Steps Towards Cognitive Vision

To build an autonomous cognitive agent is a very challenging
goal. Crucial to the ultimate attainment of this aim is an ability to
perceive, understand, formulate hypotheses and act based on the
agent's perceptions. I will discuss work undertaken at Leeds in
pursuit of this goal.  A key focus of our work is to integrate
quantitative and qualitative modes of representation and to learn as
much as possible of any domain specific models required to understand
and operate in a specific situation. As one example of our approach, I
will show how functional object categories can be learned by mining
qualitative spatio-temporal models of behaviour.