Adaptive Learning in Particle Systems

Image exploitation algorithms for Intelligence, Surveillance and Reconnaissance (ISR) and weapon systems are extremely sensitive to differences between the operating conditions (OCs) under which they are trained and the extended operating conditions (EOCs) in which the fielded algorithms are tested. As an example, terrain type is an important OC for the problem of tracking hostile vehicles from an airborne camera. A system designed to track cars driving on highways and on major city streets would probably not do well in the EOC of parking lots because of the very different dynamics. In this proposal, we outline a system we call ALPS for Adaptive Learning in Particle Systems. ALPS takes as input a sequence of video images and any available situational awareness data, such as geo-location, time of day, roadmaps, and terrain feature labels ("urban", "forest", etc.). The system then detects moving targets and tracks those targets across multiple frames using a multiple hypothesis tracker tightly coupled with a particle filter. In Phase I, we will develop a fully functional ALPS prototype capable of real-time performance. The Phase I evaluation will quantify improvement in performance of the adaptive approach across different operating scenarios, vehicle types, and motion patterns.