Advertisement

Learning Spatial Event Models from Multiple-Camera Perspectives

  • Michael H. Coen
  • Kevin W. Wilson

Abstract

Intelligent environments promise to drastically change our everyday lives by connecting computation to the ordinary, human-level events happening in the real world. This paper describes a new model for tracking people in an intelligent room through a multi-camera vision system that learns to combine event predictions from multiple video streams. The system is intended to locate and track people in the room, determine their postures, and obtain images of their faces and upper bodies suitable for use during teleconferencing. This paper describes the design and architecture of the vision system and its use in Hal, our most recently constructed intelligent room.

Keywords

Vision System Optical Flow Video Stream Application Program Interface Face Detection 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bobick, A.; Intille, S.; Davis, J.; Baird, F.; Pinhanez, C.; Campbell, L.; Ivanov, Y.; Schütte, A.; and Wilson, A. Design Decisions for Interactive Environments: Evaluating the KidsRoom. Proceedings of the 1998 AAAI Spring Symposium on Intelligent Environments. AAAI TR SS-98-02. 1998.Google Scholar
  2. 2.
    Coen, M. Building Brains for Rooms: Designing Distributed Software Agents. In Proceedings of the Ninth Conference on Innovative Applications of Artificial Intelligence. (IAAI97). Providence, R.I. 1997.Google Scholar
  3. 3.
    Coen, M. Design Principles for Intelligent Environments. In Proceedings of The Fifteenth National Conference on Artificial Intelligence. (AAAI98). Madison, Wisconsin. 1998.Google Scholar
  4. 4.
    Coen, M. (ed.) Proceedings of the 1998 AAAI Spring Symposium on Intelligent Environments. AAAI TR SS-98-02. 1998.Google Scholar
  5. 5.
    Coen, M. The Future Of Human-Computer Interaction or How I learned to stop worrying and love My Intelligent Room. IEEE Intelligent Systems. March/April. 1999.Google Scholar
  6. 6.
    Forsyth, D. and Fleck, M. Finding Naked People, European Conference on Computer Vision, Volume II, pp. 592–602. 1996.Google Scholar
  7. 7.
    Lien, J., Zlochower, A., Cohn, J., Li, C., and Kanade, T. Automatically Recognizing Facial Expressions in the Spatio-Temporal Domain. Proceedings of the Workshop on Perceptual User Interfaces (PUI’97). Alberta, Canada. pp.94–97. 1997.Google Scholar
  8. 8.
    Lucente, M.; Zwart, G.; George, A. Visualization Space: A Testbed for Deviceless Multimodal User Interface. Proceedings of the AAAI 1998 Spring Symposium on Intelligent Environments. AAAI TR SS-98-02. 1998.Google Scholar
  9. 9.
    Mozer, M. The Neural Network House: An Environment that Adapts to its Inhabitants. Proceedings of the AAAI 1998 Spring Symposium on Intelligent Environments. AAAI TR SS-98-02. 1998.Google Scholar
  10. 10.
    Scassellati, B. Eye Finding via Face Detection for a Foveated, Active Vision System, Proceedings of the National Conference on Artificial Intelligence, Madison, WI. 1998.Google Scholar
  11. 11.
    Sinha, P. Object Recognition via image invariants: A case study, Investigative Opthalmology and Visual Science, 35, pp. 1735–1740. 1994.Google Scholar
  12. 12.
    Stein, G. Internal Camera Calibration using Rotation and Geometric Shapes, Master’s Thesis, Massachusetts Institute of Technology, Cambridge, MA. 1993.Google Scholar
  13. 13.
    Stiefelhagen, R., Yang, J., and Waibel, A. Tracking Eyes and Monitoring Eye Gaze. Proceedings of the Workshop on Perceptual User Interfaces (PUI’97). Alberta, Canada. pp.98–100. 1997.Google Scholar
  14. 14.
    Want, R.; Schilit, B.; Adams, N.; Gold, R.; Petersen, K.; Goldberg, D.; Ellis, J.; and Weiser, M. The ParcTab Ubiquitous Computing Experiment. Xerox Parc technical report.Google Scholar
  15. 15.
    Weiser, M. The Computer for the 21st Century. Scientific American. pp.94–100, September, 1991.Google Scholar

Copyright information

© Springer-Verlag London Limited 2000

Authors and Affiliations

  • Michael H. Coen
    • 1
  • Kevin W. Wilson
    • 1
  1. 1.MIT Artificial Intelligence LabCambridgeUSA

Personalised recommendations