On Focus-of-Attention by Active Focusing

  • Kjell Brunnström
  • Jan-Olof Eklundh
  • Akira Kakimoto
Conference paper
Part of the NATO ASI Series book series (volume 83)

Abstract

Focus-of-attention is extremely important in human visual perception. If computer vision systems are to perform tasks in a complex, dynamic world they will have to be able to control processing in a way that is analogous to visual attention in humans.

In this paper we will investigate problems in connection with foveation, that is in examining selected regions of the world at high resolution. We will consider a static world viewed by an active observer that has this capability. The tasks we will consider is that of finding and classifying junctions of contours, features that give important information about 3-dimensional structure like object shape and occlusions. Since they are completely local features, we can study them without treating the problem of integrating local information into global cues. We will show that foveation, as simulated by controlled, active zooming, allows robust detection and classification of junctions with very simple algorithms.

Keywords

Pyramid Rounded 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ballard, D.H., (1987), Eye Movements and Visual Cognition, Proc. AAAI Workshop on Spatial Reasoning and Multi-Sensory Fusion, St Charles, III, 1987, 188–200Google Scholar
  2. Bergholm, F., (1987), Edge Focusing, IEEE PAMI, 9: 6, 726–741CrossRefGoogle Scholar
  3. Brunnström, K., Eklundh, J.O., Kakimoto, A., (1989), On Focus of Attention and Active Computer Vision, Proc. NATO ASI on Robotics and Active Computer Vision, Springer Verlag, New York, in pressGoogle Scholar
  4. Burt, P.J., (1988), Attention Mechanisms for Vision in a Dynamic World, Proc. 9th I CPR, Rome, 1989, 977–987Google Scholar
  5. Canny, J.F., (1986), A Computational Approach to Edge Detection, IEEE PAMI, 8: 6, 679–698CrossRefGoogle Scholar
  6. Harris, C., Stephens, M., (1988), A Combined Corner and Edge Detector, Proc. 4th Alvey Vision Conference, 1988, 147–152Google Scholar
  7. Hückel, M., (1971), Operator which Locates Edges in Digitized Pictures, JACM, 18, 113–125CrossRefMATHGoogle Scholar
  8. Kitchen, L., Rosenfeld, R., (1982), Gray-Level Corner Detection, Pattern Recognition Letters, 1: 2, 95–102CrossRefGoogle Scholar
  9. Marr, D., Hildreth, E., (1980), Theory of Edge Detection, Proc. Royal Society of London, B-207, 187–217Google Scholar
  10. Moravec, H.P., (1977), Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover, Stanford AIM-340Google Scholar
  11. Lindeberg, T., Eklundh, J.O., (1989), On the Computation of a Scale-Space Primal Sketch, submittedGoogle Scholar
  12. Malik, J., (1987), Interpreting Line Drawings of Curved Objects, Int. Journal of Computer Vision, 1: 1, 73–103CrossRefMathSciNetGoogle Scholar
  13. Nagel, H.H., (1986), Image Sequences - The (Octal) Years - From Phenomenology towards a Theoretical Foundation, Proc. 8th ICPR, 1174–1185Google Scholar
  14. Nagel, H.H., (1989), Personal communication Google Scholar
  15. Peleg, S., (1978), Iterative Histogram Modification 2, IEEE SMC, 8, 555–556Google Scholar
  16. Waltz, D., (1975), Understanding Line Drawings of Scenes with Shadows, in Winstor, P.H., ed., The Psychology of Computer Vision, McGraw-Hill, New YorkGoogle Scholar
  17. Waxman, A.M., Wu, J., Seibert, M., (1989), Computing Visual Motion in the Short and Long: From Receptive Fields to Neural Networks, Proc. IEEE Workshop on Visual Motion, Irvine, Ca., 1989, 156–164Google Scholar
  18. Wilson, H.R., (1983), Psychophysical Evidence for Spatial Channels, Braddick, O.J., Sleigh, A.C., eds., in Physical and Biological Processing of Images, Springer Verlag, New YorkGoogle Scholar
  19. Witkin, A.P., (1983), Scale-Space Filtering, Proc. 8th IJCAI, 1019–1021Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Kjell Brunnström
    • 1
  • Jan-Olof Eklundh
    • 1
  • Akira Kakimoto
    • 1
  1. 1.Computer Vision and Associative Pattern Processing Laboratory, (CVAP) Department of Computer Vision and Numerical AnalysisRoyal Institute of TechnologyStockholmSweden

Personalised recommendations