CTS Algorithms for Dynamic Battlefield Events

The objective of this program is to develop algorithms to detect, classify and identify dynamic and "surprise" events (i.e., battlefield events that are unscheduled, un-cued, or otherwise unpredicted prior to occurrence, such as missile launches, warhead explosions, artillery fire, etc.) measured from a remote platform to support future theater ISR architectures. The algorithms will be customized to operate on spectral-temporal data of surprise events in the visible, Short Wave InfraRed (SWIR), and Mid Wave InfraRed (MWIR) band anywhere within a large field of view/field of regard (FOV/FOR) at greater than video rates. The primary mission of the algorithms will be to detect, classify and identify battlefield signatures in real time using spectral-temporal discrimination, thereby improving targeting accuracy and increasing weapons effectiveness. The secondary mission will be kill assessment based on statistical unmixing of the target's destruction signature from that of the weapon. The classifiers developed will be based both on the existing library of surprise event data and on data collection opportunities that arise during the course of the contract. The classifiers will exploit target specific spectral-temporal features and be customized to support the unique aspects of spectral/temporal instrumentation.