Invariance--A new framework for vision

David Forsyth, Joseph L. Mundy, Andrew Zisserman, Christopher M. Brown

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

Abstract

It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.

Original languageEnglish (US)
Title of host publicationProc 3 Int Conf Comput Vision
PublisherPubl by IEEE
Pages598-605
Number of pages8
ISBN (Print)0818620579
StatePublished - Dec 1 1990
Externally publishedYes
EventProceedings 3rd International Conference on Computer Vision - Osaka, Jpn
Duration: Dec 4 1990Dec 7 1990

Publication series

NameProc 3 Int Conf Comput Vision

Other

OtherProceedings 3rd International Conference on Computer Vision
CityOsaka, Jpn
Period12/4/9012/7/90

Fingerprint

Invariance
Cameras

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Forsyth, D., Mundy, J. L., Zisserman, A., & Brown, C. M. (1990). Invariance--A new framework for vision. In Proc 3 Int Conf Comput Vision (pp. 598-605). (Proc 3 Int Conf Comput Vision). Publ by IEEE.

Invariance--A new framework for vision. / Forsyth, David; Mundy, Joseph L.; Zisserman, Andrew; Brown, Christopher M.

Proc 3 Int Conf Comput Vision. Publ by IEEE, 1990. p. 598-605 (Proc 3 Int Conf Comput Vision).

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

Forsyth, D, Mundy, JL, Zisserman, A & Brown, CM 1990, Invariance--A new framework for vision. in Proc 3 Int Conf Comput Vision. Proc 3 Int Conf Comput Vision, Publ by IEEE, pp. 598-605, Proceedings 3rd International Conference on Computer Vision, Osaka, Jpn, 12/4/90.
Forsyth D, Mundy JL, Zisserman A, Brown CM. Invariance--A new framework for vision. In Proc 3 Int Conf Comput Vision. Publ by IEEE. 1990. p. 598-605. (Proc 3 Int Conf Comput Vision).
Forsyth, David ; Mundy, Joseph L. ; Zisserman, Andrew ; Brown, Christopher M. / Invariance--A new framework for vision. Proc 3 Int Conf Comput Vision. Publ by IEEE, 1990. pp. 598-605 (Proc 3 Int Conf Comput Vision).
@inproceedings{bc7486585ff0440db6d9923ddff73af9,
title = "Invariance--A new framework for vision",
abstract = "It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.",
author = "David Forsyth and Mundy, {Joseph L.} and Andrew Zisserman and Brown, {Christopher M.}",
year = "1990",
month = "12",
day = "1",
language = "English (US)",
isbn = "0818620579",
series = "Proc 3 Int Conf Comput Vision",
publisher = "Publ by IEEE",
pages = "598--605",
booktitle = "Proc 3 Int Conf Comput Vision",

}

TY - GEN

T1 - Invariance--A new framework for vision

AU - Forsyth, David

AU - Mundy, Joseph L.

AU - Zisserman, Andrew

AU - Brown, Christopher M.

PY - 1990/12/1

Y1 - 1990/12/1

N2 - It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.

AB - It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.

UR - http://www.scopus.com/inward/record.url?scp=0025575572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025575572&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025575572

SN - 0818620579

T3 - Proc 3 Int Conf Comput Vision

SP - 598

EP - 605

BT - Proc 3 Int Conf Comput Vision

PB - Publ by IEEE

ER -