Publisher's Synopsis
The classification of battlespace detonations, specifically the determination of munitions type and size using temporal and spectral features, has been studied using near-infrared (NIR) and multi-color visible wavelength imagers. Key features from the time dependence of fireball size are identified for discriminating various types and sizes of detonation flashes. The five classes include three weights of trinitrotoluene (TNT) and two weights of an enhanced mixture, all of which are uncased and detonated with 10% C4. Using Fisher linear discriminant techniques, features are projected onto a line such that the projected points are maximally clustered for the different classes of detonations. Bayesian decision boundaries are then established on class-conditional probability densities. Feature saliency and stability are determined by selecting features that best discriminate while requiring low variations in class-conditional probability densities and high performance in independent testing.
