Proceedings

Animate Vision in a Rich Environment

Download BibTeX Cite

Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Action and Perception. Pages 27-34.

© 1995 International Joint Conferences on Artificial Intelligence

Abstract

Most research in comput er vision has been directed towards minimalistic approaches, in which problems are addressed on how properties of the environment can be comput ed from as little information as possible. Although such approaches may be scientifically well motivated they have only resulted in limited progress towards our understanding of seeing systems. Ballard, Bajcsy and others have pointed out the importance of vision being an active process which is tightly connected to behaviors. We support this thought and also propose that utilizing that the world is rich on information is essential. We develop this idea to show how attention and figure-ground segmentation by an active observer using multiple cues can be se parated from analyzing and recognizing what is seen in a consistent way. Continuous operation over time and early use of three dimensional cues are important in this context . We illustrate our proposed approach by some experiments on a real-time active system .

  1. Bajcsy, R. (1985). Active perception vs. passive perception . In Proceedings Third IEEE Workshop on Computer Vi- sion, pp. 55-59, Bellair. IEEE .
  2. Ballard, D.H. (1989). Animate vision. In 11th IJCAI.
  3. Ballard, D.H. (1991). Animate vision. AI, 48, 57-86.
  4. Biiltoff, H. and Edelman, S. (1992). Psycophysical support for a 2-d view interpolation theory of object recognition. In Proc. Nat. Acad. of Sci., volume 89, pp. 60-64.
  5. Crowley, J.L . and Christensen, H.I., editors (1995). Vision- as-Process. Esprit Basic Research Series. Springer-Verlag, Berlin .
  6. Culhane, S.M. and Tsotsos, J .K. (1992). An attentional pro- totype for early vision . In 2nd ECCV, pp. 551-562.
  7. Garding, J . and Lindeberg, T . (1995). Direct computation of shape cues based on scale-adapted spatial derivative operators. IJCV. (To appear).
  8. Gibson, J . J. (1979). The echological approach to visual per- ception. Houghton and Mifflin, Boston.
  9. Koenderink, J . J . and van Doorn, A. J. (1987). Represen- tation of local geometry in visual system. Biol. Cyb ., 55, 367-375.
  10. Nakayama, K. and Silverman, G. H. (1988). Serial and paral- lel processing of visual feature conjunctions. Nature, 320, 264-265.
  11. Pahlavan, K., Uhlin, T., and Eklundh, J .-0. (1993). Dynamic fixation . In 4th !CCV, pp. 412-419 .
  12. Shimojo, S., Silverman, G. H., and Nakayama, K. (1988) . An occlusion-related mechanism of depth perception based on motion and interocular sequence. Nature, 222, 265- 268.
  13. Tarr, M. J. and Black, M. J . (1994) . A computational and evolutionary perspective on the role of representationin vision. CVGIP: IU, 60, 65-118.
  14. Uhlin, T ., Nordlund, P., Maki, A., and Eklundh, J .-0. (1995). Towards an active visual observer. In 5th !CCV, Cam- bridge, MA. (To appear) .

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards