Room occupancy measurement using low-resolution infrared cameras

Measuring room occupancy has always been a desirable endeavour. This could be for security reasons, to save energy or simply for statistical reasons. Recently the use of thermal imaging systems in this area has increased as these systems became cheaper and therefore more attractive. This paper investigates room occupancy measurement using a low resolution (16×16 pixel) infrared camera. After giving a short overview of application areas, the chosen people detection algorithm is outlined. This includes the introduction of a novel method for blob classification, using morphological area adjustment.