Cognitively-engineered multisensor image fusion for military applications

The fusion of imagery from multiple sensors is a field of research that has been gaining prominence in the scientific community in recent years. The technical aspects of combining multisensory image information have been and are currently being studied extensively. However, the cognitive aspects of multisensor image fusion have not received as much attention. In this study, a concurrent protocol procedure was used to identify how humans fuse information from visible and infrared imagery in low- and high-stress situations. The results of the concurrent protocol were used to develop operator function models, which were then used to develop preliminary design points for fusing multisensor image data. Fused image data were then used in a combat/target identification simulation, and operator performance, accuracy, and speed were compared with results obtained using unfused data. The results show that the model is an accurate depiction of how humans interpret information from multiple disparate sensors in this particular scenario, and that the algorithm design points show promise for assisting fighter pilots in quicker and more accurate target identification.