liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Preattentive gaze control for robot vision
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
1992 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

A framework for a hierarchical approach to gaze control of a robot vision system is presented, and a implementation on a simulated robot is described. The robot is equipped with a heterogeneous sampled imaging system, a fovea, resembling the varying resolution in a human retina. The relation between the fovea and multiresolution image processing is discussed together with implications for image operations.

A stereo algorithm based on local phase differences is presented both as a stand alone algorithm and as apart of a vergence control system for the robot above. The algorithm is fast and can handle !arge disparities and still give subpixel accuracy. The algorithm uses a wavelet approach beginning at a coarse resolution and refining the disparity estimates while increasing the resolution. The method produces robust and accurate estimates of displacement on synthetic as well as real life stereo images. Disparity filter design is discussed anda number of filters are tested e.g. Gabor filters and lognorm quadrature filters. A special disparity filter designed to have only one phase cycle is also presented.

A theory for sequentially defined, data modified focus of attention, based on nested regions of interest is presented. The theory is applied to   preattentive gaze control system consisting of three control levels: camera vergence, edge tracking and object finding. The object finder uses circular symmetries as indications on possible object and directs the fixation point accordingly. The edge tracker make the fixation point follow the structures in the scene and the camera vergence control assures that both eyes are fixating the same point. The coordination between the levels is handled with potential fields in the robot parameter space.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press , 1992. , 103 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 322
Keyword [en]
Robot vision, Resolution pyramids, Phase-based disparity estimation, Focus of attention
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-54886Local ID: LiU-Tek-Lic-1992:14ISBN: 91-7870-961-X (print)OAI: oai:DiVA.org:liu-54886DiVA: diva2:311047
Presentation
(English)
Available from: 2010-04-19 Created: 2010-04-19 Last updated: 2013-11-21Bibliographically approved

Open Access in DiVA

No full text

By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 208 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf