Modeling of Human Saccadic Scanpaths Based on Visual Saliency

  • Lijuan DuanEmail author
  • Haitao Qiao
  • Chunpeng Wu
  • Zhen Yang
  • Wei Ma
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 238)


We propose a method to predict human saccadic scanpaths on natural images based on a bio-inspired visual attention model. The method integrates three related factors as driven forces to guide eye movements, sequentially-visual saliency, winner-takes-all and visual memory, respectively. When predicting a current fixation of saccadic scanpaths, we follow physiological visual memory characteristics to eliminate the effects of the previous selected fixation. Then, we use winner-takes-all to select the fixation on the current saliency map. Experimental results demonstrate that the proposed model outperform other methods on both static fixation locations and dynamic scanpaths.


visual saliency winner-takes-all visual memory saccadic scanpaths 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Itti, L.: Automatic foveation for video compression using a neurobiological model of visual attention. TIP 13(10), 1304–1318 (2004)Google Scholar
  2. 2.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. TPAMI 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  3. 3.
    Gao, D., Han, S., Vasconcelos, N.: Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition. TPAMI 31(6), 989–1005 (2009)CrossRefGoogle Scholar
  4. 4.
    Klarquist, W., Bovik, A.: Fovea: a foveated vergent active stereo vision system for dynamicthree-dimensional scene recovery. IEEE Transactions on Robotics and Automation 14(5), 755–770 (1998)CrossRefGoogle Scholar
  5. 5.
    Osberger, W., Bergmann, N., Maeder, A.: An automatic image quality assessment technique incorporating higher level perceptual factors. In: Proceedings of the 1998 International Conference on Image Processing, ICIP 1998, vol. 3, pp. 414–418 (1998)Google Scholar
  6. 6.
    Lee, S., Pattichis, M., Bovik, A.: Foveated video compression with optimal rate control. IEEE Transactions on Image Processing 10(7), 977–992 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Wang, Z., Lu, L., Bovik, A.: Foveation scalable video coding with automatic fixation selection. IEEE Transactions on Image Processing 12(2), 243–254 (2003)CrossRefGoogle Scholar
  8. 8.
    Yang, G.-Z., Dempere-Marco, L., Hu, X.-P., Rowe, A.: Visual search: psychophysical models and practical applications. Image and Vision Computing 20(4), 273–287 (2002)CrossRefGoogle Scholar
  9. 9.
    Privitera, C., Stark, L.: Human-vision-based selection of image processing algorithms for planetary exploration. IEEE Transactions on Image Processing 12(8), 917–923 (2003)CrossRefGoogle Scholar
  10. 10.
    Tsotsos, J.K., Culhane, S.M., Kei Wai, W.Y., Lai, Y., Davis, N., Nuflo, F.: Modeling visual attention via selective tuning. Artificial Intelligence 78(1), 507–545 (1995)CrossRefGoogle Scholar
  11. 11.
    Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Human Neurobiology 4(4), 219–227 (1985)Google Scholar
  12. 12.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nature Reviews Neuroscience 2(3), 194–203 (2001)CrossRefGoogle Scholar
  13. 13.
    Duan, L., Wu, C., Miao, J., Qing, L., Fu, Y.: Visual saliency detection by spatially weighted dissimilarity. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 473–480 (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Lijuan Duan
    • 1
    Email author
  • Haitao Qiao
    • 1
  • Chunpeng Wu
    • 2
  • Zhen Yang
    • 1
  • Wei Ma
    • 1
  1. 1.College of Computer Science and TechnologyBeijing University of TechnologyBeijingChina
  2. 2.Fujitsu Research & Development Center Co. Ltd.BeijingChina

Personalised recommendations