The complexity and congestion of current transportation systems often
produce traffic situations that jeopardize the safety of the people in
volved, These situations vary from maintaining a safe distance behind
a leading vehicle to safely allowing a pedestrian to cross a busy stre
et. Environmental sensing plays a critical role in virtually all of th
ese situations, Of the sensors available, vision sensors protide infor
mation that Is richer and more complete than other sensors, making the
m a logical choice for a multisensor transportation system, In this pa
per we propose robust detection and tracking techniques for intelligen
t vehicle-highway applications where computer vision plays a crucial r
ole, In particular, se demonstrate that the Controlled Active Vision f
ramework [15] can be utilized to provide a visual tracking modality to
a traffic advisory system in order to increase the overall safety mar
gin in a variety bf common traffic situations, We have selected two ap
plication examples. vehicle tracking and pedestrian tracking, to demon
strate that the framework fan provide precisely the type of informatio
n required to effectively manage the given traffic situation.