Advertisement

Unsupervised Real-Time Unusual Behavior Detection for Biometric-Assisted Visual Surveillance

  • Tsz-Ho Yu
  • Yiu-Sang Moon
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5558)

Abstract

This paper presents a novel unusual behaviors detection algorithm to acquire biometric data for intelligent surveillance in real-time. Our work aims to design a completely unsupervised method for detecting unusual behaviors without using any explicit training dataset. To this end, the proposed approach learns from the behaviors recorded in the history; such that the definition of unusual behavior is modeled according to previous observations, but not a manually labeled dataset. To implement this, pyramidal Lucas-Kanade algorithm is employed to estimate the optical flow between consecutive frames, the results are encoded into flow histograms. Leveraging the correlations between the flow histograms, unusual actions can be detected by applying principal component analysis (PCA). This approach is evaluated under both indoor and outdoor surveillance scenarios. It shows promising results that our detection algorithm is able to discover unusual behaviors and adapt to changes in behavioral pattern automatically.

Keywords

Independent Component Analysis Surveillance Video Consecutive Frame Unusual Behavior Biometric Data 
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.

References

  1. 1.
    Zhou, X., Collins, R.T., Kanade, T., Metes, P.: A master-slave system to acquire biometric imagery of humans at distance. In: IWVS 2003: First ACM SIGMM international workshop on Video surveillance, pp. 113–120. ACM, New York (2003)Google Scholar
  2. 2.
    Nishiyama, M., Yuasa, M., Shibata, T., Wakasugi, T., Kawahara, T., Yamaguchi, O.: Recognizing faces of moving people by hierarchical image-set matching. In: IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR 2007, pp. 1–8 (June 2007)Google Scholar
  3. 3.
    Chan, F., Chen, J., Moon, Y.S.: Fast construction of object correspondence in stereo camera system: an example to human face capturing system. In: IEEE Workshop on Motion and video Computing, 2008. WMVC 2008, pp. 1–6 (January 2008)Google Scholar
  4. 4.
    CNN: Police to give bomb probe details (July 2005), http://www.cnn.com/2005/WORLD/europe/07/11/london.attacks/index.html
  5. 5.
    BBC: 7/7 bombers surveillance shown (April 2008), http://news.bbc.co.uk/1/hi/england/london/7338301.stm
  6. 6.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI 1981, pp. 674–679 (1981)Google Scholar
  7. 7.
    Bouguet, J.Y.: Pyramidal implementation of the lucas kanade feature tracker: Description of the algorithm. Jean-Yves Bouguet (2002)Google Scholar
  8. 8.
    Xiang, T., Gong, S.: Activity based surveillance video content modelling. Pattern Recogn. 41(7), 2309–2326 (2008)Google Scholar
  9. 9.
    Xiang, T., Gong, S.: Video behavior profiling for anomaly detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(5), 893–908 (2008)Google Scholar
  10. 10.
    Zhong, H., Shi, J., Visontai, M.: Detecting unusual activity in video. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, vol. 2, June 2-July 2004, pp. II–819–II–826 (2004)Google Scholar
  11. 11.
    Andrade, E., Blunsden, S., Fisher, R.: Hidden markov models for optical flow analysis in crowds. In: 18th International Conference on Pattern Recognition, 2006. ICPR 2006, vol. 1, pp. 460–463 (2006)Google Scholar
  12. 12.
    Wu, X., Ou, Y., Qian, H., Xu, Y.: A detection system for human abnormal behavior. In: 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2005 (IROS 2005), pp. 1204–1208 (August 2005)Google Scholar
  13. 13.
    Li, Y., Xu, C., Liu, J., Tang, X.: Detecting irregularity in videos using kernel estimation and kd trees. In: MULTIMEDIA 2006: Proceedings of the 14th annual ACM international conference on Multimedia, pp. 639–642. ACM, New York (2006)Google Scholar
  14. 14.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, p. 2246 (1999)Google Scholar
  15. 15.
    Bobick, A., Davis, J.: The recognition of human movement using temporal templates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(3), 257–267 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Tsz-Ho Yu
    • 1
  • Yiu-Sang Moon
    • 1
  1. 1.The Chinese University of Hong KongHong Kong

Personalised recommendations