A metric of background candidate assessment for spectral target signature transforms

Previous studies examined and tested a number of statistics-based registration-free transforms to find targets amid cluttered backgrounds. These transforms temporally evolve spectral target signatures under global, varying conditions using collected imagery of regions of similar objects and content distribution from datasets gathered at two different times. The transformed target signature is then inserted into the matched filter to search for targets. Although critical for transforming spectral target signatures, finding two suitable candidate regions is often difficult, computationally intensive, and may require the aid of an image analyst. This is the first study to examine a metric to help identify suitable areas for spectral target transformation. Specifically, this study examines and finds that the average correlation coefficient between the corrected histograms of the multispectral image cube collected at two times can help assess the similarity of the areas and indicate the target-to-clutter ratio, a metric shown to predict target detection performance in matched filter searches for targets.