Integrating Inhomogeneous Processing and Proto-object Formation in a Computational Model of Visual Attention

  • Marco Wischnewski
  • Jochen J. Steil
  • Lothar Kehrer
  • Werner X. Schneider
Part of the Cognitive Systems Monographs book series (COSMOS, volume 6)


We implement a novel computational framework for attention that includes recent experimentally derived assumptions on attention which are not covered by standard computational models. To this end, we combine inhomogeneous visual processing, proto-object formation, and parts of TVA (Theory of Visual Attention [2]), a well established computational theory in experimental psychology, which explains a large range of human and monkey data on attention. The first steps of processing employ inhomogeneous processing for the basic visual feature maps. Next, we compute so-called proto-objects by means of blob detection based on these inhomogeneous maps. Our model therefore displays the well known ”global-effect” of eye movement control, that is, saccade target landing objects tend to fuse with increasing eccentricity from the center of view. The proto-objects also allow for a straightforward application of TVA and its mechanism to model task-driven selectivity. The final stage of our model consists of an attentional priority map which assigns priority to the proto-objects according to the computations of TVA. This step allows to restrict sophisticated filter computation to the proto-object regions and thereby renders our model computationally efficient by avoiding a complete standard pixel-wise priority computation of bottom-up saliency models.


Input Image Visual Attention Voronoi Cell Attentional Weight Foveal Center 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Breazeal, C., Scassellati, B.: A context-dependent attention system for a social robot. In: Proc. 16th IJCAI, pp. 1146–1153 (1999)Google Scholar
  2. 2.
    Bundesen, C.: A theory of visual attention. Psych. Rev. 97, 523–547 (1990)CrossRefGoogle Scholar
  3. 3.
    Bundesen, C., Habekost, T.: Principles of visual attention. Oxford University Press, Oxford (2008)Google Scholar
  4. 4.
    Bundesen, C., Habekost, T., Killingsbaek, S.: A neural theory of visual attention: Bridging cognition and neurophysiology. Psych. Rev. 112, 291–328 (2005)CrossRefGoogle Scholar
  5. 5.
    Deubel, H., Schneider, W.X.: Saccade target selection and object recognition: Evidence for a common attentional mechanism. Vis. Res. 36, 1827–1837 (1996)CrossRefGoogle Scholar
  6. 6.
    Driscoll, J.A., Peters II, R.A., Cave, K.R.: A visual attention network for a humanoid robot. In: Proc. IEEE/RSJ IROS 1998, pp. 12–16 (1998)Google Scholar
  7. 7.
    Findlay, J.M.: Global processing for saccadic eye movements. Vis. Res. 22, 1033–1045 (1982)CrossRefGoogle Scholar
  8. 8.
    Forssén, P.E.: Low and medium level vision using channel representations. Dissertation No. 858 (2004), ISBN 91-7373-876-XGoogle Scholar
  9. 9.
    Fogel, I., Sagi, D.: Gabor filters as texture dicriminator. Biol. Cybern. 61, 103–113 (1989)CrossRefGoogle Scholar
  10. 10.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. In: IEEE ICCV, pp. 195–202 (1998)Google Scholar
  11. 11.
    Kehrer, L.: Central performance drop on perceptual segregation tasks. Spatial Vision 4, 45–62 (1989)CrossRefGoogle Scholar
  12. 12.
    Nagai, Y., Hosoda, K., Morita, A., Asada, M.: A constructive model for the development of joint attention. Connection Science 15, 211–229 (2003)CrossRefGoogle Scholar
  13. 13.
    Orabona, F., Metta, G., Sandini, G.: A Proto-object based visual attention model. In: Paletta, L., Rome, E. (eds.) WAPCV 2007. LNCS (LNAI), vol. 4840, pp. 198–215. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  14. 14.
    Palmer, S.E.: Vision Science, pp. 29–31. The MIT Press, Cambridge (1999)Google Scholar
  15. 15.
    Schneider, W.X.: VAM: A neuro-cognitive model for visual attention control of segmentation, object recognition, and space-based motor action. Vis. Cog. 2, 331–375 (1995)CrossRefGoogle Scholar
  16. 16.
    Steil, J.J., Heidemann, G., Jockusch, J., Rae, R., Jungclaus, N., Ritter, H.: Guiding attention for grasping tasks by gestural instruction: The GRAVIS-robot architecture. In: Proc. IEEE/RSJ IROS 2001, pp. 1570–1577 (2001)Google Scholar
  17. 17.
    Sun, Y., Fisher, R., Wang, F., Gomes, H.M.: A computer vision model for visual-object-based attention and eye movements. Computer Vision and Image Understanding 112, 126–142 (2008)CrossRefGoogle Scholar
  18. 18.
    Treisman, A.M.: Features and objects: The fourteenth Bartlett memorial lecture. Quarterly Journal of Experimental Psychology 40A, 201–237 (1988)Google Scholar
  19. 19.
    Walther, D., Koch, C.: Modeling attention to salient proto-objects. Neural Networks 19, 1395–1407 (2006)zbMATHCrossRefGoogle Scholar
  20. 20.
    Watson, A.B.: Detection and recognition of simple spatial forms. In: Braddick, O.J., Sleigh, A.C. (eds.) Physiological and biological processing of images, pp. 100–114. Springer, Heidelberg (1983)Google Scholar
  21. 21.
    Wolfe, J.M.: Guided search 2.0: a revised model of visual search. Psychonomic Bulletin and Review 1, 202–238 (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Marco Wischnewski
    • 1
  • Jochen J. Steil
    • 2
  • Lothar Kehrer
    • 3
  • Werner X. Schneider
    • 4
  1. 1.Center of Excellence - Cognitive Interaction Technology (CITEC) and Neuro-cognitive PsychologyBielefeld University 
  2. 2.Research Institute for Cognition and Robotics (CoR-Lab)Bielefeld University 
  3. 3.Neuro-cognitive PsychologyBielefeld University 
  4. 4.Neuro-cognitive Psychology and Center of Excellence - Cognitive Interaction Technology (CITEC)Bielefeld University 

Personalised recommendations