Skip to main content
SpringerLink
Log in

Small scale crowd behavior classification by Euclidean distance variation-weighted network

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Crowd behavior analysis is a key research topic in the field of computer vision. The traditional method of crowd behavior analysis can be divided into two categories. One is the microscopic-based method, which is mainly through extracting the gestures and trajectories of every individual to recognize the behavior of a crowd. The other is the macroscopic-based method, in which the statistical characteristics of a crowd are used to represent the crowd behavior. By exploring the connection between the microscopic and macroscopic properties of a crowd, a method which use Euclidean distance variation-weighted network to recognize the crowd behavior is proposed in this paper. Firstly, the trajectories and location information of the individuals in crowd are captured by tracking every pedestrian. Furthermore, by calculating the Euclidean distance variation between two individuals the interaction between individuals is gained. Then, the Euclidean distance variation-weighted networks of five typical crowd behavior including gather, meet, together, separation and dispersion are constructed. The nodes represent individuals in the crowd and the weight of each edge represents the extent of interaction between individuals. Finally, the characteristic parameters of crowd networks including the path length and network weights are extracted and the crowd behavior is classified by using k-nearest neighbor method. Experimental results show the proposed method can effectively express and recognize small-scale crowd behavior. The lowest classification accuracy of the proposed method can reach 86.8 % in the five kinds of crowd behavior.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Alqaysi HH, Sasi S (2013) Detection of abnormal behavior in dynamic crowded gatherings. Applied imagery pattern recognition workshop: sensing for control and augmentation, 2013 IEEE(AIPR) Washington, DC, pp 1−6

  2. Amine D, Nassreddine B, Bouabdellah K (2014) Energy efficient and safe weighted clustering algorithm for mobile wireless sensor networks. Procedia Comput Sci 34:63–70

    Article  Google Scholar 

  3. An X, Zhang L, Li Y, Zhang J (2014) Synchronization analysis of complex networks with multi-weights and its application in public traffic network. Physica A Stat Mech Appl 412:149–156

    Article  MathSciNet  Google Scholar 

  4. Biswas S, Babu RV (2014) Anomaly detection in compressed H.264/AVC video. Multimed Tools Appl Accepted. doi:10.1007/s11042-014-2219-4. Published online 28 Aug 2014

  5. Brostow GJ, Cipolla R (2006) Unsupervised Bayesian detection of independent motion in crowds. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, 1:594−601

  6. Estrada E, Vargas-Estrada E (2012) Distance-sum heterogeneity in graphs and complex networks. Appl Math Comput 218(21):10393–10405

    Article  MathSciNet  MATH  Google Scholar 

  7. Ge W, Collins RT (2009) Marked point processes for crowd counting. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. Miami, FL 1–4:2913–2920

  8. Golas A, Narain R, Curtis S, Lin M (2014) Hybrid long-range collision avoidance for crowd simulation. IEEE Trans Vis Comput Graph 20(7):1022–1034

    Article  Google Scholar 

  9. Gu X, Cui J, Zhu Q (2014) Abnormal crowd behavior detection by using the particle entropy. Optik Int J Light Electron Opt 125(14):3428–3433

    Article  Google Scholar 

  10. Haritaoglu I, Harwood D, Davis LS (2000) W4: real-time surveillance of people and their activities. IEEE Trans Pattern Anal Mach Intell 22(8):809–830

    Article  Google Scholar 

  11. Hsieh JW, Hsu YT, Liao HYM, Chen CC (2008) Video-based human movement analysis and its application to surveillance systems. IEEE Trans Multimedia 10(3):372–384

    Article  Google Scholar 

  12. Kountouriotis V, Thomopoulos SCA, Papelis Y (2014) An agent-based crowd behaviour model for real time crowd behaviour simulation. Pattern Recogn Lett 44:30–38

    Article  Google Scholar 

  13. Kratz L, Nishino K (2009) Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. Miami, FL 1–4:1446–1453

  14. Krishnan R, Sarkar S (2015) Conditional distance based matching for one-shot gesture recognition. Pattern Recogn 48(8):1302–1314

