Group Algorithms for Surveillance and Precision Tracking (GrASP)

A surveillance system needs to accurately locate and identify not only single targets, but also groups of targets engaged in a common activity. Existing tracking systems are capable of tracking individual targets quite accurately; however, they fail to useinformation related to group behavior in order to improve these estimates. As part of our Phase I work, ORINCON developedAlgorithms those are able to exploit group motion information in order to improve the estimate of the individual targets that are contained within the group. During Phase II, we propose to extend our group tracking capabilities to handle scenarios that arerepresentative of wide-area surveillance. Key to these scenarios is the large number of targets (100-1000) and the relatively slow revisit rates (45-60 seconds). These characteristics are in contrast to precision engagement scenarios that consider tens oftargets with revisit rates of 1-5 seconds. Also, as part of our proposed Phase II work, we will develop a robust tracking system simultaneously in surveillance and precision mode. Furthermore, we propose to integrate this tracking system into an automaticcontext alert system to provide input to military operators of groups and individual targets that are of high priority to the warfighter. We propose to demonstrate this notional system concept using government-provided data from data collections oroperational scenarios.c