Direct interpretation of dynamic images and camera motion for vision guided robotics

Koichiro Deguchi

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

The relation between dynamic images and camera motion for vision guided robots was analyzed by studying the properties of the surface of a specific object and use its differential or tangential property for visual servoing. The study used the principal component analysis and the Karhunen-Loeve (KL) expansion to represent the images with a composition of small number of eigenimages. It was found that a normal vector of the surface is related to the Interaction Matrix, and the feasibility of the basic idea for visual servoing was confirmed with a preliminary experiment. A dynamic estimation of the normal vectors to move robot arm mounting a camera to a goal position is also presented.

Original languageEnglish
Pages313-320
Number of pages8
Publication statusPublished - 1996 Dec 1
EventProceedings of the 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems - Washington, DC, USA
Duration: 1996 Dec 81996 Dec 11

Other

OtherProceedings of the 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems
CityWashington, DC, USA
Period96/12/896/12/11

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Direct interpretation of dynamic images and camera motion for vision guided robotics'. Together they form a unique fingerprint.

  • Cite this

    Deguchi, K. (1996). Direct interpretation of dynamic images and camera motion for vision guided robotics. 313-320. Paper presented at Proceedings of the 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems, Washington, DC, USA, .