3D object recognition in cluttered environments by segment-based stereo vision

Yasushi Sumi, Yoshihiro Kawai, Takashi Yoshimi, Fumiaki Tomita

Research output: Contribution to journalArticle

63 Citations (Scopus)

Abstract

We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.

Original languageEnglish
Pages (from-to)5-23
Number of pages19
JournalInternational Journal of Computer Vision
Volume46
Issue number1
DOIs
Publication statusPublished - 2002 Jan
Externally publishedYes

Fingerprint

Stereo vision
Object recognition
Computer aided design
Robots
Sensors

Keywords

  • 3D object modeling
  • 3D object recognition
  • 3D shape matching
  • Free-form objects
  • Robot vision
  • Segment-based stereo vision

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering

Cite this

3D object recognition in cluttered environments by segment-based stereo vision. / Sumi, Yasushi; Kawai, Yoshihiro; Yoshimi, Takashi; Tomita, Fumiaki.

In: International Journal of Computer Vision, Vol. 46, No. 1, 01.2002, p. 5-23.

Research output: Contribution to journalArticle

Sumi, Yasushi ; Kawai, Yoshihiro ; Yoshimi, Takashi ; Tomita, Fumiaki. / 3D object recognition in cluttered environments by segment-based stereo vision. In: International Journal of Computer Vision. 2002 ; Vol. 46, No. 1. pp. 5-23.
@article{9263e7fdac374db3b7c27261c2501b66,
title = "3D object recognition in cluttered environments by segment-based stereo vision",
abstract = "We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.",
keywords = "3D object modeling, 3D object recognition, 3D shape matching, Free-form objects, Robot vision, Segment-based stereo vision",
author = "Yasushi Sumi and Yoshihiro Kawai and Takashi Yoshimi and Fumiaki Tomita",
year = "2002",
month = "1",
doi = "10.1023/A:1013240031067",
language = "English",
volume = "46",
pages = "5--23",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - 3D object recognition in cluttered environments by segment-based stereo vision

AU - Sumi, Yasushi

AU - Kawai, Yoshihiro

AU - Yoshimi, Takashi

AU - Tomita, Fumiaki

PY - 2002/1

Y1 - 2002/1

N2 - We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.

AB - We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.

KW - 3D object modeling

KW - 3D object recognition

KW - 3D shape matching

KW - Free-form objects

KW - Robot vision

KW - Segment-based stereo vision

UR - http://www.scopus.com/inward/record.url?scp=0036163184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036163184&partnerID=8YFLogxK

U2 - 10.1023/A:1013240031067

DO - 10.1023/A:1013240031067

M3 - Article

AN - SCOPUS:0036163184

VL - 46

SP - 5

EP - 23

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -