29 European Conference on Visual Perception
St-Petersburg, Russia
20-25 August 2006


Important Note: The abstracts presented on this website have not yet been updated with author corrections and publisher revisions. See printed abstract book for most recent versions.

ECVP2006 Abstract




Local descriptor groupings in reinforcement learning of sensory-motor attention
      L Paletta    
Institute of Digital Image Processing, Joanneum Research, Wastiangasse 6, A-8010 Graz, Austria
  lucas.paletta@joanneum.at
 
      G Fritz    
Institute of Digital Image Processing, Joanneum Research, Wastiangasse 6, A-8010 Graz, Austria
  gerald.fritz@joanneum.at
 
      C Seifert    
Institute of Digital Image Processing, Joanneum Research, Wastiangasse 6, A-8010 Graz, Austria
  christin.seifert@joanneum.at
 

Previous research on behavioural modelling of saccadic image interpretation (Henderson, 1982 Psychological Science 8 51 - 55) has emphasised the sampling of informative parts under visual attention to guide visual perception. We propose a system of sequential attention for object recognition that (i) groups n-tuples of local gradient based image descriptors (Lowe, 2004 International Journal of Computer Vision 60 91 - 110) being scale, rotation, and to high degree illumination tolerant, defining a vocabulary of prototypical code descriptors, (ii) selects only informative groupings for further processing, (iii) learns a predictive mapping from a current perceptual state in a Markov decision process to a next saccadic action, and (iv) present a model of object recognition being capable of integrating sequential information by minimization of entropy in the Bayesian modelling of object hypotheses. The innovative abstraction level of informative groupings provides perceptual meta-states in sensory-motor attention, enabling the learning of a purposeful grammar integrating atomic feature-saccade mappings into a meaningful recognition behaviour. We demonstrate highly accurate recognition of outdoor facades in a mobile vision application, using the sensory-motor context of trans-saccadic object recognition.

Support:
None.

Presentation Website:
None.

Keywords:
transsaccadic object recognition
reinforcement learning
grouping of local descriptors

Presentation:
Image processing, applications, models
Poster: Monday, 21 August 2006; 15:30-16:30  /  Attended: 15:30-16:30

Copyright ©2001-2006 ConferenceSoft.com - All Rights Reserved