A low-rank constraint for parallel stereo cameras

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Title of host publicationPattern Recognition
Subtitle of host publication35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings
EditorsJoachim Wickert, Matthias Hein, Bernt Schiele
Place of PublicationBerlin, Heidelberg
Pages31-40
Number of pages10
Edition1.
ISBN (electronic)978-3-642-40602-7
Publication statusPublished - 2013
Event35th German Conference on Pattern Recognition, GCPR 2013 - Saarbrücken, Germany
Duration: 3 Sept 20136 Sept 2013

Publication series

Name Lecture Notes in Computer Science (LNCS)
PublisherSpringer Verlag
Volume8142
ISSN (Print)0302-9743
ISSN (electronic)1611-3349
Name Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)
ISSN (Print)3004-9946
ISSN (electronic)3004-9954

Abstract

Stereo-camera systems enjoy wide popularity since they provide more restrictive constraints for 3d-reconstruction. Given an image sequence taken by parallel stereo cameras, a low-rank constraint is derived on the measurement data. Correspondences between left and right images are not necessary yet reduce the number of optimization parameters. Conversely, traditional algorithms for stereo factorization require all feature points in both images to be matched, otherwise left and right image streams need be factorized independently. The performance of the proposed algorithm will be evaluated on synthetic data as well as two real image applications.

ASJC Scopus subject areas

Cite this

A low-rank constraint for parallel stereo cameras. / Cordes, Christian; Ackermann, Hanno; Rosenhahn, Bodo.
Pattern Recognition: 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings. ed. / Joachim Wickert; Matthias Hein; Bernt Schiele. 1. ed. Berlin, Heidelberg, 2013. p. 31-40 ( Lecture Notes in Computer Science (LNCS); Vol. 8142), ( Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Cordes, C, Ackermann, H & Rosenhahn, B 2013, A low-rank constraint for parallel stereo cameras. in J Wickert, M Hein & B Schiele (eds), Pattern Recognition: 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings. 1. edn, Lecture Notes in Computer Science (LNCS), vol. 8142, Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP), Berlin, Heidelberg, pp. 31-40, 35th German Conference on Pattern Recognition, GCPR 2013, Saarbrücken, Germany, 3 Sept 2013. https://doi.org/10.1007/978-3-642-40602-7_4
Cordes, C., Ackermann, H., & Rosenhahn, B. (2013). A low-rank constraint for parallel stereo cameras. In J. Wickert, M. Hein, & B. Schiele (Eds.), Pattern Recognition: 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings (1. ed., pp. 31-40). ( Lecture Notes in Computer Science (LNCS); Vol. 8142), ( Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)).. https://doi.org/10.1007/978-3-642-40602-7_4
Cordes C, Ackermann H, Rosenhahn B. A low-rank constraint for parallel stereo cameras. In Wickert J, Hein M, Schiele B, editors, Pattern Recognition: 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings. 1. ed. Berlin, Heidelberg. 2013. p. 31-40. ( Lecture Notes in Computer Science (LNCS)). ( Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)). doi: 10.1007/978-3-642-40602-7_4
Cordes, Christian ; Ackermann, Hanno ; Rosenhahn, Bodo. / A low-rank constraint for parallel stereo cameras. Pattern Recognition: 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013, Proceedings. editor / Joachim Wickert ; Matthias Hein ; Bernt Schiele. 1. ed. Berlin, Heidelberg, 2013. pp. 31-40 ( Lecture Notes in Computer Science (LNCS)). ( Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)).
Download
@inproceedings{fea00e9c91484eb9a6cba3f2ca80065b,
title = "A low-rank constraint for parallel stereo cameras",
abstract = "Stereo-camera systems enjoy wide popularity since they provide more restrictive constraints for 3d-reconstruction. Given an image sequence taken by parallel stereo cameras, a low-rank constraint is derived on the measurement data. Correspondences between left and right images are not necessary yet reduce the number of optimization parameters. Conversely, traditional algorithms for stereo factorization require all feature points in both images to be matched, otherwise left and right image streams need be factorized independently. The performance of the proposed algorithm will be evaluated on synthetic data as well as two real image applications.",
author = "Christian Cordes and Hanno Ackermann and Bodo Rosenhahn",
year = "2013",
doi = "10.1007/978-3-642-40602-7_4",
language = "English",
isbn = "978-3-642-40601-0",
series = " Lecture Notes in Computer Science (LNCS)",
publisher = "Springer Verlag",
pages = "31--40",
editor = "Joachim Wickert and Matthias Hein and Bernt Schiele",
booktitle = "Pattern Recognition",
edition = "1.",
note = "35th German Conference on Pattern Recognition, GCPR 2013 ; Conference date: 03-09-2013 Through 06-09-2013",

}

Download

TY - GEN

T1 - A low-rank constraint for parallel stereo cameras

AU - Cordes, Christian

AU - Ackermann, Hanno

AU - Rosenhahn, Bodo

PY - 2013

Y1 - 2013

N2 - Stereo-camera systems enjoy wide popularity since they provide more restrictive constraints for 3d-reconstruction. Given an image sequence taken by parallel stereo cameras, a low-rank constraint is derived on the measurement data. Correspondences between left and right images are not necessary yet reduce the number of optimization parameters. Conversely, traditional algorithms for stereo factorization require all feature points in both images to be matched, otherwise left and right image streams need be factorized independently. The performance of the proposed algorithm will be evaluated on synthetic data as well as two real image applications.

AB - Stereo-camera systems enjoy wide popularity since they provide more restrictive constraints for 3d-reconstruction. Given an image sequence taken by parallel stereo cameras, a low-rank constraint is derived on the measurement data. Correspondences between left and right images are not necessary yet reduce the number of optimization parameters. Conversely, traditional algorithms for stereo factorization require all feature points in both images to be matched, otherwise left and right image streams need be factorized independently. The performance of the proposed algorithm will be evaluated on synthetic data as well as two real image applications.

UR - http://www.scopus.com/inward/record.url?scp=84886427279&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-40602-7_4

DO - 10.1007/978-3-642-40602-7_4

M3 - Conference contribution

AN - SCOPUS:84886427279

SN - 978-3-642-40601-0

T3 - Lecture Notes in Computer Science (LNCS)

SP - 31

EP - 40

BT - Pattern Recognition

A2 - Wickert, Joachim

A2 - Hein, Matthias

A2 - Schiele, Bernt

CY - Berlin, Heidelberg

T2 - 35th German Conference on Pattern Recognition, GCPR 2013

Y2 - 3 September 2013 through 6 September 2013

ER -

By the same author(s)