Robust Airborne Combat Identification using Scale-Invariant Spatial and Spectral Electro-Optic Signatures

Electro-optic (EO) imagery provides a rich source of information for feature-based target combat identification (CID). Yet, variable operating conditions, including sensor range, depression angle, and angle of approach, as well as target illumination and degree of occlusion, have so far prevented the development and effective deployment of a complete solution for real-time airborne CID. While much attention has been devoted to discovering target features which are invariant to orientation and affine view transformation, the resulting features have proven to be insufficiently discriminatory for large model databases. To address these and other challenges, we propose the use of scale- and affine transformation-invariant spatial and intensity features, combined with color/spectral histogram features, for robust, high-performance CID. Furthermore, we show how real-time airborne processing capability can be achieved through efficient candidate target segmentation followed by a hierarchical classification structure. This framework ensures that the most computationally demanding operations are only performed for a small number of most likely candidate target matches. Throughout, we show how storage and bandwidth requirements can be minimized, to enable deployment of the complete CID system on the F/A-18E/F and a variety of other platforms, leading to reduced operator workload and improved combat effectiveness.