Wide-threat detection: recognition of adversarial missions and activity patterns in Empire Challenge 2009
Georgiy Levchuk, Charlotte Shabarekh, Caitlin Furjanic · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2011
In this paper, we present results of adversarial activity recognition using data collected in the Empire Challenge (EC 09) exercise. The EC09 experiment provided an opportunity to evaluate our probabilistic spatiotemporal mission recognition algorithms using the data from live air-born and ground sensors. Using ambiguous and noisy data about locations of entities and motion events on the ground, the algorithms inferred the types and locations of OPFOR activities, including reconnaissance, cache runs, IED emplacements, logistics, and planning meetings. In this paper, we present detailed summary of the validation study and recognition accuracy results. Our algorithms were able to detect locations and types of over 75% of hostile activities in EC09 while producing 25% false alarms.