Visual attention analysis by pseudo gravitational field

ABSTRACT

As a crucial step of the visual cognition and perception, visual attention analysis shows great importance in many research or application areas. In this paper, we treat this problem from a new angle, inspired by the classic gravitational field theory. By defining "mass" of each pixel, we compute "force" between them to obtain a so-called pseudo gravitational field over an image. Then, we propose an iteration algorithm to simulate the movement of the fixation points affected by this field. Finally, stable visual attention points or areas are obtained when those fixation points finally aggregate around some special pixels or areas. The main contributions are threefold: (1) by introducing classic gravitational field theory into visual attention analysis, a new point of view is proposed; (2) a competition scheme is constructed and the meaning of attraction can be applied into visual attention analysis intuitively; (3) by using pixels into computation through down sampling, a faster analysis method is achieved. The experimental result shows that our method is effective and consistent with the generally accepted definition of visual attention.

REFERENCES

• 1: C.Koch and S.Ullman. Shifts in selective visual attention: towards the underlying neural circuitry. Human Neurobiology, 4:219--227, 1985.
• 2: E.Niebur and C.Koch. Computational architectures for attention. R. Parasuraman, (Ed.), The attentive brain, Cambridge, MA: MIT Press.
• 3: J.M.Wolfe and K. Cave. Deploying visual attention: The guided search model. John Wiley & Sons Ltd., 1990.
• 4: L.Itti, C.Koch, and E.Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 20(11):1254--1259, 1998.
• 5: H. Liu, S. Jiang, Q. Huang, and et al. Region-based visual attention analysis with its application in image browsing on small displays. In Proceedings of the 15th international conference on Multimedia, 2007.
• 6: S. Lloyd and Y. Ng. Black hole computers. Scientific American, 291:52--61, 2004.
• 7: Y. Ma and H. Zhang. Contrast-based image attention analysis by using fuzzy growing. ACM Multimedia, 34:374--381, 2003.
• 8: O. L. Meur and P. L. Callet. A coherent computational approach to model bottom-up visual attention. IEEE Trans. on Pattern Analysis and Machine Intelligence, 28(5):802--817, 2006.
• 9: R.Milanese, S.Gil, and T.Pun. attentive mechanism for dynamic and static scene analysis. Optical Engineering, 34:2428--2434, 1995.
• 10: S.Baluja and D.A.Pomerleau. Expectation-based selective attention dor visual monitoring and control of a robot vehicle. Robotics and Autonomous System, 22(3-4):329--344, Dec 1997.
• 11: J. K. Tsotsos, S. M. Culhane, W. Wai, and et al. Modeling visual attention via selective tuning. Artificial Intelligence, 78:507--545, 1995.
• 12: W.James. The Principles of Psychology. Holt, New York, 1890.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
        I.4.10 Image Representation
            Subjects: Statistical

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
        I.4.10 Image Representation
            Subjects: Hierarchical

General Terms:
Algorithms, Experimentation, Theory

Keywords:
attention analysis, gravitational field, simulation algorithm