Remote Eye Tracking: State of the Art and Directions for Future Development

Recent years have seen rapid developments in the field of remote eye tracking. Whereas only a few years ago the standard in eye tracking was for systems to be intrusive, i.e. they either required the user’s head to be fixated or equipment to be mounted on the user’s head, systems have now evolved to the point where the user can move freely in front of the system (within certain limits), and good accuracy (1 degree or better) is achieved throughout the whole working range. This has been demonstrated by a number of commercial and academic systems, both multi-camera (Beymer and Flickner, 2003; LC Technologies, 2006) and singlecamera (Tobii, 2002; SMI, 2006; Hennessey et al., 2006; Guestrin and Eizenman, 2006; Meyer et al., 2006). To clarify terms, we will use the term “remote eye tracking” here to mean a system that operates without contact with the user and permits free head movement within reasonable limits without losing tracking.