A neural network for 3D gaze recording with binocular eye trackers

Using eye tracking for the investigation of visual attention has become increasingly popular during the last few decades. Nevertheless, only a small number of eye tracking studies have employed 3D displays, although such displays would closely resemble our natural visual environment. Besides higher cost and effort for the experimental setup, the main reason for the avoidance of 3D displays is the problem of computing a subject's current 3D gaze position based on the measured binocular gaze angles. The geometrical approaches to this problem that have been studied so far involved substantial error in the measurement of 3D gaze trajectories. In order to tackle this problem, we developed an anaglyph-based 3D calibration procedure and used a well-suited type of artificial neural network—a parametrized self-organizing map (PSOM)—to estimate the 3D gaze point from a subject's binocular eye-position data. We report an experiment in which the accuracy of the PSOM gaze-point estimation is compared to a geometrical solution. The results show that the neural network approach produces more accurate results than the geometrical method, especially for the depth axis and for distant stimuli.

[1]  Donald L. Fisher,et al.  EYE MOVEMENTS AND THE PERCEPTUAL SPAN DURING VISUAL SEARCH , 1987 .

[2]  B. C. Motter,et al.  The guidance of eye movements during active visual search , 1998, Vision Research.

[3]  J. K. O'Regan,et al.  Eye movements : from physiology to cognition : selected/edited proceedings of the Third European Conference on Eye Movements, Dourdan, France, September 1985 , 1987 .

[4]  J. Findlay,et al.  Eye guidance and visual search , 1998 .

[5]  Eyal M. Reingold,et al.  Selection By Looking: A Novel Computer Interface And Its Application To Psychological Research , 1995 .

[6]  D E Williams,et al.  Preattentive guidance of eye movements during triple conjunction search tasks: The effects of feature discriminability and saccadic amplitude , 2001, Psychonomic bulletin & review.

[7]  Dave M. Stampe,et al.  Heuristic filtering and reliable calibration methods for video-based pupil-tracking systems , 1993 .

[8]  J. H. Bertera,et al.  Eye movements and the span of the effective stimulus in visual search , 2000, Perception & psychophysics.

[9]  K. Preston White,et al.  Eye-gaze word processing , 1990, IEEE Trans. Syst. Man Cybern..

[10]  Helge Ritter,et al.  Parametrized Self-Organizing Maps , 1993 .

[11]  Andrew T. Duchowski,et al.  Eye Tracking Methodology: Theory and Practice , 2003, Springer London.

[12]  K. Rayner.  Eye movements in reading and information processing: 20 years of research. , 1998, Psychological bulletin.

[13]  R. B. Mercer,et al.  The Ocular Communicator: A Device to Enable Persons with Severe Physical Disabilities to Communicate Using Eye Movements. , 1987 .

[14]  M. Behrmann,et al.  Patterns of eye movements during parallel and serial visual search tasks. , 1997, Canadian journal of experimental psychology = Revue canadienne de psychologie experimentale.

[15]  Arthur M. Jacobs.  TOWARD A MODEL OF EYE MOVEMENT CONTROL IN VISUAL SEARCH , 1987 .

[16]  J. Findlay,et al.  Visual search in depth , 2001, Vision Research.

[17]  David L. Sheinberg,et al.  Eye movements during parallel-serial visual search. , 1997, Journal of experimental psychology. Human perception and performance.

[18]  Eyal M. Reingold,et al.  Empirical Evaluation of a Novel Gaze-Controlled Zooming Interface , 2001 .

[19]  Helge J. Ritter,et al.  An Artificial Neural Network for High Precision Eye Movement Tracking , 1994, KI.

[20]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.