Trajectory-Based Abnormality Categorization for Learning Route Patterns in Surveillance

  • Pau Baiget
  • Carles Fernández
  • Xavier Roca
  • Jordi Gonzàlez
Part of the Studies in Computational Intelligence book series (SCI, volume 384)


The recognition of abnormal behaviors in video sequences has raised as a hot topic in video understanding research. Particularly, an important challenge resides on automatically detecting abnormality. However, there is no convention about the types of anomalies that training data should derive. In surveillance, these are typically detected when new observations differ substantially from observed, previously learned behavior models, which represent normality. This paper focuses on properly defining anomalies within trajectory analysis: we propose a hierarchical representation conformed by Soft, Intermediate, and Hard Anomaly, which are identified from the extent and nature of deviation from learned models. Towards this end, a novel Gaussian Mixture Model representation of learned route patterns creates a probabilistic map of the image plane, which is applied to detect and classify anomalies in real-time. Our method overcomes limitations of similar existing approaches, and performs correctly even when the tracking is affected by different sources of noise. The reliability of our approach is demonstrated experimentally.


Gaussian Mixture Model Anomaly Detection Vector Quantization Route Model Semantic Region 
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.
    Basharat, A., Gritai, A., Shah, M.: Learning object motion patterns for anomaly detection and improved object detection. In: CVPR, Anchorage, USA (2008)Google Scholar
  2. 2.
    Black, J., Makris, D., Ellis, T.: Hierarchical database for a multi-camera surveillance system. Pattern Analysis and Applications 7(4), 430–446 (2004)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bremond, F., Thonnat, M., Zuniga, M.: Video understanding framework for automatic behavior recognition. Behavior Research Methods 3(38), 416–426 (2006)CrossRefGoogle Scholar
  4. 4.
    de Boor, C.: A practical guide to splines. Springer, New York (1978)zbMATHCrossRefGoogle Scholar
  5. 5.
    Fernández, C., Baiget, P., Roca, F.X., Gonzàlez, J.: Interpretation of Complex Situations in a Semantic-Based Surveillance Framework. Signal Processing: Image Communication 23(7), 554–569 (2008)CrossRefGoogle Scholar
  6. 6.
    Fernyhough, J.H., Cohn, A.G., Hogg, D.: Generation of semantic regions from image sequences. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 475–484. Springer, Heidelberg (1996)Google Scholar
  7. 7.
    Gonzàlez, J., Rowe, D., Varona, J., Roca, F.: Understanding dynamic scenes based on human sequence evaluation. IMAVIS 27(10), 1433–1444 (2009)Google Scholar
  8. 8.
    Hu, W., Xiao, X., Fu, Z., Xie, D.: A system for learning statistical motion patterns. IEEE TPAMI 28(9), 1450–1464 (2006)CrossRefGoogle Scholar
  9. 9.
    Johnson, N., Hogg, D.: Learning the distribution of object trajectories for event recognition. In: BMVC 1995, pp. 583–592. BMVA Press, Surrey (1995)Google Scholar
  10. 10.
    Makris, D., Ellis, T.: Learning semantic scene models from observing activity in visual surveillance. IEEE TSMC–Part B 35(3), 397–408 (2005)Google Scholar
  11. 11.
    Piciarelli, C., Foresti, G.L.: On-line trajectory clustering for anomalous events detection. PRL 27(15), 1835–1842 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pau Baiget
    • 1
  • Carles Fernández
    • 1
  • Xavier Roca
    • 1
  • Jordi Gonzàlez
    • 1
  1. 1.Dept. Ciències de la Computació & Computer Vision CenterEdifici O, Campus Universitat Autónoma de BarcelonaBarcelonaSpain

Personalised recommendations