Obtaining function models using active vision strategies

Lam, C. P., West, G. A. W. and Venkatesh, S. 1999, Obtaining function models using active vision strategies, in Proceedings of the 12th Conference on Vision Interface, Canadian Image Processing and Pattern Recognition Society, London, Ont., pp. 344-351.

Attached Files
Name Description MIMEType Size Downloads

Title Obtaining function models using active vision strategies
Author(s) Lam, C. P.
West, G. A. W.
Venkatesh, S.
Conference name Vision Interface. Conference (12th : 1999 : Trois-Rivieres, Canada)
Conference location Trois-Rivieres, Canada
Conference dates 18-21 May 1999
Title of proceedings Proceedings of the 12th Conference on Vision Interface
Editor(s) [Unknown]
Publication date 1999
Conference series Vision Interface. Conference
Start page 344
End page 351
Total pages 8
Publisher Canadian Image Processing and Pattern Recognition Society
Place of publication London, Ont.
Keyword(s) active vision
functional representation
2D and 3D scene analysis
Summary This paper addresses the problem of determening which 3D shape is present, and more importantly, the dimensions of the shape within a scene. This is performed in an active vision system because it reduces the complexity of the problem through the use of gaze stabilisation, choice of foveation point and selective processing by adaptively processing regions of interest. In our case only a small number of equations and parameters are needed for each shape. For example, a container has width and height. These are incorporated into functional descriptions of the shapes.
ISSN 0843-803X
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Copyright notice ©1999, Canadian Image Processing and Pattern Recognition Society
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044783

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Link to Related Work
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 17 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Tue, 01 May 2012, 10:57:47 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.