In recent years, distributed computer vision has gained a lot of attention within the computer vision community for applications
such as video surveillance and object tracking. The collective information gathered by multiple cameras that are strategically
placed has many advantages. For example, aggregation of information from multiple viewpoints reduces the uncertainty about
the scene. Further, there is no single point of failure, thus the system as a whole could continue to perform the task at
hand. However, the advantages arising out of such cooperation can be realized only by timely sharing of the information between
them. This paper discusses the design of a distributed vision system that enables several heterogeneous sensors with different
processing rates to exchange information in a timely manner in order to achieve a common goal, say tracking of multiple human
subjects and mobile robots in an indoor smart environment.
In our fault-tolerant distributed vision system, a resource manager manages individual cameras and buffers the time-stamped
object candidates received from them. A User Agent with a given task specification approaches the resource manager, first
for knowing the available resources (cameras) and later for receiving the object candidates from the resources of its interest.
Thus the resource manager acts as a proxy between the user agents and cameras, thereby freeing the cameras to do dedicated
feature detection and extraction only. In such a scenario, many failures are possible. For example, one of the cameras may
have a hardware failure or it may lose the target, which moved away from its field of view. In this context, important issues
such as failure detection and handling, synchronization of data from multiple sensors and sensor reconfiguration by view planning
are discussed in the paper. Experimental results with real scene images will be given.
Abstract This work is supported by DARPA/ITO Mobile Autonomous Robots S/W (MARS) (Contract Number DOD DABT63-99-1-004) and Software
for Distributed Robotics (SDR) (Contract Number DOD DABT63-99-1-0022)