Event Modeling and Recognition Using Markov Logic Networks

  • Son D. Tran
  • Larry S. Davis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)


We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited to overcome them. The knowledge is represented as first-order logic production rules with associated weights to indicate their confidence. These rules are used in combination with a relaxed deduction algorithm to construct a network of grounded atoms, the Markov Logic Network. The network is used to perform probabilistic inference for input queries about events of interest. The system’s performance is demonstrated on a number of videos from a parking lot domain that contains complex interactions of people and vehicles.


  1. 1.
    Richardson, M., Domingos, P.: Markov Logic Networks. Machine Learning 62, 107–136 (2006)CrossRefGoogle Scholar
  2. 2.
    Nevatia, R., Zhao, T., Hongeng, S.: Hierarchical language-based representation of events in video stream. In: Proc. of CVPRW on Event Mining, pp. 39–47. IEEE, Los Alamitos (2003)Google Scholar
  3. 3.
    Yamato, J., Ohya, J., Ishi, K.: Recognizing human action in time-sequential images using Hidden Markov models. In: Proc. CVPR 1992, pp. 379–385. IEEE, Los Alamitos (1992)Google Scholar
  4. 4.
    Rota, N., Thonnat, M.: Activity recognition from video sequences using declarative models. In: Proc. ECAI 2002, pp. 673–680 (2002)Google Scholar
  5. 5.
    Shet, V., Harwood, D., Davis, L.: Multivalued default logic for identity maintenance in visual surveillance. In: Proc. ECCV 2006. LNCS, vol. 4, pp. 119–132. Springer, Heidelberg (2006)Google Scholar
  6. 6.
    Shet, V., Neumann, J., Ramesh, V., Davis, L.: Bilattice-based logical reasoning for human detection. In: Proc. CVPR 2007, pp. 1–8. IEEE, Los Alamitos (2007)Google Scholar
  7. 7.
    Getoor, L., Taskar, B.: Intro. to Statistical Relational Learning. MIT Press, Cambridge (2007)zbMATHGoogle Scholar
  8. 8.
    Liao, L., Fox, D., Kautz, H.: Location-based activity recognition using Relational Markov Networks. In: Proc. IJCAI 2005, pp. 773–778. Morgan Kaufmann, Inc., San Francisco (2005)Google Scholar
  9. 9.
    Pentney, W., Popescu, A., Wang, S., Kautz, H., Philipose, M.: Sensor-based understanding of daily life via large-scale use of common sense. In: Proc. AAAI 2006 (2006)Google Scholar
  10. 10.
    Biswas, R., Thrun, S., Fujimura, K.: Recognizing activities with multiple cues. In: IEEE Works. on Human Motion, pp. 255–270 (2007)Google Scholar
  11. 11.
    Bobick, A., Ivanov, Y.: Action recognition using probabilistic parsing. In: CVPR 1998, pp. 196–202 (1998)Google Scholar
  12. 12.
    Kok, S., Singla, P., Richardson, M., Domingos, P.: The Alchemy system for statistical relational AI. Tech Report - CS Dept., Univ. of Washington (2005)Google Scholar
  13. 13.
    Minker, J., Seipel, D.: Disjunctive logic programming: A survey and assessment. In: Computational Logic, London, UK, pp. 472–511. Springer, Heidelberg (2002)Google Scholar
  14. 14.
    Singla, P., Domingos, P.: Memory-efficient inference in relational domains. In: Proc. AAAI 2006, AAAI Press, Menlo Park (2006)Google Scholar
  15. 15.
    Singla, P., Domingos, P.: Entity resolution with Markov Logic. In: Proc. ICDM, pp. 572–582. IEEE, Los Alamitos (2006)Google Scholar
  16. 16.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR 2005, vol. 2, pp. 886–893. IEEE, Los Alamitos (2005)Google Scholar
  17. 17.
    Liu, H.: The ConceptNet Project,
  18. 18.
    Stork, D.: The OpenMind Initiative,

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Son D. Tran
    • 1
  • Larry S. Davis
    • 1
  1. 1.Department of Computer ScienceUniversity of MarylandCollege ParkUSA

Personalised recommendations