    Article  Google Scholar 

  15. Li W, Mahadevan V, Vasconcelos N (2014) Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell 36(1):18–32

    Article  Google Scholar 

  16. Lin J, Ding Y (2013) A temporal hand gesture recognition system based on hog and motion trajectory. Optik Int J Light Electron Opt 124(24):6795–6798

    Article  Google Scholar 

  17. Morris BT, Trivedi MM (2008) A survey of vision-based trajectory learning and analysis for surveillance. IEEE Trans Circuits Syst Video Technol 18(8):1114–1127

    Article  Google Scholar 

  18. Nam Y (2014) Crowd flux analysis and abnormal event detection in unstructured and structured scenes. Multimedia Tools Appl 72:3001–3029

    Article  Google Scholar 

  19. Nix T, Bettati R (2014) Neighborhood failures in random topology covert communication networks. Procedia Comput Sci 32:1127–1134

    Article  Google Scholar 

  20. Raheja JL, Chaudhary A, Maheshwari S (2014) Hand gesture pointing location detection. Optik Int J Light Electron Opt 125(3):993–996

    Article  Google Scholar 

  21. Rao Y, Chen L, Liu Q, Lin W, Li Y, Zhou J (2011) Real-time control of individual agents for crowd simulation. Multimedia Tools Appl 54:397–414

    Article  Google Scholar 

  22. Saini M, Atrey PK, Mehrotra S, Kankanhalli M (2014) W3-privacy: understanding what, when, and where inference channels in multi-camera surveillance video. Multimedia Tools Appl 68:135–158

    Article  Google Scholar 

  23. Vezzani R, Cucchiara R (2010) Video Surveillance Online Repository (ViSOR): an integrated framework. Multimedia Tools Appl 50:359–380

    Article  Google Scholar 

  24. Wang S (2012) The improved Dijkstra’s shortest path algorithm and its application. Procedia Eng 29:1186–1190

    Article  Google Scholar 

  25. Wang B, Ye M, Li X, Zhao F, Ding J (2012) Abnormal crowd behavior detection using high-frequency and spatio-temporal features. Mach Vis Appl 23:501–511

    Article  Google Scholar 

  26. Zawidzki M, Chraibi M, Nishinari K (2014) Crowd-Z: the user-friendly framework for crowd simulation on an architectural floor plan. Pattern Recogn Lett 44:88–97

    Article  Google Scholar 

  27. Zhang X, Li X, Liang M, Wang Y (2011) Covariance tracking with forgetting factor and random sampling. Int J Uncertainty Fuzziness Knowledge Based Syst 19(3):547–558

    Article  Google Scholar 

  28. Zhang Y, Li X, Yang J, Liu Y, Xiong N, Vasilakos A (2013) A real-time dynamic key management for hierarchical wireless multimedia sensor network. Multimedia Tools Appl 67:97–117

    Article  Google Scholar 

  29. Zhou Y, Yan S, Huang TS (2007) Detecting anomaly in videos from trajectory similarity analysis. In: IEEE International Conference on Multimedia and Expo, 2007. Beijing, China, p1087–1090

  30. Zhou Y, Yan S, Huang TS (2008) Pair-activity classification by bi-trajectory analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. Anchorage, AK, 1−6:3682−3689

Download references

Acknowledgments

This research was supported by National Natural Science Foundation of China (No. 61271409), China Postdoctoral Science Foundation (No. 2012M510768, No. 2013T60264), Natural Science Foundation of Hebei Province, China (No. F2013203364), and China Scholarship Council (No. 2011813018).

Author information

Authors and Affiliations

  1. School of Electrical Engineering, Yanshan University, Qinhuangdao, China

    Xuguang Zhang, Meiling Ouyang & Xufeng Zhang

Authors
  1. Xuguang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Meiling Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xufeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xuguang Zhang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, X., Ouyang, M. & Zhang, X. Small scale crowd behavior classification by Euclidean distance variation-weighted network. Multimed Tools Appl 75, 11945–11960 (2016). https://doi.org/10.1007/s11042-015-2670-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-015-2670-x

Keywords

Search

Navigation