Pose determination of a three-dimensional object using triangle pairs

Seppo Linnainmaa, David Harwood, Larry Davis

Research output: Contribution to journalArticleScientificpeer-review

126 Citations (Scopus)

Abstract

A procedure is presented to estimate the unconstrained three-dimensional 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 position are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image.
Most likely candidates for location are found, and then the remaining rotational parameters are evaluated. Two solutions are generally admitted to the distribution by every match of triangles. The number of possible matches is reduced by checking a simple geometric relation among triples.
Even with partial occlusion, experiments indicate that the procedure is very reliably accurate, although optimization can further improve estimates of the parameters
Original languageEnglish
Pages (from-to)634-647
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume10
Issue number5
DOIs
Publication statusPublished - 1988
MoE publication typeA1 Journal article-refereed

Fingerprint

Triangle
Three-dimensional
Hough transforms
Hough Transform
Occlusion
Estimate
Likely
Partial
Optimization
Experiments
Experiment
Object

Cite this

Linnainmaa, Seppo ; Harwood, David ; Davis, Larry. / Pose determination of a three-dimensional object using triangle pairs. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 1988 ; Vol. 10, No. 5. pp. 634-647.
@article{87d8ff43c06642f2abf597a17b5f5210,
title = "Pose determination of a three-dimensional object using triangle pairs",
abstract = "A procedure is presented to estimate the unconstrained three-dimensional 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 position are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Most likely candidates for location are found, and then the remaining rotational parameters are evaluated. Two solutions are generally admitted to the distribution by every match of triangles. The number of possible matches is reduced by checking a simple geometric relation among triples. Even with partial occlusion, experiments indicate that the procedure is very reliably accurate, although optimization can further improve estimates of the parameters",
author = "Seppo Linnainmaa and David Harwood and Larry Davis",
year = "1988",
doi = "10.1109/34.6772",
language = "English",
volume = "10",
pages = "634--647",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
number = "5",

}

Pose determination of a three-dimensional object using triangle pairs. / Linnainmaa, Seppo; Harwood, David; Davis, Larry.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, No. 5, 1988, p. 634-647.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Pose determination of a three-dimensional object using triangle pairs

AU - Linnainmaa, Seppo

AU - Harwood, David

AU - Davis, Larry

PY - 1988

Y1 - 1988

N2 - A procedure is presented to estimate the unconstrained three-dimensional 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 position are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Most likely candidates for location are found, and then the remaining rotational parameters are evaluated. Two solutions are generally admitted to the distribution by every match of triangles. The number of possible matches is reduced by checking a simple geometric relation among triples. Even with partial occlusion, experiments indicate that the procedure is very reliably accurate, although optimization can further improve estimates of the parameters

AB - A procedure is presented to estimate the unconstrained three-dimensional 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 position are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Most likely candidates for location are found, and then the remaining rotational parameters are evaluated. Two solutions are generally admitted to the distribution by every match of triangles. The number of possible matches is reduced by checking a simple geometric relation among triples. Even with partial occlusion, experiments indicate that the procedure is very reliably accurate, although optimization can further improve estimates of the parameters

U2 - 10.1109/34.6772

DO - 10.1109/34.6772

M3 - Article

VL - 10

SP - 634

EP - 647

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

ER -