Infrared search and track signal processing: a potential application of artificial neural computing

A requirement of modern airborne infrared search and track (IRST) systems is to detect targets at long distances, often in the presence of heavy cloud clutter in sky scenes, or possibly ground clutter when the IR sensor is looking down. A number of spatial processing algorithms have been tested in this study, including (1) an LMS filter and (2) an artificial neural network trained to recognize point source objects. It is the purpose of this paper to present the preliminary findings and conclusions relative to the performance of these two quite dissimilar signal IRST processing architectures. The two IRST signal processing algorithms mentioned are compared using seven test images from an IR imagery database