FLIR ATR using location uncertainty

A model-based FLIR ATR algorithm is described. It utilizes boundary contras t for target detection and recognition. Boundary contrast is related to the location uncertainty at target boundary points. A polygon model is used fo r deriving target centroid location uncertainty caused by the boundary poin t location uncertainty. The significance of the work lies in the sound math ematical models used in deriving the relationship between contrast and loca tion uncertainty for the boundary points and the relationship between bound ary point location uncertainty and centroid location uncertainty Experiment results show significantly improved performance in detection, recognition, and localization. (C) 2000 SPIE and IS&T. [S1017-9909(00)01602-0].