Advanced HSI Change Detection Algorithms for Exploitation of Space-Based Imagery

This proposed effort will capitalize on recent advancements in hyperspectral imagery- (HSI-) based real-time registration and spectral change detection processing to enhance our capability to detect, identify and track objects from space-based imagery and high-altitude surveillance imagery. Existing approaches based solely on spatial, temporal or spectral information fall short of demanding DoD needs because of several limiting factors. Primary among these is the complexity of the clutter environment viewed by down-looking spaceborne instruments. This is compounded by the limitation on optical instruments for simultaneously obtaining high-resolution temporal, spatial, and spectral information. We propose to incorporate target spectral signature information into multi-look change detection and tracking algorithms to significantly enhance capabilities of multi-spectral and hyperspectral systems to provide high-performance target detection, identification and tracking.