Helmet-mounted uncooled FPA camera for buried object detection

Software neural nets hosted on a parallel processor can analyze input from an IR imager to evaluate the likelihood of a buried object. However, it is only recently that low weight, staring LWIR sensors have become available in uncooled formats at sensitivities that provide enough information for useful man-portable helmet mounted applications. The images from the IR are presented to a human user through a see-through display after processing and highlighting by a neural net housed in a fanny-pack. This paper describes the phenomenology of buried object detection in the infrared, the neural net based image processing, the helmet mounted IR sensor and the ergonomics of mounting a sensor to head gear. The maturing and commercialization of uncooled focal plane arrays and high density electronics enables lightweight, low cost, small camera packages that can be integrated with hard hats and military helmets. The head gear described has a noise equivalent delta temperature (NEDT) of less than 50 milliKelvin, consumes less than 10 watts and weighs about 1.5 kilograms.