Advertisement

Bayesian Modeling of Visual Attention

  • Jinhua Xu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7664)

Abstract

The mechanism in the brain that determines which part of the multitude of sensory data is currently of most interest is called selective attention. There are two kinds of attention cues, stimulus-driven bottom-up cues and goal-driven top-down cues determined by cognitive phenomena like knowledge, expectations, reward, and current goals. In this paper, we propose a Bayesian approach that explains the optimal integration of top-down cues and bottom-up cues. The top down cues include appearance feature, contexts, and locations of a target. The bottom up attention (saliency) is defined as the joint probability of the local feature and context at a location in the scene. The feature and context is organized in a pyramid structure. In this way, multiscale saliency is easily implemented. We demonstrate that the proposed visual saliency effectively predicts human gaze in free-viewing of natural scenes.

Keywords

Visual attention Visual saliency Bayesian modeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Itti, L., Koch, C., Niebur, E.: A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE T. Pattern Anal. 20, 1254–1259 (1998)CrossRefGoogle Scholar
  2. 2.
    Frintrop, S., Rome, E., Christensen, H.I.: Computational Visual Attention Systems and Their Cognitive Foundations: A Survey. ACM Trans. Appl. Percept. 7 (2010)Google Scholar
  3. 3.
    Itti, L., Koch, C.: Computational Modelling of Visual Attention. Nat. Rev. Neurosci. 2, 194–203 (2001)CrossRefGoogle Scholar
  4. 4.
    Theeuwes, J.: Top-down and Bottom-up Control of Visual Selection. Acta Psychol. 135, 77–99 (2010)CrossRefGoogle Scholar
  5. 5.
    Borji, A., Itti, L.: State-of-the-Art in Visual Attention Modeling. IEEE Trans. Pattern Anal. Mach. Intell. (2012)Google Scholar
  6. 6.
    Itti, L., Koch, C.: A Saliency-Based Search Mechanism for Overt and Covert Shifts of Visual Attention. Vision Res. 40, 1489–1506 (2000)CrossRefGoogle Scholar
  7. 7.
    Bruce, N.D., Tsotsos, J.K.: Saliency, Attention, and Visual Search: an Information Theoretic Approach. J. Vis. 9, 5, 1–24 (2009)Google Scholar
  8. 8.
    Zhang, L., Tong, M.H., Marks, T.K., Shan, H., Cottrell, G.W.: SUN: A Bayesian Framework for Saliency Using Natural Statistics. J. Vis. 8, 32, 1–20 (2008)Google Scholar
  9. 9.
    Gao, D., Han, S., Vasconcelos, N.: Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition. IEEE Trans. Pattern. Anal. Mach. Intell. 31, 989–1005 (2009)CrossRefGoogle Scholar
  10. 10.
    Gao, D., Vasconcelos, N.: Decision-Theoretic Saliency: Computational Principles, Biological Plausibility, and Implications for Neurophysiology and Psychophysics. Neural Comput. 21, 239–271 (2009)zbMATHCrossRefGoogle Scholar
  11. 11.
    Itti, L., Baldi, P.: Bayesian Surprise Attracts Human Attention. Vision Res. 49, 1295–1306 (2009)CrossRefGoogle Scholar
  12. 12.
    Torralba, A., Oliva, A., Castelhano, M.S., Henderson, J.M.: Contextual Guidance of Eye Movements and Attention in Real-World Scenes: the Role of Global Features in Object Search. Psychol. Rev. 113, 766–786 (2006)CrossRefGoogle Scholar
  13. 13.
    Xu, J., Yang, Z., Tsien, J.Z.: Emergence of Visual Saliency from Natural Scenes via Context-Mediated Probability Distributions Coding. PLoS One 5 (2010)Google Scholar
  14. 14.
    Galleguillos, C., Belongie, S.: Context Based Object Categorization: A Critical Survey. Computer Vision and Image Understanding 114, 712–722 (2010)CrossRefGoogle Scholar
  15. 15.
    Olmos, A., Kingdom, F.A.: McGill Calibrated Color Image Database (2004)Google Scholar
  16. 16.
    Hyvarinen, A.: Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Trans. Neural Netw. 10, 626–634 (1999)CrossRefGoogle Scholar
  17. 17.
    Bell, A.J., Sejnowski, T.J.: The “Independent Components” of Natural Scenes Are Edge Filters. Vision Res. 37, 3327–3338 (1997)CrossRefGoogle Scholar
  18. 18.
    Olshausen, B.A., Field, D.J.: Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images. Nature 381, 607–609 (1996)CrossRefGoogle Scholar
  19. 19.
    Simoncelli, E.P., Olshausen, B.A.: Natural Image Statistics and Neural Representation. Annu. Rev. Neurosci. 24, 1193–1216 (2001)CrossRefGoogle Scholar
  20. 20.
    Tatler, B.W., Baddeley, R.J., Gilchrist, I.D.: Visual Correlates of Fixation Selection: Effects of Scale and Time. Vision Res. 45, 643–659 (2005)CrossRefGoogle Scholar
  21. 21.
    Bruce, N.D.B., Tsotsos, J.K.: Saliency Based on Information Maximization. In: Advances in Neural Information Processing Systems, pp. 155–162 (2006)Google Scholar
  22. 22.
    Gao, D., Vasconcelos, N.: Bottom-up Saliency Is a Discriminant Process. In: ICCV, Rio de Janeiro, Brazil (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jinhua Xu
    • 1
  1. 1.Department of Computer Science and TechnologyEast China Normal UniversityShanghaiChina

Personalised recommendations