Hyperspectral Identification for Collaborative Tracking

We will develop a system called HyperTrack that will significantly advance the capability of target tracking systems. HyperTrack will include new algorithms for acquiring target models and new methods for using these models for tracking. The Phase I effort will focus on the use of target spectral and geometric characteristics. Physical models will be used to allow a target spectral model to adapt to changing environmental conditions while at the same time adapting to maximize contrast with the background. We will also develop a module for the acquisition of target geometric models that will allow tracking in the presence of partial obscuration and changes in target pose and sensor viewpoint. A general Bayesian technique will be developed to combine information that is acquired from different sensors on different platforms. We will characterize the algorithms during Phase I using a range of airborne imagery that includes vehicle and dismount targets. The algorithms will be structured to allow near real-time operation on modest hardware. We provide a detailed commercialization plan for the new software.