epipolar-line interactions.",
author = "Hiroshi Ishikawa",
year = "1999",
language = "English",
volume = "1",
pages = "132--137",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE",

}

TY - CHAP

T1 - Multi-scale feature selection in stereo

AU - Ishikawa, Hiroshi

PY - 1999

Y1 - 1999

N2 - In binocular stereo matching, points in left and right images are matched according to features that characterize each point and identify pairs of points. When one tries to use multiple features, a difficult problem is which feature, or combination of features, to use. Moreover, features are difficult to cross-normalize and so comparisons must take into account not only their output, but also their distribution (their output for different parameters). We present a new approach that uses geometric constraints on the matching surface to select optimal feature or combination of features from multiscale-edge and intensity features. The approach requires the cyclopean coordinate system to set mutually exclusive matching choices. To obtain the matching surface, we solve a global optimization problem on an energy functional that models occlusions, discontinuities, and inter-epipolar-line interactions.

AB - In binocular stereo matching, points in left and right images are matched according to features that characterize each point and identify pairs of points. When one tries to use multiple features, a difficult problem is which feature, or combination of features, to use. Moreover, features are difficult to cross-normalize and so comparisons must take into account not only their output, but also their distribution (their output for different parameters). We present a new approach that uses geometric constraints on the matching surface to select optimal feature or combination of features from multiscale-edge and intensity features. The approach requires the cyclopean coordinate system to set mutually exclusive matching choices. To obtain the matching surface, we solve a global optimization problem on an energy functional that models occlusions, discontinuities, and inter-epipolar-line interactions.

UR - http://www.scopus.com/inward/record.url?scp=0032689676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032689676&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032689676

VL - 1

SP - 132

EP - 137

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE

ER -