Automation of rare target detection via adaptive fusion

Fusing the outputs of multiple algorithms has been found to provide more consistent detection of rare targets in hyperspectral imagery. An analogous process that fuses different outputs from the same algorithm with different input parameter values also shows promise for eliminating the need for supervised parameter tuning. Together these strategies provide significant improvement in the consistency and automation of hyperspectral target detection. Results are presented for nine test cases involving both visible/near-infrared/shortwave-infrared and long-wavelength infrared hyperspectral imagery.