Automatic Detection and Tracking of Suspicious Dismounts

The capability to automatically monitor areas of strategic interest at increased ranges will undoubtedly yield a key advantage on the battlefield by reducing manpower and improving knowledge of enemy target locations. The ability to effectively exploit data from multiple sensor types to find, track, and recognize targets of interest such as dismounts is key to realizing the promise of AFSOC advanced sensors. Yet due to a number of well-known challenges, including the large number of target classes and aspects, long and varying viewing range, obscured targets, cluttered backgrounds, various geographic and weather conditions, sensor noise, and variations caused by translation, rotation, and scaling of the targets, effective algorithms for discriminating enemy and neutral targets have been elusive to date. An integrated solution which addresses the aforementioned problems in a rigorous, methodical way is necessary to achieve the goals of AFSOC advanced sensors. During Phase I of this contract, Toyon Research demonstrated the feasibility of its algorithms for distinguishing armed dismounts from unarmed dismounts by searching for line-shaped objects consistent with the appearance of weapons. For Phase II, Toyon Research Corporation proposes to further develop advanced algorithms and software to automatically detect and classify dismounts, distinguishing gun-carrying dismounts from those which are unarmed. In addition, Toyon proposes to gather test data from airborne platforms on which to demonstrate its algorithms and demonstrate real-time operation. BENEFIT: Toyon''s has successfully tracked multiple, closely spaced targets using multiple sensor types (including EO, I, MWIR, and LWIR), mounted on multiple platforms (hand-held, building pan-tilt-zoom, and UAV). Successful completion of this work will result in a prototype that can discriminate armed dismounts from unarmed dismounts, and run in real time. Such a system will allow the warfighter to prioritize targets and engage targets of increased threat before targets of less threat and also avoid engagement of neutral targets, which increases the safety of the warfighter and overall probability of a successful mission. Commercial applications are expected to include industrial, law-enforcement, and home security.