Trends in active vision

  • Jan-Olof Eklundh
Chapter
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1000)

Abstract

Active, or animate, computer vision regards the visual process as an active and task-oriented process over time. It also emphasizes the strong ties between perception and action that one can observe among seeing creatures. This paradigm has emerged over the past decade, and the article reviews its background, as well as progress made and noticeable trends. Although progress so far is limited, both concerning theoretical foundations and practical implementations, the field addresses key issues about seeing systems. Active vision is therefore likely to have substantial impact on our understanding of computational vision as well as of intelligent agents.

Keywords

Computer Vision Machine Vision Computational Vision Motion Parallax Binocular Disparity 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aloimonos, Y., Purposive and Qualitative Active Vision, Proc. DARPA Image Understanding Workshop (1990), pp. 816–828.Google Scholar
  2. 2.
    Aloimonos, Y. (Ed.), Active Perception, Lawrence Erlbaum Associates, Hillsdale, NJ. (1993).Google Scholar
  3. 3.
    Andersen, C.S. and Christensen, H.I., Using Multiple Cues for Controlling an Agile Camera Head, Proc. Workshop on Visual Behaviors, IEEE CS Press. (1994), pp. 97–101.Google Scholar
  4. 4.
    Arbib, M.A., Levels of Modeling Visually Guided Behavior (with peer commentary and author's response), Behavioral and Brain Science 10 (1987) 407–415.Google Scholar
  5. 5.
    Arbib, M.A. and Liaw J-S., Sensorimotor Transformations in the World of Frogs and Robots, Journal of Artificial Intelligence 72 (1995) 53–79.CrossRefGoogle Scholar
  6. 6.
    Ballard, D.H., Ozcandarli, A., Eye Fixation and Early Vision: Kinetic Depth, Proc. 2nd ICCV, Tampa, FL (1988), pp. 524–531.Google Scholar
  7. 7.
    Ballard, D.H., Animate vision, Journal of Artificial Intelligence 48 (1991) 57–86.CrossRefGoogle Scholar
  8. 8.
    Brooks, R.A. (1991), Intelligence without representation, Journal of Artificial Intelligence 47 (1991) 137–160.Google Scholar
  9. 9.
    Brown, C.M., The Rochester Robot, TR-257, Department of Computer Science. University of Rochester, Rochester, NY (1988).Google Scholar
  10. 10.
    Brown, C.M., Gaze Control with Interaction and Delay, IEEE Transactions on Systems, Man and Cybernetics 20 (1990a) 518–527.Google Scholar
  11. 11.
    Brown, C.M., Perception and Cooperation in Gaze Control, Biological Cybernetics 63 (1990b) 61–70.CrossRefGoogle Scholar
  12. 12.
    Burt, P.J., Smart Sensing in Machine Vision, Academic Press, New York, NY (1988).Google Scholar
  13. 13.
    Campbell, F.W. and Robson, J.G., Application of Fourier Analysis to the Visibility of Gratings, Journal of Physiology 197 (1968) 551–556.PubMedGoogle Scholar
  14. 14.
    Carpenter, R.H.S., Movements of the Eyes, Pion Limited, London, second edition (1988).Google Scholar
  15. 15.
    Clark, J.J. and Ferrier, N.J., Modal Control of an Attentive Vision System, Proc 2nd ICCV, Tampa, FL (1988), pp. 514–523.Google Scholar
  16. 16.
    Crowley, J.L. and Christensen, H.I. (Eds.), Vision as Process, Springer-Verlag, Berlin (1995).Google Scholar
  17. 17.
    Dickmanns, E.D. and Graefe, V., Dynamic Monocular Machine Vision, Machine Vision and Applications 1 (1988) 223–240.CrossRefGoogle Scholar
  18. 18.
    Edelman, S., Representing Three-dimensional Objects by Sets of Activities of Receptive Fields, Biological Cybernetics 70 (1993) 37–45.CrossRefGoogle Scholar
  19. 19.
    Freeman, W.T. and Adelson, E.H., The design and Use of Steerable Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence 13 (1991) 891–906.CrossRefGoogle Scholar
  20. 20.
    Gårding, J. and Lindeberg, T., Direct Computation of Shape cues Based on ScaleAdtapted Spatial Derivative Operators, International Journal of Computer Vision (1995) (to appear).Google Scholar
  21. 21.
    Gibson, J.J., The Perception of the Visual World, Houghton Mifflin. Boston, MA (1950).Google Scholar
  22. 22.
    Hubel, D.H. and Wiesel, T., Receptive Fields and Functional Architecture of Monkey Striate Cortex, Journal of Physiology 160 (1968) 106–154.Google Scholar
  23. 23.
    Jones, D.G. and Malik, J., A Computational Framework for Determining Stereo Correspondences from a Set of Linear Spatial Filters, in: G. Sandini (Ed.), Computer Vision — ECCV '92, Proc. 2nd European Conference on Computer Vision, Lecture Notes in Computer Science, Vol. 588, Springer-Verlag, Berlin (1992), pp. 395–410.Google Scholar
