Over the past several years, hyperspectral sensor technology has evolved to the point where real-time processing for operational applications is achievable. Algorithms supporting such sensors must be fully automated and robust. Our approach, for target detection applications, is to select signatures from a target reflectance library database and project them to the at-sensor and collection-specific radiance domain using the weather forecast or radiosonde data. This enables platform-based detection immediately following data acquisition without the need for further atmospheric compensation. One advantage of this method for reflective hyperspectral sensors is the ability to predict the radiance signatures of targets under multiple illumination conditions. A three-phase approach is implemented, where the library generation and data acquisition phases provide the necessary input for the automated detection phase. In addition to employing the target detector itself, this final phase includes a series of automated filters, adaptive thresholding, and confidence assignments to extract the optimal information from the detection scores for each spectral class. Our prototype software is applied to 50 reflective hyperspectral datacubes to measure detection performance over a range of targets, backgrounds, and environmental conditions.