| Peer-Reviewed

Crowd Anomaly Detection Using Standardized Modeled Input.

Published: 30 December 2012
Views:       Downloads:
Abstract

A variety of techniques exist for tracking and detection of pedestrian traffic.The “proof of concept” or the utility of these methods is often illustrated by analysis of a video or photographs produced by the researcher as part of the development process of the algorithms.Although these images are often based on actual human subjects, they lack portability and ground truth or at best require tedious hand mapping to record ground truth.Hence, each algorithm is developed and tested for a unique situation.Consequently, as an alternative process we propose using gaming techniques to generate pedestrian and crowd like movements that readily produce ground truth referenced via data logs.For this initial study, we have used modifications of the Reynolds flocking model to generate crowd like behavior.Using these algorithms and open-source software platforms, we generated reference crowds and then added individual pedestrian behavior within the simulated crowd.Various detection methods were applied to differentcrowd scenarios to explore and assess the utility of detection methods, illustrate the possibilities of this technique, and demonstrate an initial screening for a detection algorithm.Although not a final proof of a detection process, this method allows facile, rapid, and comparative initial evaluation of the methods under consideration.

Published in International Journal of Intelligent Information Systems (Volume 1, Issue 1)
DOI 10.11648/j.ijiis.20120101.11
Page(s) 1-6
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2012. Published by Science Publishing Group

Previous article
Keywords

Crowd Anomaly Detection, Simulated Crowd, Crowd Scenarios, and Detection Algorithm

References
[1] E. L. Andrade, S. Blunsden, and R. B. Fisher, "Modelling crowd scenes for event detection," in 18th International Conference on Pattern Recognition, 2006. ICPR 2006, vol. 1, pp. 175–178
[2] A. B. Chan, Z. S. J. Liang, and N. Vasconcelos, "Privacy preserving crowd monitoring: Counting people without people models or tracking," in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, 2008, pp. 1–7
[3] D. Y. Chen and P. C. Huang, "Dynamic human crowd modeling and its application to anomalous events detection," in Multimedia and Expo (ICME), 2010 IEEE International Conference on, pp. 1582–1587
[4] V. Mahadevan, W. Li, V. Bhalodia, and N. Vasconcelos, "Anomaly detection in crowded scenes," in Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, Los Alamitos, CA, USA, 2010, vol. 0, pp. 1975–1981
[5] T. Hospedales, J. Li, S. Gong, and T. Xiang, "Identifying Rare and Subtle Behaviours: A Weakly Supervised Joint Topic Model," Pattern Analysis and Machine Intelligence, IEEE Transactions on, no. 99, pp. 1–1
[6] D. Helbing, A. Johansson, and H. Z. Al-Abideen, "Dynamics of crowd disasters: An empirical study," Physical Review E, vol. 75, p. 7), 2007
[7] M. Moussaïd, D. Helbing, and G. Theraulaz, "How simple rules determine pedestrian behavior and crowd disasters," Proceedings of the National Academy of Sciences, Apr. 2011
[8] B. Zhan, D. Monekosso, P. Remagnino, S. Velastin, and L.-Q. Xu, "Crowd analysis: a survey," Machine Vision and Applications, vol. 19, no. 5, pp. 345–357, 2008
[9] V. Chandola, A. Banerjee, and V. Kumar, "Anomaly detection: A survey," ACM Comput. Surv., vol. 41, no. 3, pp. 15:1–15:58, Jul. 2009
[10] J. C. S. Jacques Junior, S. R. Musse, and C. R. Jung, "Crowd Analysis Using Computer Vision Techniques," Signal Processing Magazine, IEEE, vol. 27, no. 5, pp. 66–77, 2010
[11] M. Rodriguez, J. Sivic, I. Laptev, and J.-Y. Audibert, "Data-driven crowd analysis in videos," in 2011 IEEE International Conference on Computer Vision (ICCV), 2011, pp. 1235–1242
[12] D. Helbing, L. Buzn, A. Johansson, and T. Werner, "Self-Organized Pedestrian Crowd Dynamics: Experiments, Simulations, and Design Solutions," Transportation Science, vol. 39, no. 1, p. 24, 2005
[13] R. Mehran, A. Oyama, and M. Shah, "Abnormal crowd behavior detection using social force model," in IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 935–942
[14] J. M. Usher and L. Strawderman, "Simulating operational behaviors of pedestrian navigation," Computers & Industrial Engineering, vol. 59, no. 4, pp. 736–747, Nov. 2010
[15] L. Heïgeas, A. Luciani, J. Thollot, and N. Castagné, "A physically-based particle model of emergent crowd behaviors," arXiv preprint arXiv:1005.4405, 2010
[16] A. Treuille, S. Cooper, and Z. Popović, "Continuum crowds," in ACM Transactions on Graphics (TOG), 2006, vol. 25, pp. 1160–1168
[17] C. W. Reynolds, "Flocks, herds and schools: A distributed behavioral model," in ACM SIGGRAPH Computer Graphics, 1987, vol. 21, pp. 25–34
[18] U. Wilensky, (1999). Center for Connected Learning and Computer-Based Modeling, Northwestern University [online]. 1999. Available at:
[19] MATLAB (Version 2010b) [Computer Software]. Natick, MA, USA: The Mathworks
[20] Unity [Computer Software]. San Francisco, CA, USA: Unity Technologies
[21] R. Narain, A. Golas, S. Curtis, and M. C. Lin, "Aggrgate Dynamics for Dense Crowd Simulation," in SIGGRAPH Asia 2009 Proceedings, 2009
Cite This Article
  • APA Style

