Coherence Fields for 3D Saliency Prediction

In the coherence theory of attention [26] a coherence field is defined by a hierarchy of structures, supporting the activities across the different stages of visual attention. At the interface between low level and mid level attention processing stages are the proto-objects, generated in parallel and collecting features of the scene at specific location and time. These structures fade away if the region is not further attended by attention. We introduce a method to computationally model these structures on the basis of experiments made in dynamic 3D environments, where the only control is due to the Gaze Machine, a gaze measurement framework that can record pupil motion at the required speed and project the point of regard in the 3D space [25],[24]. We show also how, from these volatile structures, it is possible to predict saliency in 3D dynamic environments.

[1]  Fiora Pirri,et al.  Bottom-Up Gaze Shifts and Fixations Learning by Imitation , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  U. Neisser,et al.  Selective looking: Attending to visually specified events , 1975, Cognitive Psychology.

[3]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[4]  Eileen Kowler.  Eye movements: The past 25years , 2011, Vision Research.

[5]  Alessandro Rudi,et al.  A general method for the point of regard estimation in 3D space , 2011, CVPR 2011.

[6]  Anne Treisman,et al.  Preattentive processing in vision , 1985, Computer Vision Graphics and Image Processing.

[7]  L. Stark,et al.  The trajectories of saccadic eye movements. , 1979, Scientific American.

[8]  Ronald A. Rensink,et al.  TO SEE OR NOT TO SEE: The Need for Attention to Perceive Changes in Scenes , 1997 .

[9]  José R. Álvarez,et al.  Artificial Intelligence and Knowledge Engineering Applications: A Bioinspired Approach: First International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2005, Las Palmas, Canary Islands, Spain, June 15-18, 2005, Proceedings, Part II , 2005, IWINAC.

[10]  J. Wolfe,et al.  Guided Search 2.0 A revised model of visual search , 1994, Psychonomic bulletin & review.

[11]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[12]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[13]  Ronald A. Rensink,et al.  On the Failure to Detect Changes in Scenes Across Brief Interruptions , 2000 .

[14]  L. Itti,et al.  Visual causes versus correlates of attentional selection in dynamic scenes , 2006, Vision Research.

[15]  J. Wolfe,et al.  The role of categorization in visual search for orientation. , 1992, Journal of experimental psychology. Human perception and performance.

[16]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[17]  B. Julesz,et al.  Texton gradients: The texton theory revisited , 2004, Biological Cybernetics.

[18]  Nuno Vasconcelos,et al.  Spatiotemporal Saliency in Dynamic Scenes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[20]  Fiora Pirri,et al.  3D Saliency maps , 2011, CVPR 2011 WORKSHOPS.

[21]  Garrison W. Cottrell,et al.  Visual saliency model for robot cameras , 2008, 2008 IEEE International Conference on Robotics and Automation.

[22]  Christof Koch,et al.  Modeling attention to salient proto-objects , 2006, Neural Networks.

[23]  L Stark,et al.  Closely spaced saccades. , 1975, Investigative ophthalmology.

[24]  Christof Koch,et al.  Predicting human gaze using low-level saliency combined with face detection , 2007, NIPS.

[25]  Giulio Sandini,et al.  A Proto-object Based Visual Attention Model , 2008, WAPCV.

[26]  Marie desJardins,et al.  Data Clustering with a Relational Push-Pull Model , 2007 .

[27]  Fiora Pirri,et al.  From Saliency to Eye Gaze: Embodied Visual Selection for a Pan-Tilt-Based Robotic Head , 2011, ISVC.

[28]  Ronald A. Rensink.  The Dynamic Representation of Scenes , 2000 .

[29]  S. Yantis,et al.  Selective visual attention and perceptual coherence , 2006, Trends in Cognitive Sciences.

[30]  Ali Shokoufandeh,et al.  Landmark Selection for Vision-Based Navigation , 2006, IEEE Trans. Robotics.

[31]  Laurent Itti,et al.  Robot steering with spectral image information , 2005, IEEE Transactions on Robotics.

[32]  J. Wolfe.  The Parallel Guidance of Visual Attention , 1992 .

[33]  Wei Zhou,et al.  An updated Time-Optimal 3rd-Order Linear Saccadic Eye Plant Model , 2009, Int. J. Neural Syst..

[34]  John K. Tsotsos,et al.  Attention in Cognitive Systems, 5th International Workshop on Attention in Cognitive Systems, WAPCV 2008, Fira, Santorini, Greece, May 12, 2008, Revised Selected Papers , 2009, WAPCV.

[35]  J. Duncan,et al.  Visual search and stimulus similarity. , 1989, Psychological review.

[36]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[37]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[38]  Minoru Asada,et al.  Image feature generation by visio-motor map learning towards selective attention , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[39]  Gang Kou,et al.  Feature Selection for Nonlinear Kernel Support Vector Machines , 2007 .

[40]  Heinz Hügli,et al.  Model Performance for Visual Attention in Real 3D Color Scenes , 2005, IWINAC.