3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation

Wei Song, Takahiro Natsume, Mamoru Minami

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

Abstract

This paper presents a vision-related technique for 3-D position/ orientation measurement. The proposed method utilizes the genetic algorithm (GA) and unprocessed gray-scale image input from stereo-vision, in order to perform recognition of a target being imaged with known target object shape. In fact here, the problem to recognize the target shape and simultaneous detection of the position/orientation, is converted to an optimistic problem of a model-based evalution function, named as surface-strips model-based fitness function that consists in the computation of the brightness difference between an internal surface and a contour-strips. In order to evaluate the proposed 3-D recognition method, experiments by a robot manipulator equipped with two hand-eye cameras have been conducted to recognize a ball on a turning table. The results show its effectiveness of this method for real-time visual servoing by manipulator.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages277-282
Number of pages6
Publication statusPublished - 2004
Externally publishedYes
EventSICE Annual Conference 2004 - Sapporo, Japan
Duration: Aug 4 2004Aug 6 2004

Other

OtherSICE Annual Conference 2004
CountryJapan
CitySapporo
Period8/4/048/6/04

Fingerprint

Manipulators
Genetic algorithms
Visual servoing
Stereo vision
End effectors
Luminance
Cameras
Robots
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Song, W., Natsume, T., & Minami, M. (2004). 3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation. In Proceedings of the SICE Annual Conference (pp. 277-282). [WAI-13-2]

3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation. / Song, Wei; Natsume, Takahiro; Minami, Mamoru.

Proceedings of the SICE Annual Conference. 2004. p. 277-282 WAI-13-2.

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

Song, W, Natsume, T & Minami, M 2004, 3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation. in Proceedings of the SICE Annual Conference., WAI-13-2, pp. 277-282, SICE Annual Conference 2004, Sapporo, Japan, 8/4/04.
Song W, Natsume T, Minami M. 3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation. In Proceedings of the SICE Annual Conference. 2004. p. 277-282. WAI-13-2
@inproceedings{b6b504ac67164eb085008ccba1a77f3c,
title = "3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation",
abstract = "This paper presents a vision-related technique for 3-D position/ orientation measurement. The proposed method utilizes the genetic algorithm (GA) and unprocessed gray-scale image input from stereo-vision, in order to perform recognition of a target being imaged with known target object shape. In fact here, the problem to recognize the target shape and simultaneous detection of the position/orientation, is converted to an optimistic problem of a model-based evalution function, named as surface-strips model-based fitness function that consists in the computation of the brightness difference between an internal surface and a contour-strips. In order to evaluate the proposed 3-D recognition method, experiments by a robot manipulator equipped with two hand-eye cameras have been conducted to recognize a ball on a turning table. The results show its effectiveness of this method for real-time visual servoing by manipulator.",
author = "Wei Song and Takahiro Natsume and Mamoru Minami",
year = "2004",
language = "English",
pages = "277--282",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - 3-D position/orientation measrurement using model-based matching method and GA - Proposal of calculation method and evaluation

AU - Song, Wei

AU - Natsume, Takahiro

AU - Minami, Mamoru

PY - 2004

Y1 - 2004

N2 - This paper presents a vision-related technique for 3-D position/ orientation measurement. The proposed method utilizes the genetic algorithm (GA) and unprocessed gray-scale image input from stereo-vision, in order to perform recognition of a target being imaged with known target object shape. In fact here, the problem to recognize the target shape and simultaneous detection of the position/orientation, is converted to an optimistic problem of a model-based evalution function, named as surface-strips model-based fitness function that consists in the computation of the brightness difference between an internal surface and a contour-strips. In order to evaluate the proposed 3-D recognition method, experiments by a robot manipulator equipped with two hand-eye cameras have been conducted to recognize a ball on a turning table. The results show its effectiveness of this method for real-time visual servoing by manipulator.

AB - This paper presents a vision-related technique for 3-D position/ orientation measurement. The proposed method utilizes the genetic algorithm (GA) and unprocessed gray-scale image input from stereo-vision, in order to perform recognition of a target being imaged with known target object shape. In fact here, the problem to recognize the target shape and simultaneous detection of the position/orientation, is converted to an optimistic problem of a model-based evalution function, named as surface-strips model-based fitness function that consists in the computation of the brightness difference between an internal surface and a contour-strips. In order to evaluate the proposed 3-D recognition method, experiments by a robot manipulator equipped with two hand-eye cameras have been conducted to recognize a ball on a turning table. The results show its effectiveness of this method for real-time visual servoing by manipulator.

UR - http://www.scopus.com/inward/record.url?scp=12744274831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12744274831&partnerID=8YFLogxK

M3 - Conference contribution

SP - 277

EP - 282

BT - Proceedings of the SICE Annual Conference

ER -