Computation of shape through controlled active exploration

Christopher E. Smith, Nikolaos P Papanikolopoulos

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

14 Scopus citations

Abstract

In this paper, we present a technique for the derivation of depth from feature points on a target's surface using the Controlled Active Vision framework. We use a single visual sensor mounted on the end-effector of a robotic manipulator to automatically select feature using adaptive control techniques. Movements of the manipulator produce displacements that are measured using a Sum-of-Squared Difference (SSD) optical flow. The measured displacements are fed into the controller to alter the path of the manipulator and to refine the depth estimate.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Editors Anon
PublisherPubl by IEEE
Pages2516-2522
Number of pages7
Editionpt 3
ISBN (Print)0818653329
StatePublished - Dec 1 1994
EventProceedings of the 1994 IEEE International Conference on Robotics and Automation. Part 3 (of 4) - San Diego, CA, USA
Duration: May 8 1994May 13 1994

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Numberpt 3
ISSN (Print)1050-4729

Other

OtherProceedings of the 1994 IEEE International Conference on Robotics and Automation. Part 3 (of 4)
CitySan Diego, CA, USA
Period5/8/945/13/94

Fingerprint Dive into the research topics of 'Computation of shape through controlled active exploration'. Together they form a unique fingerprint.

Cite this