ICVS2007 // Vision Systems in the Real World: Adaptation, Learning, Evaluation // 21.03.-24.03.2007 // hosted by Bielefeld University, Germany
Call for papers PDF
Conference Brochure PDF
Conference Brochure PDF
 
AIPR
GI - Computer Vision Section
Bielefeld University
INRIA SOPHIA ANTIPOLIS
Sponsors
Conference Sponsor: SFB 673 - Alignment in Communication
Workshop Sponsor: Multimedia Understanding through Semantics, Computation and Learning (MUSCLE)


Invited Talk: Prof. Dr. John Tsotsos, York University, Canada

Title of the Talk

Active Robotic Vision Systems that Search

Abstract

John K. Tsotsos and Ksenia Shubina

Visual attention is a multi-faceted phenomenon, playing different roels in different situations and for different processing mechanisms. Regardless, attention is a mechanism that optimizes the search processes inherent in vision. This perspective leads to sound theoretical foundation for studies of attention in both machine and in the brain. The development of this foundation and the many ways in which attentional processes manifest themselves will be overviewed. One particular example of a practical robotic vision system that employs some of these attentional processes will be described. A difficult problem for robotic vision systems is visual search for a given target in an arbitrary 3D space. A solution to this problem will be described that optimizes the probability of finding the target given a fixed cost limit in terms of total number of robotic actions the robot requires to find its visual target. A robotic realization will be shown.

About the speaker

John Tsotsos holds the position of a Professor in the Department of Computer Science and Engineering at York University, Canada, and as an Adjunct Professor in Ophthalmology at the University of Toronto. Until November 2006, he was director of York's Centre for Vision Research. Please have a look at  his website for further information.

ICVS2007 // Vision Systems in the Real World: Adaptation, Learning, Evaluation // 21.03.-24.03.2007 // hosted by Bielefeld University, Germany LOGIN IMPRINT