Abstract
This paper presents a real-time abnormal situation detection method in crowded scenes based on the crowd motion characteristics including the particle energy and the motion directions. The particle energy is determined by computation of optical flow derived from two adjacent frames. The particle energy is modified by multiplying the foreground to background ratio. The motion directions are measured by mutual information of the direction histograms of two neighboring motion vector fields. Mutual information is used to measure the similarity between two direction histograms derived from three adjacent frames. The direction probability distribution for each frame can be directly estimated from the direction histogram by dividing the entries by the total number of the vectors. A metric for all the video frames is computed using normalized mutual information to detect the abnormal situation. Both the modified particle energy and mutual information of direction histograms contribute to the detection of the abnormal events. Furthermore, the dynamic abnormality is measured to detect the dynamical movement associated with severe change in the motion state according to the spatio-temporal characteristics. In experiments, we will show that the proposed method detects the abnormal situations effectively.
Similar content being viewed by others
References
Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–6 (2007). doi:10.1109/CVPR.2007.382977
Andrade, E.L., Blunsden, S., Fisher, R.B.: Hidden markov models for optical flow analysis in crowds. In: ICPR ’06, Proceedings of the 18th International Conference on Pattern Recognition, vol. 01, pp. 460–463. IEEE Computer Society, Washington, DC (2006). doi:10.1109/ICPR.2006.621
Baker, S., Matthews, I.: Lucas-kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56(3), 221–255 (2004)
Barron, J., Fleet, D., Beauchemin, S., Burkitt, T.A.: Performance of optical flow techniques. In: Proceedings CVPR ’92, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 236–242 (1992). doi:10.1109/CVPR.1992.223269
Black, M.J, Anandan, P.: A framework for the robust estimation of optical flow. In: Proceedings of Fourth International Conference on Computer Vision, pp. 231–236. IEEE press, New York (1993)
Bouguet, J.Y.: Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corp. 5 (2001)
Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., Schnorr, C.: Variational optical flow computation in real time. IEEE Trans. Image Process. 14(5), 608–615 (2005a)
Bruhn, A., Weickert, J., Kohlberger, T., Schnörr, C.: Discontinuity-preserving computation of variational optic flow in real-time. In: Scale Space and PDE Methods in Computer Vision, pp. 279–290. Springer, Berlin (2005b)
Duong, T., Bui, H., Phung, D., Venkatesh, S.: Activity recognition and abnormality detection with the switching hidden semi-markov model. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, vol. 1, pp. 838–845 (2005). doi:10.1109/CVPR.2005.61
Hu, M., Ali, S., Shah, M.: Detecting global motion patterns in complex videos. In: ICPR 2008, 19th International Conference on Pattern Recognition, pp. 1–5 (2008). doi:10.1109/ICPR.2008.4760950
Ihaddadene, N., Djeraba, C.: Real-time crowd motion analysis. In: 19th International Conference on Pattern Recognition (ICPR 2008), pp. 1–4, IEEE, Tampa (2008). doi:10.1109/ICPR.2008.4761041
Jaynes, E.T.: Information theory and statistical mechanics. Phys. Rev. 106(4), 620 (1957)
Li, J., Gong, S., Xiang, T.: Global behaviour inference using probabilistic latent semantic analysis. In: BMVC’08, p. 10
Li, W., Wu, X., Zhao, H.A.: New techniques of foreground detection, segmentation and density estimation for crowded objects motion analysis. JIP 19, 190–200 (2011)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, vol. 2, pp. 674–679. Morgan Kaufmann Publishers Inc., San Francisco (1981). http://dl.acm.org/citation.cfm?id=1623264.1623280
Ma, R., Li, L., Huang, W., Tian, Q.: On pixel count based crowd density estimation for visual surveillance. In: IEEE Conference on Cybernetics and Intelligent Systems, vol. 1, pp. 170–173 (2004). doi:10.1109/ICCIS.2004.1460406
