Tracking applications based on distributed and embedded sensor networks are emerging today, both in the field
of surveillance (airports, lab facilities, train stations, museums, public spots) and industrial vision (visual servoing, factory automation).

The SmartSurv system comprises network-enabled Smart Cameras for probabilistic tracking. They are capable of tracking objects
adaptively in real-time and offer a very bandwidth conservative approach, as the whole computation is performed embedded in each Smart Camera. Only the tracking results are transmitted which are on a higher level of abstraction.

Real Time Tracking Unit

The tracking unit is capable of handling multiple hypotheses (multi modal probability density functions) and nonlinear systems. The achieved robustness is further increased by adaptivity mechanisms.

• Multiple persons can be tracked independent of each other.
• A handover unit ensures tracking also when a person leaves one camera's field of view and enters another.
• Statistics are generated by SmartSurv showing, e.g., an estimate of person occupancy throughout the camera network over time.