Using global consistency to recognise euclidean objects with an uncalibrated camera

D. A. Forsyth, J. L. Mundy, A. Zisserman, C. A. Rothwell

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

Abstract

A recognition strategy consisting of a mixture of indexing on invariants and search, allows objects to be recognised up to a Euclidean ambiguity with an uncalibrated camera. The approach works by using projective invariants to determine all the possible projectively equivalent models for a particular imaged object; then a system of global consistency constraints is used to determine which of these projectively equivalent, but Euclidean distinct, models corresponds to the objects viewed. These constraints follow from properties of the imaging geometry. In particular, a recognition hypothesis is equivalent to an assertion about, among other things, viewing conditions and geometric relationships between objects, and these assertions must be consistent for hypotheses to be correct. The approach is demonstrated to work on images of real scenes consisting of polygonal objects and polyhedra.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherPubl by IEEE
Pages502-507
Number of pages6
ISBN (Print)0818658274
StatePublished - Jan 1 1994
Externally publishedYes
EventProceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Seattle, WA, USA
Duration: Jun 21 1994Jun 23 1994

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

OtherProceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySeattle, WA, USA
Period6/21/946/23/94

Fingerprint

Cameras
Imaging techniques
Geometry

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Forsyth, D. A., Mundy, J. L., Zisserman, A., & Rothwell, C. A. (1994). Using global consistency to recognise euclidean objects with an uncalibrated camera. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 502-507). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). Publ by IEEE.

Using global consistency to recognise euclidean objects with an uncalibrated camera. / Forsyth, D. A.; Mundy, J. L.; Zisserman, A.; Rothwell, C. A.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Publ by IEEE, 1994. p. 502-507 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

Forsyth, DA, Mundy, JL, Zisserman, A & Rothwell, CA 1994, Using global consistency to recognise euclidean objects with an uncalibrated camera. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Publ by IEEE, pp. 502-507, Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 6/21/94.
Forsyth DA, Mundy JL, Zisserman A, Rothwell CA. Using global consistency to recognise euclidean objects with an uncalibrated camera. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Publ by IEEE. 1994. p. 502-507. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Forsyth, D. A. ; Mundy, J. L. ; Zisserman, A. ; Rothwell, C. A. / Using global consistency to recognise euclidean objects with an uncalibrated camera. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Publ by IEEE, 1994. pp. 502-507 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{5699a72e9e094591946e6c443460468e,
title = "Using global consistency to recognise euclidean objects with an uncalibrated camera",
abstract = "A recognition strategy consisting of a mixture of indexing on invariants and search, allows objects to be recognised up to a Euclidean ambiguity with an uncalibrated camera. The approach works by using projective invariants to determine all the possible projectively equivalent models for a particular imaged object; then a system of global consistency constraints is used to determine which of these projectively equivalent, but Euclidean distinct, models corresponds to the objects viewed. These constraints follow from properties of the imaging geometry. In particular, a recognition hypothesis is equivalent to an assertion about, among other things, viewing conditions and geometric relationships between objects, and these assertions must be consistent for hypotheses to be correct. The approach is demonstrated to work on images of real scenes consisting of polygonal objects and polyhedra.",
author = "Forsyth, {D. A.} and Mundy, {J. L.} and A. Zisserman and Rothwell, {C. A.}",
year = "1994",
month = "1",
day = "1",
language = "English (US)",
isbn = "0818658274",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "Publ by IEEE",
pages = "502--507",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Using global consistency to recognise euclidean objects with an uncalibrated camera

AU - Forsyth, D. A.

AU - Mundy, J. L.

AU - Zisserman, A.

AU - Rothwell, C. A.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - A recognition strategy consisting of a mixture of indexing on invariants and search, allows objects to be recognised up to a Euclidean ambiguity with an uncalibrated camera. The approach works by using projective invariants to determine all the possible projectively equivalent models for a particular imaged object; then a system of global consistency constraints is used to determine which of these projectively equivalent, but Euclidean distinct, models corresponds to the objects viewed. These constraints follow from properties of the imaging geometry. In particular, a recognition hypothesis is equivalent to an assertion about, among other things, viewing conditions and geometric relationships between objects, and these assertions must be consistent for hypotheses to be correct. The approach is demonstrated to work on images of real scenes consisting of polygonal objects and polyhedra.

AB - A recognition strategy consisting of a mixture of indexing on invariants and search, allows objects to be recognised up to a Euclidean ambiguity with an uncalibrated camera. The approach works by using projective invariants to determine all the possible projectively equivalent models for a particular imaged object; then a system of global consistency constraints is used to determine which of these projectively equivalent, but Euclidean distinct, models corresponds to the objects viewed. These constraints follow from properties of the imaging geometry. In particular, a recognition hypothesis is equivalent to an assertion about, among other things, viewing conditions and geometric relationships between objects, and these assertions must be consistent for hypotheses to be correct. The approach is demonstrated to work on images of real scenes consisting of polygonal objects and polyhedra.

UR - http://www.scopus.com/inward/record.url?scp=0028132373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028132373&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028132373

SN - 0818658274

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 502

EP - 507

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

PB - Publ by IEEE

ER -