Triangle-based pose determination of 3-D objects

Seppo Linnainmaa; David Harwood; Larry Davis

Triangle-based pose determination of 3-D objects

Seppo Linnainmaa
, David Harwood
, Larry Davis

VTT Technical Research Centre of Finland

VTT (former employee or external)

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

Abstract

A procedure is presented to estimate the unconstrained three-dimensional (3-D) location and orientation of an object with a known shape when it is visible in a single image. Using a generalized Hough transform, all six parameters of the object pose are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Even with partial occlusion, experiments indicate that the procedure is very accurate.

Original language	English
Title of host publication	8th International Conference on Pattern Recognition (8ICPR)
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	116-118
ISBN (Print)	978-0-8186-0742-4
Publication status	Published - 1986
MoE publication type	A4 Article in a conference publication
Event	8th International Conference on Pattern Recognition (8ICPR) - Paris, France Duration: 27 Oct 1986 → 31 Oct 1986

Conference

Conference	8th International Conference on Pattern Recognition (8ICPR)
Country/Territory	France
City	Paris
Period	27/10/86 → 31/10/86

Cite this

@inproceedings{947e128690d341a08f0e8cb6df3d768b,

title = "Triangle-based pose determination of 3-D objects",

abstract = "A procedure is presented to estimate the unconstrained three-dimensional (3-D) location and orientation of an object with a known shape when it is visible in a single image. Using a generalized Hough transform, all six parameters of the object pose are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Even with partial occlusion, experiments indicate that the procedure is very accurate.",

author = "Seppo Linnainmaa and David Harwood and Larry Davis",

year = "1986",

language = "English",

isbn = "978-0-8186-0742-4",

pages = "116--118",

booktitle = "8th International Conference on Pattern Recognition (8ICPR)",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

note = "8th International Conference on Pattern Recognition (8ICPR) ; Conference date: 27-10-1986 Through 31-10-1986",

}

TY - GEN

T1 - Triangle-based pose determination of 3-D objects

AU - Linnainmaa, Seppo

AU - Harwood, David

AU - Davis, Larry

PY - 1986

Y1 - 1986

N2 - A procedure is presented to estimate the unconstrained three-dimensional (3-D) location and orientation of an object with a known shape when it is visible in a single image. Using a generalized Hough transform, all six parameters of the object pose are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Even with partial occlusion, experiments indicate that the procedure is very accurate.

AB - A procedure is presented to estimate the unconstrained three-dimensional (3-D) location and orientation of an object with a known shape when it is visible in a single image. Using a generalized Hough transform, all six parameters of the object pose are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Even with partial occlusion, experiments indicate that the procedure is very accurate.

M3 - Conference article in proceedings

SN - 978-0-8186-0742-4

SP - 116

EP - 118

BT - 8th International Conference on Pattern Recognition (8ICPR)

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 8th International Conference on Pattern Recognition (8ICPR)

Y2 - 27 October 1986 through 31 October 1986

ER -

Triangle-based pose determination of 3-D objects

Abstract

Conference

Fingerprint

Cite this