Multivalued Default Logic for Identity Maintenance in Visual Surveillance

  • Vinay D. Shet
  • David Harwood
  • Larry S. Davis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3954)


Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent “atomic” events. It also requires the capacity to robustly track individuals and maintain their identities across single as well as multiple camera views. Identity maintenance is a primary source of uncertainty for activity recognition and has been traditionally addressed via different appearance matching approaches. However these approaches, by themselves, are inadequate. In this paper, we propose a prioritized, multivalued, default logic based framework that allows reasoning about the identities of individuals. This is achieved by augmenting traditional appearance matching with contextual information about the environment and self identifying traits of certain actions. This framework also encodes qualitative confidence measures for the identity decisions it takes and finally, uses this information to reason about the occurrence of certain predefined activities in video.


Activity Recognition Belief Revision Belief State Priority Level Default Rule 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Nakajima, C., Pontil, M., Heisele, B., Poggio, T.: Full-body person recognition system. Pattern Recognition 36(9), 1997–2006 (2003)CrossRefMATHGoogle Scholar
  2. 2.
    BenAbdelkader, C., Cutler, R., Davis, L.: Motion-based recognition of people in eigengait space. In: Proc. of Intl. Conf. on Auto Face and Gesture Recogtn. (2002)Google Scholar
  3. 3.
    Zhou, S., Krueger, V., Chellappa, R.: Probabilistic recognition of human faces from video. Comput. Vis. Image Underst. 91(1-2), 214–245 (2003)CrossRefGoogle Scholar
  4. 4.
    McCarthy, J.: Artificial intelligence, logic and formalizing common sense. Philosophical Logic and Artificial Intelligence (1989)Google Scholar
  5. 5.
    Krumm, J., Harris, S., Meyers, B., Brumitt, B., Hale, M., Shafer, S.: Multi-camera multi-person tracking for easyliving. In: Proc. Intl. Wkshp. on Visual Surveil (2000)Google Scholar
  6. 6.
    Wei, G., Petrushin, V., Gershman, A.: Multiple-camera people localization in a cluttered environment. In: The 5th Intl Workshop on Multimedia Data Mining (2004)Google Scholar
  7. 7.
    Starner, T., Pentland, A.: Real-time american sign language recognition from video using hidden markov models. In: Proc. of the Intl. Sym. on Computer Vision (1995)Google Scholar
  8. 8.
    Ivanov, Y.A., Bobick, A.F.: Recognition of visual activities and interactions by stochastic parsing. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 852–872 (2000)CrossRefGoogle Scholar
  9. 9.
    Buxton, H., Gong, S.: Advanced Visual Surveillance using Bayesian Networks. In: International Conference on Computer Vision, Cambridge, Massachusetts (1995)Google Scholar
  10. 10.
    Intille, S.S., Bobick, A.F.: A framework for recognizing multi-agent action from visual evidence. In: Proceedings of the sixteenth NCAIIAAI, pp. 518–525 (1999)Google Scholar
  11. 11.
    Rota, N.A., Thonnat, M.: Activity recognition from video sequences using declarative models. In: 14th ECAI 2000 Berlin Germany (2000)Google Scholar
  12. 12.
    Cohn, A.G., Magee, D.R., Galata, A., Hogg, D.C., Hazarika, S.M.: Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction. In: Freksa, C., Brauer, W., Habel, C., Wender, K.F. (eds.) Spatial Cognition III. LNCS, vol. 2685, pp. 232–248. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  13. 13.
    Bremond, F., Thonnat, M.: A context representation for surveillance systems. In: ECCV Worshop on Conceptual Descriptions from Images (1996)Google Scholar
  14. 14.
    Vu, V., Bremond, F., Thonnat, M.: Automatic video interpretation: A novel algorithm for temporal scenario recognition. In: The Eighteenth IJCAI 2003 (2003)Google Scholar
  15. 15.
    Shet, V., Harwood, D., Davis, L.: VidMAP: Video Monitoring of Activity with Prolog. In: IEEE Intl. Conf. on Advanced Video and Signal based Surveillance (2005)Google Scholar
  16. 16.
    Reiter, R.: A logic for default reasoning. Readings in nonmonotonic reasoning, pp. 68–93 (1987)Google Scholar
  17. 17.
    Ginsberg, M.L.: Multi-valued logics: a uniform approach to reasoning in artificial intelligence. Computational Intelligence 4, 265–316 (1988)CrossRefGoogle Scholar
  18. 18.
    Brewka, G.: Adding priorities and specificity to default logic. In: MacNish, C., Moniz Pereira, L., Pearce, D.J. (eds.) JELIA 1994. LNCS, vol. 838, pp. 247–260. Springer, Heidelberg (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Vinay D. Shet
    • 1
  • David Harwood
    • 1
  • Larry S. Davis
    • 1
  1. 1.Computer Vision LaboratoryUniversity of MarylandCollege ParkUSA

Personalised recommendations