Skip to main content
SpringerLink
Log in

Spatial and temporal variations of feature tracks for crowd behavior analysis

  • Original Paper
  • Published:
Journal on Multimodal User Interfaces Aims and scope Submit manuscript

Abstract

The study of crowd behavior in public areas or during some public events is receiving a lot of attention in security community to detect potential risk and to prevent overcrowd. In this paper, we propose a novel approach for change detection, event recognition and characterization in human crowds. It consists of modeling time-varying dynamics of the crowd using local features. It also involves a feature tracking step which allows excluding feature points on the background and extracting long-term trajectories. This process is favourable for the later crowd event detection and recognition since the influence of features irrelevant to the underlying crowd is removed and the tracked features undergo an implicit temporal filtering. These feature tracks are further employed to extract regular motion patterns such as speed and flow direction. In addition, they are used as an observation of a probabilistic crowd function to generate fully automatic crowd density maps. Finally, the variation of these attributes (local density, speed, and flow direction) in time is employed to determine the ongoing crowd behaviors. The experimental results on two different datasets demonstrate the effectiveness of our proposed approach for early detection of crowd change and accurate results for event recognition and characterization.

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

Similar content being viewed by others

Notes

  1. http://www.nue.tu-berlin.de/menue/forschung/projekte/rlof.

  2. These results have to be considered carefully, because in [26] according to the number of frames, we noticed that the authors used one frame out of each three frames. Also, the original ground truths have been used in these results. These two factors may boost the results reported in the compared paper.

  3. Again, these comparisons have to be considered carefully, even though we mostly agree with the compared methods on the ground truth labels, and on the evaluation strategy, we cannot ensure that the algorithms run on the same dataset because of the random selection of training/testing samples.

References

  1. University of minnesota crowd activity dataset. http://www.mha.cs.umn.edu/Movies/Crowd-Activity-All.avi

  2. Albiol A, Silla MJ, Albiol A, Mossi JM (2009) Video analysis using corner motion statistics. In: IEEE International Workshop on PETS, pp 31–37

  3. Albiol A, Silla MJ, Albiol A, Mossi JM (2009) Video analysis using corners motion analysis. In: International Workshop on Performance Evaluation of Tracking and Surveillance, pp 31–38

  4. Ali S, Shah M (2007) A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis, 7th edn. In: CVPR, pp 1–6

  5. Almeida IR, Jung CR (2013) Change detection in human crowds. In: Conference on Graphics, Patterns and Images, p 26

  6. Briassouli A, Kompatsiaris I (2011) Spatiotemporally localized new event detection in crowds. In: Proceedings of the IEEE International Conference on ICCV Workshops, pp 928–933

  7. Butenuth M, Burkert F, Schmidt F, Hinz S, Hartmann D, Kneidl A, Borrmann A, Sirmacek B (2011) Integrating pedestrian simulation, tracking and event detection for crowd analysis. In: ICCV Workshops, pp 150–157

  8. Cermeno E, Mallor S, Siguenza J (2013) Learning crowd behavior for event recognition. In: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), pp 1–5

  9. Chan A, Morrow M, Vasconcelos N (2009) Analysis of crowded scenes using holistic properties. In: Proceedings of the 11th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, PETS-09

  10. Chan AB, Morrow M, Vasconcelos N (2009) Analysis of crowded scenes using holistic properties. In: IEEE International Workshop on PETS

  11. Chen DY, Huang PC (2011) Motion-based unusual event detection in human crowds. J Visual Commun Image Represent 22(2):178–186

    Article  Google Scholar 

  12. Dee H, Hogg D (2004) Detecting inexplicable behaviour. In: Proceedings of the British Machine Vision Conference, The British Machine Vision Association, pp 477–486

  13. Ferryman J, Shahrokni A (2009) Pets 2009: dataset and challenge. In: PETS, pp 1–6

  14. Fradi H, Dugelay JL (2012) Low level crowd analysis using frame-wise normalized feature for people counting. In: IEEE International Workshop on Information Forensics and Security

  15. Fradi H, Dugelay J-L, (2013) Crowd density map estimation based on feature tracks. In: MMSP 15th International Workshop on Multimedia Signal Processing, September 30–October 2, 2013, Pula, Italy

  16. Fradi H, Zhao X, Dugelay JL (2013) Crowd density analysis using subspace learning on local binary pattern. In: ICME 2013, IEEE International Workshop on Advances in Automated Multimedia Surveillance for Public Safety

  17. Garate C, Bilinski P, Bremond F (2009) Crowd event recognition using HOG tracker. In: Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS-Winter), Snowbird, UT, États-Unis, pp 1–6

  18. Ihaddadene N, Djeraba C (2008) Real-time crowd motion analysis. In: IEEE ICPR, pp 1–4

  19. Kaltsa V, Briassouli A, Kompatsiaris I, Strintzis MG (2012) Timely, robust crowd event characterization. In: ICIP, pp 2697–2700

  20. Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model. In: CVPR, pp 935–942

  21. Polus A, Schofer JL, Ushpiz A (1983) Pedestrian flow and level of service. J Transp Eng 109:46–56

    Article  Google Scholar 

  22. Rosten E, Porter R, Drummond T (2010) Faster and better: a machine learning approach to corner detection. IEEE Trans Pattern Anal Mach Intell 32:105–119

    Article  Google Scholar 

  23. Saxena S, Brémond F, Thonnat M, Ma R (2008) Crowd behavior recognition for video surveillance. In: Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS ’08. Springer, Berlin, Heidelberg, pp 970–981

  24. Senst T, Eiselein V, Evangelio RH, Sikora T (2011) Robust modified l2 local optical flow estimation and feature tracking. In: IEEE Workshop on Motion and Video Computing (WMVC), pp 685–690

  25. Senst T, Eiselein V, Sikora T (2012) Robust local optical flow for feature tracking. Trans Circuits Syst Video Technol 22(9):1377–1387

    Article  Google Scholar 

  26. Shi Y, Gao Y, Wang R (2010) Real-time abnormal event detection in complicated scenes. In: Proceedings of the 2010 20th International Conference on Pattern Recognition, ICPR ’10. DC, USA, IEEE Computer Society, Washington, pp 3653–3656

  27. Tomasi C, Kanade T (1991) Detection and tracking of point features. Technical report CMU-CS-91-132, CMU

  28. Xu T, Peng P, Fang X, Su C, Wang Y, Tian Y, Zeng W, Huang T. (2012) Single and multiple view detection, tracking and video analysis in crowded environments. In: AVSS. IEEE Computer Society, pp 494–499

  29. Zhang Y, Qiny L, Yao H, Xu P, Huang Q (2013) Beyond particle flow: bag of trajectory graphs for dense crowd event recognition. In: ICIP

Download references

Author information

Authors and Affiliations

  1. EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France

    Hajer Fradi & Jean-Luc Dugelay

Authors
  1. Hajer Fradi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jean-Luc Dugelay
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hajer Fradi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fradi, H., Dugelay, JL. Spatial and temporal variations of feature tracks for crowd behavior analysis. J Multimodal User Interfaces 10, 307–317 (2016). https://doi.org/10.1007/s12193-015-0179-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12193-015-0179-2

Keywords

Search

Navigation