  24. 24.
    Koenderink, J.J. and van Doorn, J.J., Receptive Field Families, Biological Cybernetics 63 (1990) 291–298.CrossRefGoogle Scholar
  25. 25.
    Krotkov, E.P., Active Computer Vision by Cooperative Focus and Stereo, Springer-Verlag. Berlin (1989).Google Scholar
  26. 26.
    Kutulakos, K.N. and Dyer, C.R., Recovering Shape by Purposive Viewpoint Adjustment, International Journal of Computer Vision 12 (1994) 137–172.CrossRefGoogle Scholar
  27. 27.
    Mallot, H., Personal Communication (1995).Google Scholar
  28. 28.
    Marr, D., Vision, W.H. Freeman, New York (1982).Google Scholar
  29. 29.
    Mayhew, J.E.W., Personal Communication (1995).Google Scholar
  30. 30.
    Murray, D.M., Du, F., McLauchlan, P.F., Reid, I.D., Sharkey, P.M. and Brady, J.M., Design of Stereo Heads, in: Blake, A. and Yuille, A. (Eds.). Active Vision, the MIT Press, Cambridge, MA (1990), pp. 155–172.Google Scholar
  31. 31.
    Murray, D.M., Du, F., McLauchlan, P.F., Reid, I.D. and Sharkey, P.M., Reactions to Peripheral image Motion Using a Head/Eye Platform, Proc. Fourth International Conference on Computer Vision, Berlin (1993), pp. 403–409.Google Scholar
  32. 32.
    Nelson, R.C, Vision as intelligent behavior — an introduction to machine vision. research at the University of Rochester, International Journal of Computer Vision 7 (1991) 5–10.CrossRefGoogle Scholar
  33. 33.
    Pahlavan, K. and Eklundh, J-O., A Head-Eye System — Analysis and Design, Computer Vision Graphics and Image Processing: Image Understanding 56 (1992) 41–56Google Scholar
  34. 34.
    Pahlavan, K., Active Robot Vision and Primary Ocular Processes, Dissertation. Royal Institute of Technology, Stockholm (1993).Google Scholar
  35. 35.
    Pahlavan, K., Uhlin, T. and Eklundh, J-O., Active vision as Methodology, in: Aloimonos, Y. (Ed.), Active Perception, Lawrence Erlbaum Associates, Hillsdale, NJ. (1993)Google Scholar
  36. 36.
    Rao, R.P. and Ballard, D.H., Learning Saccadic Eye Movements Using Multiscale Spatial Filters, in: Tsauro, G., Touretzky, D. and Leen, T. (Eds.). Advances in Neural Information Processing Systems 7, the MIT Press, Cambridge, MA (1995).Google Scholar
  37. 37.
    Rimey, R.D. and Brown, C.M., Control of Selective Perception Using Bayes nets and Decision Theory, International Journal of Computer Vision 12 (1994) 173–208.CrossRefGoogle Scholar
  38. 38.
    Uhlin, T., Nordlund, P., Maki, A. and Eklundh, J-O., Towards an Active Visual Observer, Proc. 5th ICCV(1995), pp. 679–686.Google Scholar
  39. 39.
    Uhlin, T. and Eklundh, J-O., Animate Vision in a Rich Environment, Proc. IJCAI-95, Montreal (1995) (to appear).Google Scholar
  40. 40.
    Ullman, S., Visual Routines. Readings in Computer Vision, Morgan-Kaufmann Publishers, Los Altos, CA (1987), pp. 298–328.Google Scholar
  41. 41.
    Ramachandran, V.S., Interactions Between Motion, Depth, Color and Form, the Utilitarian Theory of Perception, in: Blakemore, C. (Ed.). Vision: Coding and Efficiency, Cambridge University Press, New York, NY (1990), pp. 346–360.Google Scholar
  42. 42.
    Robinson, D.A., The Oculomotor Control System: A Review, Proceedings of the IEEE 56 (1968) 1032–1049.Google Scholar
  43. 43.
    Sandini, G. and Tistarelli, M., Vision and Space Variant Sensing, in: Wechsler, H. (Ed.), Neural Networks for Perception, Academic Press, New York, NY (1992), pp. 398–425.Google Scholar
  44. 44.
    Thorpe, C., Herbert, M., Kanade, T. and Shafer, S., The new Generation System for the CMU Navlab, in: Masaki, I. (Ed.), Vision-based Vehicle Guidance, Springer-Verlag, Berlin (1992), pp. 30–82.Google Scholar
  45. 45.
    Tsotsos, J.K., Behaviorist intelligence and the scaling problem, Journal of Artificial Intelligence 75 (1995) 135–160.CrossRefGoogle Scholar
  46. 46.
    Wallace, R.S., Ong, P.W., Bederson, B.B. and Schwartz, E.L., Space Variant Image Processing, International Journal of Computer Vision 13 (1968) 71–90.CrossRefGoogle Scholar
  47. 47.
    Yarbus, A., Eye Movements and Vision, Plenum Press, New York, NY (1967).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Jan-Olof Eklundh
    • 1
  1. 1.Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing ScienceKTH (Royal Institute of Technology)StockholmSweden

Personalised recommendations