When interpreting a dynamic and uncertain world it is important to hav
e a high-level vision component that can guide the reasoning of the wh
ole vision system. This guidance is provided by an attentional mechani
sm that exploits knowledge of the specific problem being solved. Here
we survey work relevant to the development of such an attentional mech
anism, using surveillance as an application domain to tie together iss
ues of spatial representation, events, behaviour, control and planning
. The paper culminates in a brief description of HIVIS-WATCHER a progr
am that makes use of all these areas.