Universität Bielefeld - Sonderforschungsbereich 360
Vision, Action and the Design of Intelligent Systems
Yiannis Aloimonos
Computer Vision Lab, Department of Computer Science
University of Maryland
My work on Active Vision has recently focused on the computational
modelling of navigational tasks, where my investigations were guided
by the idea of approaching vision for behavioral systems in form of
modules that are directly related to perceptual tasks. These studies
led me to branch in various directions and inquire into the problems
that have to be addressed in order to obtain an overall understanding
of perceptual systems. In this talk I present my views about the
architecture of vision systems, about how to tackle the design and
analysis of perceptual systems, and promising future research
directions. The suggested approach for understanding behavioral
vision to realize the relationship of perception and action builds on
two earlier approaches, the Medusa philosophy and the Synthetic
approach. The resulting framework calls for synthesizing an
artificial vision system by studying vision competences of increasing
complexity and at the same time pursuing the integration of the
perceptual components with action and learning modules. I expect
that Computer Vision research in the future will progress in tight
collaboration with many other disciplines that are concerned with
empirical approaches to vision, i.e., the understanding of biological
vision. Throughout the talk I describe biological findings that
motivate computational arguments which I believe will influence
studies of Computer Vision in the near future.
Anke Weinberger, 1997-12-08