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, 9780818658273
DOIs
StatePublished - 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

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Using global consistency to recognise euclidean objects with an uncalibrated camera'. Together they form a unique fingerprint.

Cite this