Title: Distributed camera control for opportunistic visual sensing

Abstract: Camera sensor networks using static cameras that cover a
wide-area may have low cost, but such a network may also provide low
resolution imagery, may image uninteresting features or viewpoints,
etc. Consequences of such scenarios are the increased difficulty of
analysis of the collected video data and accumulation of vast
quantities of unimportant imagery. We propose a control mechanisms for
a distributed camera sensor network to obtain opportunistic
high-resolution facial imagery via distributed constrained
optimization of PTZ parameters for each camera in the network. All
cameras use information broadcast by neighboring cameras to optimize
their PTZ parameters. At certain time steps, due to the configuration
of the targets relative to the cameras, and the fact that each camera
may track many targets, the camera network may be able to achieve the
tracking specification with remaining degrees-of-freedom that can be
used to obtain high-res facial images from desirable aspect
angles. The challenge is to define algorithms to automatically find
these time instants, the appropriate imaging camera, and the
appropriate parameter settings for all cameras to capitalize on these
opportunities. The solution proposed herein involves a Bayesian
formulation (for automatic trading off of objective maximization
versus the risk of losing track of any target), design of aligned
local and global objective functions and the inequality constraint
set, and development of algorithms that allow cameras to exchange
information and asymptotically converge on a pair of primal-dual
optimal solutions.