|
The intended operational environment is over an area with widely
varying geographical terrain containing traffic networks in city,
suburban and rural areas, which may be both densely and sparsely
populated by vehicles ranging from passenger cars to tractor-trailers.
Demonstration video
 |
The UAV is required to "understand" what happens on those roads -
conventional maneuvers of individual cars and other road vehicles,
dangerous or otherwise exceptional maneuvers, structure of the traffic
e.g. congestion. It is also to perform tasks that are assigned by the
operator or triggered by the observations it makes itself, for example
to follow a certain car that flees from the scene of an apparent
crime, or to assist a certain car so that it can make it through
difficult traffic and get to a particular destination as quickly as
possible.
The activities in this operational environment will be those that one
would expect from familiarity with normal road traffic. |
The UAV's "understanding" of the environment is dictated by its sensory
capabilities and by the major tasks that are defined for it. They are:
- to monitor traffic situations,
- to identify and track individual vehicles,
- to identify episodic behavior of both individual and groups of
vehicles,
- to gather data pertaining to road network use and abuse,
- to provide assistance to emergency services, and
- to serve as a mobile sensory platform with real-time information
gathering and processing capabilities.
One important basic processing step is to find moving objects in the
scene. This can be a challenging task due to camera motion etc. The
video clip shows a stabilized road scene to the left. Motion blobs has
been detected via spatio-temporal filtering (right). These motion
blobs contains information of motion velocity and direction, and can
be used as input to a object tracking algorithm.
From the motion information of the individual vehicles, information
about the road network, etc, it is possible to implement the tasks
described above.
|
