An Object Pose Estimation System Using A Single Camera

T. Shakunaga

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

9 Citations (Scopus)

Abstract

This paper presents the framework for a CAD-based monocular vision system that estimates an object pose. Estimation of pose from a single view is discussed according to an a priori 3-d object model that includes key primitive elements and the relations among them. Estimation strategy is discussed briefly, and several algorithms used in a pose estimation are presented. The proposed system - implemented in four subsystems for object-image correspondence, feasible pose enumeration, pose selection, and estimation refinement - integrates sensor information and a priori knowledge about the treated objects. Experimental results for synthesized and real images show the effectiveness of this system for pose estimation and 3-d pose tracking.

Original languageEnglish
Title of host publicationIROS 1992 - Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems
Subtitle of host publicationSensor-Based Robotics and Opportunties for its Industrial Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1053-1060
Number of pages8
ISBN (Electronic)0780307372
DOIs
Publication statusPublished - Jan 1 1992
Externally publishedYes
Event1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992 - Raleigh, United States
Duration: Jul 7 1992Jul 10 1992

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992
CountryUnited States
CityRaleigh
Period7/7/927/10/92

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint Dive into the research topics of 'An Object Pose Estimation System Using A Single Camera'. Together they form a unique fingerprint.

Cite this