A Bayesian Approach to Situated Vision

  • Giuseppe Boccignone
  • Vittorio Caggiano
  • Gianluca Di Fiore
  • Angelo Marcelli
  • Paolo Napoletano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3704)


How visual attention is shared between objects moving in an observed scene is a key issue to situate vision in the world. In this note, we discuss how a computational model taking into account such issue, can be designed in a bayesian framework. To validate the model, experiments with eye-tracked human subjects are presented and discussed.


Visual Attention Motion Segmentation Average Observer Gaussian Pyramid Local Saliency 
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.
    Hayhoe, M.M., Ballard, D.H., Bensinger, D.: Task constraints in visual working memory. Vision Research 38, 125–137 (1998)CrossRefGoogle Scholar
  2. 2.
    Pylyshyn, Z.: Situating vision in the world. Trends in Cognitive Sciences 4, 197–207 (2000)CrossRefGoogle Scholar
  3. 3.
    Zeki, S.: A Vision of the Brain. Backwell Science, Oxford (1993)Google Scholar
  4. 4.
    Goodale, M., Humphrey, G.: The objects of action and perception. Cognition 67, 181–207 (1998)CrossRefGoogle Scholar
  5. 5.
    Krauzlis, R., Stone, L.: Tracking with the minds eye. Trends Neuroscience 22, 544–550 (1999)CrossRefGoogle Scholar
  6. 6.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nature Reviews - Neuroscience 2, 1–11 (2001)Google Scholar
  7. 7.
    Lee, T.S., Mumford, D.: Hierarchical bayesian inference in the visual cortex. J. Opt. Soc. Am. A 20, 1434–1448 (2003)CrossRefGoogle Scholar
  8. 8.
    Anandan, P.: A computational framework and an algorithm for the measurment of visual motion. Int. Journal of Computer Vision 2, 283–310 (1989)CrossRefGoogle Scholar
  9. 9.
    Boccignone, G., Ferraro, M., Napoletano, P.: Diffused expectation maximisation for image segmentation. Electronics Letters 40, 1107–1108 (2004)CrossRefGoogle Scholar
  10. 10.
    Boccignone, G., Caggiano, V., Di Fiore, G., Marcelli, A., Napoletano, P.: Attentive video analysis using spatial-based and object-based cues. In: Proceedings CAMP 2005. IEEE Computer Soc. Press, Los Alamitos (2005)Google Scholar
  11. 11.
    Vasconcelos, N., Lippman, A.: Empirical bayesian motion segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 23, 217–220 (2001)CrossRefGoogle Scholar
  12. 12.
    Weiss, Y., Adelson, E.: A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models. In: Proc. IEEE Conf. CVPR 1996, pp. 321–326. IEEE Computer Soc. Press, Los Alamitos (1996)Google Scholar
  13. 13.
    Isard, M., Blake, A.: Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision 29, 5–28 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Giuseppe Boccignone
    • 1
  • Vittorio Caggiano
    • 1
  • Gianluca Di Fiore
    • 2
  • Angelo Marcelli
    • 1
  • Paolo Napoletano
    • 1
  1. 1.Natural Computation Lab, DIIIEUniversitá diSalernoFisciano (SA)Italy
  2. 2.Co.Ri.Tel. LabsFisciano (SA)Italy

Personalised recommendations