Eye movement predictions on natural videos

Abstract We analyze the predictability of eye movements of observers viewing dynamic scenes. We first assess the effectiveness of model-based prediction. The model is divided into intersaccade prediction, which is based on a limited history of attended locations, and saccade prediction, which is based on a list of salient locations. The quality of the predictions and of the underlying saliency maps is tested on a large set of eye movement data recorded on high-resolution real-world video sequences. In addition, frequently fixated locations are used to predict individual eye movements to obtain a reference for model-based predictions.

[1]  Gerhard Krieger,et al.  Investigation of a sensorimotor system for saccadic scene analysis: an integrated approach , 1998 .

[2]  Fred Stentiford,et al.  An estimator for visual attention through competitive novelty with application to image compression , 2001 .

[3]  R. Almond.  The therapeutic community. , 1971, Scientific American.

[4]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[5]  Thomas Martinetz,et al.  Saliency Extraction for Gaze-Contingent Displays , 2004, GI Jahrestagung.

[6]  D. Noton,et al.  Eye movements and visual perception. , 1971, Scientific American.

[7]  Angelo Marcelli,et al.  Analysis of Dynamic Scenes Based on Visual Attention , 2002 .

[8]  Thomas Martinetz,et al.  Individual predictions of eye-movements with dynamic scenes , 2003, IS&T/SPIE Electronic Imaging.

[9]  John K. Tsotsos,et al.  Neurobiology of Attention , 2005 .

[10]  N. Shimizu.  [Neurology of eye movements]. , 2000, Rinsho shinkeigaku = Clinical neurology.

[11]  E. Barth,et al.  On the Uniqueness of Curvature Features 1 , 2000 .

[12]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[13]  E. Barth,et al.  A geometric framework for nonlinear visual coding. , 2000, Optics express.

[14]  Thomas Martinetz,et al.  EYE MOVEMENT PREDICTIONS ENHANCED BY SACCADE DETECTION , 2004 .

[15]  E. Barth,et al.  On the Uniqueness of Curvature Features 1 2 , 2000 .

[16]  Henrik I. Christensen,et al.  A Control Theoretical Approach to Active Vision , 1995, ACCV.

[17]  Laurent Itti,et al.  Models of Bottom-up Attention and Saliency , 2005 .

[18]  C. Zetzsche,et al.  Fundamental limits of linear filters in the visual processing of two-dimensional signals , 1990, Vision Research.

[19]  George W. Ficken.  Behind the eye , 1982 .

[20]  S. Lippman,et al.  The Scripps Institution of Oceanography , 1959, Nature.

[21]  Erhardt Barth,et al.  Variability of eye movements on high-resolution natural videos , 2002 .

[22]  A. Noë,et al.  A sensorimotor account of vision and visual consciousness. , 2001, The Behavioral and brain sciences.

[23]  Claudio M. Privitera,et al.  Algorithms for Defining Visual Regions-of-Interest: Comparison with Eye Fixations , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Thomas Martinetz,et al.  Dynamic predictions of tracked gaze , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[25]  Andrew Zisserman,et al.  An Affine Invariant Salient Region Detector , 2004, ECCV.

[26]  Raymond Klein,et al.  Inhibition of return , 2000, Trends in Cognitive Sciences.

[27]  L. Itti.  Author address: , 1999 .