Active object recognition integrating attention and viewpoint control

  • Sven J. Dickinson
  • Henrik I. Christensen
  • John Tsotsos
  • Göran Olofsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


We present an active object recognition strategy which combines the use of an attention mechanism for focusing the search for a 3-D object in a 2-D image, with a viewpoint control strategy for disambiguating recovered object features. The attention mechanism consists of a probabilistic search through a hierarchy of predicted feature observations, taking objects into a set of regions classified according to the shapes of their bounding contours. If the features recovered during the attention phase do not provide a unique mapping to the 3-D object being searched, the probabilistic feature hierarchy can be used to guide the camera to a new viewpoint from where the object can be disambiguated.


Target Object Visual Event Attention Mechanism Active Vision Target Face 
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.


  1. 1.
    I. Biederman. Human image understanding: Recent research and a theory. Computer Vision, Graphics, and Image Processing, 32:29–73, 1985.Google Scholar
  2. 2.
    S. Dickinson, P. Jasiobedzki, H. Christensen, and G. Olofsson. Qualitative tracking of 3-D objects using active contour networks. In Proceedings, CVPR '94, Seattle, June 1994.Google Scholar
  3. 3.
    S. Dickinson, A. Pentland, and A. Rosenfeld. 3-D shape recovery using distributed aspect matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):174–198, 1992.Google Scholar
  4. 4.
    W. Grimson and T. Lozano-Pérez. Model-based recognition and localization from sparse range or tactile data. International Journal of Robotics Research, 3(3):3–35, 1984.Google Scholar
  5. 5.
    D. Huttenlocher and S. Ullman. Recognizing solid objects by alignment with an image. International Journal of Computer Vision, 5(2):195–212, 1990.Google Scholar
  6. 6.
    F. Jensen, H. Christensen, and J. Nielsen. Baysian methods for interpretation and control in multiagent vision systems. In K. Bowyer, editor, SPIE Applications of AI X: Machine Vision and Robotics, volume 1708, pages 536–548, Orlando, FL, April 1992.Google Scholar
  7. 7.
    J. Koenderink and A. van Doorn. The internal representation of solid shape with respect to vision. Biological Cybernetics, 32:211–216, 1979.Google Scholar
  8. 8.
    Y. Lamdan, J. Schwartz, and H. Wolfson. On recognition of 3-D objects from 2-D images. In Proceedings, IEEE International Conference on Robotics and Automation, pages 1407–1413, Philadelphia, PA, 1988.Google Scholar
  9. 9.
    T. Levitt, J. Agosta, and T. Binford. Model based influence diagrams for machine vision. In M. Herion, R. Shacter, L. Kanal, and J. lemmer, editors, Uncertainty in Artificial Intelligence 5, volume 10 of Machine Intelligence and Pattern Recognition Series, pages 371–388. North Holland, 1990.Google Scholar
  10. 10.
    D. Lowe. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Norwell, MA, 1985.Google Scholar
  11. 11.
    D. Metaxas and S. Dickinson. Integration of quantitative and qualitative techniques for deformable model fitting from orthographic, perspective, and stereo projections. In Proceedings, Fourth International Conference on Computer Vision (ICCV), Berlin, May 1993.Google Scholar
  12. 12.
    J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann Publishers, Inc., 1987.Google Scholar
  13. 13.
    R. Rimey and C. Brown. Where to look next using a bayes net: Incorporating geometric relations. In G. Sandini, editor, European Conference on Computer Vision (ECCV), volume 588 of Lecture Notes in Computer Science, pages 542–550. Springer Verlag, May 1992.Google Scholar
  14. 14.
    J. Tsotsos. On the relative complexity of active vs passive visual search. International Journal of Computer Vision, 7(2):127–141, 1992.Google Scholar
  15. 15.
    D. Wilkes, S. Dickinson, and J. Tsotsos. Quantitative modeling of view degeneracy. In Proceedings, 8th Scandinavian Conference on Image Analysis, University of TromsØ, Norway, May 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Sven J. Dickinson
    • 1
  • Henrik I. Christensen
    • 2
  • John Tsotsos
    • 1
  • Göran Olofsson
    • 3
  1. 1.Dept. of Computer ScienceUniversity of TorontoTorontoCanada
  2. 2.Laboratory of Image AnalysisIES Aalborg UniversityAalborgDenmark
  3. 3.Computational Vision and Active Perception LaboratoryRoyal Institute of TechnologyStockholmSweden

Personalised recommendations