Marana, A., Velastin, S., Costa, L., Lotufo, R.: Estimation of crowd density using image processing. In: IEE Colloquium on Image Processing for Security Applications (Digest No.: 1997/074), pp. 11/1–11/8 (1997). doi:10.1049/ic:19970387
Marana, A.N., Cavenaghi, M.A., Ulson, R.S., Drumond, F.L.: Real-time crowd density estimation using images. Adv. Vis. Comput. 3804, 355–362 (2005)
Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: CVPR 2009, IEEE Conference on Computer Vision and Pattern Recognition, pp. 935–942 (2009). doi:10.1109/CVPR.2009.5206641
Nam, Y.: Crowd flux analysis and abnormal event detection in unstructured and structured scenes. Multimed. Tools Appl. pp. 1–29 (2013a)
Nam, Y.: Dr. yunyoung nam-google sites (2013b). https://sites.google.com/site/yynams/crowd-activity
Nam, Y., Rho, S., Park, J.: Intelligent video surveillance system: 3-tier context-aware surveillance system with metadata. Multimed. Tools Appl. 57, 315–334 (2012). doi:10.1007/s11042-010-0677-x
Nam, Y., Rho, S., Park, J.: Inference topology of distributed camera networks with multiple cameras. Multimed. Tools Appl. 67(1), 289–309 (2013). doi:10.1007/s11042-012-0997-0
Papoulis, A., Pillai, S.U.: Probability, random variables, and stochastic processes. Tata McGraw-Hill Education, New Delhi (2002)
Pavón, J., Gómez-Sanz, J., Fernández-Caballero, A., Valencia-Jiménez, J.J.: Development of intelligent multisensor surveillance systems with agents. Robot Auton. Syst. 55(12), 892–903 (2007). doi:10.1016/j.robot.2007.07.009
Pluim, J., Maintz, J., Viergever, M.: Mutual-information-based registration of medical images: a survey. IEEE Trans. Med. Imaging 22(8), 986–1004 (2003). doi:10.1109/TMI.2003.815867
Rahmalan, H., Nixon, M., Carter, J.: On crowd density estimation for surveillance. In: The Institution of Engineering and Technology Conference on Crime and Security, pp. 540–545 (2006)
UMN: Umn: Unusual crowd activity dataset of university of minnesota (2013). http://mha.cs.umn.edu/Movies/Crowd-Activity-All.avi
Valera, M., Velastin, S.: Intelligent distributed surveillance systems: a review. In: IEE Proceedings on Vision, Image and Signal Processing, vol. 152(2), pp. 192–204 (2005). doi:10.1049/ip-vis:20041147
Van-Trees, H.: Detection, Estimation, and Modulation Theory. Part I. Wiley, New York (2001)
Wang, X., Ma, X., Grimson, W.E.L.: Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models. IEEE Trans. Pattern Anal. Mach. Intell. 31, 539–555 (2009). doi:10.1109/TPAMI.2008.87, http://dl.acm.org/citation.cfm?id=1512152.1512378
Wu, S., Moore, B., Shah, M.: Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2054–2060 (2010). doi:10.1109/CVPR.2010.5539882
Yang, H., Nam, Y., Cho, W.D., Choi, Y.J.: Adaptive background modeling for effective ghost removal and robust left object detection. In: 2nd International Conference on Information Technology Convergence and Services (ITCS), pp. 1–6 (2010). doi:10.1109/ITCS.2010.5581283
Zhang, D., Gatica-Perez, D., Bengio, S., McCowan, I.: Semi-supervised adapted hmms for unusual event detection. In: CVPR 2005. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 611–618 (2005). doi:10.1109/CVPR.2005.316
Zhong, H., Shi, J., Visontai, M.: Detecting unusual activity in video. In: CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. II-819–II-826 (2004). doi:10.1109/CVPR.2004.1315249
Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: 17th International Conference on (ICPR’04) Proceedings of the Pattern Recognition, vol. 2, pp. 28–31. IEEE Computer Society, Washington, DC (2004). doi:10.1109/ICPR.2004.479
Acknowledgments
They would like to thank Dianne Greco for previewing our manuscript.
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported by the Soonchunhyang University Research Fund and also supported by the International Collaborative R&D Program of the Ministry of Knowledge Economy (MKE), the Korean government, as a result of Development of Security Threat Control System with Multi-Sensor Integration and Image Analysis Project, 2010-TD-300802-002.
Rights and permissions
About this article
Cite this article
Nam, Y., Hong, S. Real-time abnormal situation detection based on particle advection in crowded scenes. J Real-Time Image Proc 10, 771–784 (2015). https://doi.org/10.1007/s11554-014-0424-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-014-0424-z