    Michael E. Long, Alexander Glade, Kevin J. Bierre, Bartholomew L. Moore. (2012). Crowd Anomaly Detection Using Standardized Modeled Input.. International Journal of Intelligent Information Systems, 1(1), 1-6. https://doi.org/10.11648/j.ijiis.20120101.11

    Copy | Download

    ACS Style

    Michael E. Long; Alexander Glade; Kevin J. Bierre; Bartholomew L. Moore. Crowd Anomaly Detection Using Standardized Modeled Input.. Int. J. Intell. Inf. Syst. 2012, 1(1), 1-6. doi: 10.11648/j.ijiis.20120101.11

    Copy | Download

    AMA Style

    Michael E. Long, Alexander Glade, Kevin J. Bierre, Bartholomew L. Moore. Crowd Anomaly Detection Using Standardized Modeled Input.. Int J Intell Inf Syst. 2012;1(1):1-6. doi: 10.11648/j.ijiis.20120101.11

    Copy | Download

  • @article{10.11648/j.ijiis.20120101.11,
      author = {Michael E. Long and Alexander Glade and Kevin J. Bierre and Bartholomew L. Moore},
      title = {Crowd Anomaly Detection Using Standardized Modeled Input.},
      journal = {International Journal of Intelligent Information Systems},
      volume = {1},
      number = {1},
      pages = {1-6},
      doi = {10.11648/j.ijiis.20120101.11},
      url = {https://doi.org/10.11648/j.ijiis.20120101.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20120101.11},
      abstract = {A variety of techniques exist for tracking and detection of pedestrian traffic.The “proof of concept” or the utility of these methods is often illustrated by analysis of a video or photographs produced by the researcher as part of the development process of the algorithms.Although these images are often based on actual human subjects, they lack portability and ground truth or at best require tedious hand mapping to record ground truth.Hence, each algorithm is developed and tested for a unique situation.Consequently, as an alternative process we propose using gaming techniques to generate pedestrian and crowd like movements that readily produce ground truth referenced via data logs.For this initial study, we have used modifications of the Reynolds flocking model to generate crowd like behavior.Using these algorithms and open-source software platforms, we generated reference crowds and then added individual pedestrian behavior within the simulated crowd.Various detection methods were applied to differentcrowd scenarios to explore and assess the utility of detection methods, illustrate the possibilities of this technique, and demonstrate an initial screening for a detection algorithm.Although not a final proof of a detection process, this method allows facile, rapid, and comparative initial evaluation of the methods under consideration.},
     year = {2012}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Crowd Anomaly Detection Using Standardized Modeled Input.
    AU  - Michael E. Long
    AU  - Alexander Glade
    AU  - Kevin J. Bierre
    AU  - Bartholomew L. Moore
    Y1  - 2012/12/30
    PY  - 2012
    N1  - https://doi.org/10.11648/j.ijiis.20120101.11
    DO  - 10.11648/j.ijiis.20120101.11
    T2  - International Journal of Intelligent Information Systems
    JF  - International Journal of Intelligent Information Systems
    JO  - International Journal of Intelligent Information Systems
    SP  - 1
    EP  - 6
    PB  - Science Publishing Group
    SN  - 2328-7683
    UR  - https://doi.org/10.11648/j.ijiis.20120101.11
    AB  - A variety of techniques exist for tracking and detection of pedestrian traffic.The “proof of concept” or the utility of these methods is often illustrated by analysis of a video or photographs produced by the researcher as part of the development process of the algorithms.Although these images are often based on actual human subjects, they lack portability and ground truth or at best require tedious hand mapping to record ground truth.Hence, each algorithm is developed and tested for a unique situation.Consequently, as an alternative process we propose using gaming techniques to generate pedestrian and crowd like movements that readily produce ground truth referenced via data logs.For this initial study, we have used modifications of the Reynolds flocking model to generate crowd like behavior.Using these algorithms and open-source software platforms, we generated reference crowds and then added individual pedestrian behavior within the simulated crowd.Various detection methods were applied to differentcrowd scenarios to explore and assess the utility of detection methods, illustrate the possibilities of this technique, and demonstrate an initial screening for a detection algorithm.Although not a final proof of a detection process, this method allows facile, rapid, and comparative initial evaluation of the methods under consideration.
    VL  - 1
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY, USA

  • B. Thomas Golisano College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, USA

  • B. Thomas Golisano College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, USA

  • Second Avenue Software, Inc., Pittsford, NY, USA

  • Sections