In its early years the field of computer vision was largely motivated by researchers seeking computational models of biological vision and solutions to practical problems in manufacturing defense and medicine. For the past two decades or so there has been an increasing interest in computer vision as an input modality in the context of humancomputer interaction. Such visionbased interaction can endow interactive systems with visual capabilities similar to those important to humanhuman interaction in order to perceive nonverbal cues and incorporate this information in applications such as interactive gaming visualization art installations intelligent agent interaction and various kinds of command and control tasks.