University of Surrey

Test tubes in the lab Research in the ATI Dance Research

A generalised exemplar approach to modelling perception action couplings

Ellis, L and Bowden, R (2005) A generalised exemplar approach to modelling perception action couplings In: Tenth IEEE International Conference on Computer Vision Workshops (ICCVW'05), 2005-10-17 - 2005-10-20, Beijing, China.

[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

We present a framework for autonomous behaviour in vision based artificial cognitive systems by imitation through coupled percept-action (stimulus and response) exemplars. Attributed Relational Graphs (ARGs) are used as a symbolic representation of scene information (percepts). A measure of similarity between ARGs is implemented with the use of a graph isomorphism algorithm and is used to hierarchically group the percepts. By hierarchically grouping percept exemplars into progressively more general models coupled to progressively more general Gaussian action models, we attempt to model the percept space and create a direct mapping to associated actions. The system is built on a simulated shape sorter puzzle that represents a robust vision system. Spatio temporal hypothesis exploration is performed ef- ficiently in a Bayesian framework using a particle filter to propagate game play over time.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Computing
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
NameEmailORCID
Ellis, LUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Date : 17 October 2005
Identification Number : 10.1109/ICCV.2005.254
Uncontrolled Keywords : Layout, Shape, Machine vision, Particle filters, Solid modeling, Robustness, Bayesian methods, Biological system modeling, Training data, Data mining
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 26 Oct 2016 13:00
Last Modified : 31 Oct 2017 18:51
URI: http://epubs.surrey.ac.uk/id/eprint/812623

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800