Real Time Detection of Social Interactions in Surveillance Video

  • Paolo Rota
  • Nicola Conci
  • Nicu Sebe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)


In this paper we present a novel method to detect the presence of social interactions occurring in a surveillance scenario. The algorithm we propose complements motion features with proxemics cues, so as to link the human motion with the contextual and environmental information. The extracted features are analyzed through a multi-class SVM. Testing has been carried out distinguishing between casual and intentional interactions, where intentional events are further subdivided into normal and abnormal behaviors. The algorithm is validated on benchmark datasets, as well as on a new dataset specifically designed for interactions analysis.


Video Sequence Surveillance Video Real Time Detection Casual Interaction Social Force Model 
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.
    Piotto, N., Conci, N., De Natale, F.: Syntactic matching of trajectories for ambient intelligence applications. IEEE Transactions on Multimedia 11(7), 1266–1275 (2009)CrossRefGoogle Scholar
  2. 2.
    Zhang, Y., Ge, W., Chang, M., Liu, X.: Group context learning for event recognition. In: WACV (2010)Google Scholar
  3. 3.
    Turaga, P., Chellappa, R., Subrahmanian, V., Udrea, O.: Machine recognition of human activities: A survey. IEEE Transactions on Circuits and Systems for Video Technology 18(11), 1473–1488 (2008)CrossRefGoogle Scholar
  4. 4.
    Scovanner, P., Tappen, M.: Learning pedestrian dynamics from the real world. In: ICCV, pp. 381–388 (2009)Google Scholar
  5. 5.
    Robertson, N., Reid, I.: Behaviour understanding in video: a combined method. In: ICCV, vol. 1 (2005)Google Scholar
  6. 6.
    Hall, E.: The hidden dimension, vol. 6. Doubleday, New York (1966)Google Scholar
  7. 7.
    Hall, E.: The silent language. Anchor (1973)Google Scholar
  8. 8.
    Cristani, M., Bazzani, L., Paggetti, G., Fossati, A., Tosato, D., Del Bue, A., Menegaz, G., Murino, V.: Social interaction discovery by statistical analysis of f-formations. In: Proceedings of British Machine Vision Conference (2011)Google Scholar
  9. 9.
    Zen, G., Lepri, B., Ricci, E., Lanz, O.: Space speaks: towards socially and personality aware visual surveillance. In: MPVA 2010, pp. 37–42. ACM (2010)Google Scholar
  10. 10.
    Pellegrini, S., Ess, A., Schindler, K., Van Gool, L.: You’ll never walk alone: Modeling social behavior for multi-target tracking. In: ICCV (2009)Google Scholar
  11. 11.
    Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: CVPR (2009)Google Scholar
  12. 12.
    Cui, X., Liu, Q., Gao, M., Metaxas, D.: Abnormal detection using interaction energy potentials. In: CVPR, pp. 3161–3167 (2011)Google Scholar
  13. 13.
    Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: CVPR (2012)Google Scholar
  14. 14.
    Cristani, M., Paggetti, G., Vinciarelli, A., Bazzani, L., Menegaz, G., Murino, V.: Towards computational proxemics: Inferring social relations from interpersonal distances. In: SocialCom, pp. 290–297 (2011)Google Scholar
  15. 15.
    Rota, P., Zhang, B., Ullah, H., Conci, N.: Unitn social interactions dataset. University of Trento, Italy (2012),
  16. 16.
    Laghaee, A.: Behave dataset (2007),

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Paolo Rota
    • 1
  • Nicola Conci
    • 1
  • Nicu Sebe
    • 1
  1. 1.University of TrentoPovoItaly

Personalised recommendations