High-speed object pose recognition using distinctive 3-D vector pairs

Shuichi Akizuki, Manabu Hashimoto

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We propose a high-speed 3-D object pose recognition method. The method's main feature is that a set of distinctive 3-D vector pairs, each of which consists of three different 3-D points, is used for matching process. A vector pair with a low occurrence probability of a model object means that it is distinctive not only in a model but also in an acquired image. Therefore, such vector pairs are expected to avoid false matching. Experimental results have shown that the proposed method is about 60 times faster and increases the recognition success rate from 62.0% to 94.6% in comparison with the Spin Image method.

Original languageEnglish
Pages (from-to)1853-1854
Number of pages2
JournalIEEJ Transactions on Electronics, Information and Systems
Volume133
Issue number9
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Object recognition

Keywords

  • 3-D object recognition
  • 3-D vector pair
  • Occurrence probability
  • Range image

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

High-speed object pose recognition using distinctive 3-D vector pairs. / Akizuki, Shuichi; Hashimoto, Manabu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 133, No. 9, 2013, p. 1853-1854.

Research output: Contribution to journalArticle

Akizuki, Shuichi ; Hashimoto, Manabu. / High-speed object pose recognition using distinctive 3-D vector pairs. In: IEEJ Transactions on Electronics, Information and Systems. 2013 ; Vol. 133, No. 9. pp. 1853-1854.
@article{bb160528cbe1440a9ee45a614fd5e5b8,
title = "High-speed object pose recognition using distinctive 3-D vector pairs",
abstract = "We propose a high-speed 3-D object pose recognition method. The method's main feature is that a set of distinctive 3-D vector pairs, each of which consists of three different 3-D points, is used for matching process. A vector pair with a low occurrence probability of a model object means that it is distinctive not only in a model but also in an acquired image. Therefore, such vector pairs are expected to avoid false matching. Experimental results have shown that the proposed method is about 60 times faster and increases the recognition success rate from 62.0{\%} to 94.6{\%} in comparison with the Spin Image method.",
keywords = "3-D object recognition, 3-D vector pair, Occurrence probability, Range image",
author = "Shuichi Akizuki and Manabu Hashimoto",
year = "2013",
doi = "10.1541/ieejeiss.133.1853",
language = "English",
volume = "133",
pages = "1853--1854",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "9",

}

TY - JOUR

T1 - High-speed object pose recognition using distinctive 3-D vector pairs

AU - Akizuki, Shuichi

AU - Hashimoto, Manabu

PY - 2013

Y1 - 2013

N2 - We propose a high-speed 3-D object pose recognition method. The method's main feature is that a set of distinctive 3-D vector pairs, each of which consists of three different 3-D points, is used for matching process. A vector pair with a low occurrence probability of a model object means that it is distinctive not only in a model but also in an acquired image. Therefore, such vector pairs are expected to avoid false matching. Experimental results have shown that the proposed method is about 60 times faster and increases the recognition success rate from 62.0% to 94.6% in comparison with the Spin Image method.

AB - We propose a high-speed 3-D object pose recognition method. The method's main feature is that a set of distinctive 3-D vector pairs, each of which consists of three different 3-D points, is used for matching process. A vector pair with a low occurrence probability of a model object means that it is distinctive not only in a model but also in an acquired image. Therefore, such vector pairs are expected to avoid false matching. Experimental results have shown that the proposed method is about 60 times faster and increases the recognition success rate from 62.0% to 94.6% in comparison with the Spin Image method.

KW - 3-D object recognition

KW - 3-D vector pair

KW - Occurrence probability

KW - Range image

UR - http://www.scopus.com/inward/record.url?scp=84884854601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884854601&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.133.1853

DO - 10.1541/ieejeiss.133.1853

M3 - Article

VL - 133

SP - 1853

EP - 1854

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 9

ER -