Abstract
We propose a novel method of abnormal crowd behavior detection in surveillance videos. Mainly, our work focuses on detecting crowd divergence behavior that can lead to serious disasters like a stampede. We introduce a notion of physically capturing motion in the form of images and classify crowd behavior using a convolution neural network (CNN) trained on motion-shape images (MSIs). First, the optical flow (OPF) is computed, and finite-time Lyapunov exponent (FTLE) field is obtained by integrating OPF. Lagrangian coherent structure (LCS) in the FTLE field represents crowd-dominant motion. A ridge extraction scheme is proposed for the conversion of LCS-to-grayscale MSIs. Lastly, a supervised training approach is utilized with CNN to predict normal or divergence behavior for any unknown image. We test our method on six real-world low- as well as high-density crowd datasets and compare performance with state-of-the-art methods. Experimental results show that our method is not only robust for any type of scene but also outperform existing state-of-the-art methods in terms of accuracy. We also propose a divergence localization method that not only identifies divergence starting (source) points but also comes with a new feature of generating a ‘localization mask’ around the diverging crowd showing the size of divergence. Finally, we also introduce two new datasets containing videos of crowd normal and divergence behaviors at the high density.
Similar content being viewed by others
References
Illiyas, F.T., Mani, S.K., Pradeepkumar, A.P., Mohan, K.: Human stampedes during religious festivals: a comparative review of mass gathering emergencies in India. Int. J. Disaster Risk Reduct. 5, 10–18 (2013). https://doi.org/10.1016/j.ijdrr.2013.09.003
Batty, M., Desyllas, J., Duxbury, E.: The discrete dynamics of small-scale spatial events: agent-based models of mobility in carnivals and street parades. Int. J. Geogr. Inf. Sci. 17(7), 673–697 (2003). https://doi.org/10.1080/1365881031000135474
Dong, Y.-H., Liu, F., Liu, Y.-M., Jiang, X.-R., Zhao, Z.-X.: Emergency preparedness for mass gatherings: lessons of ‘12.31’ stampede in Shanghai Bund. Chin. J. Traumatol. 20(4), 240–242 (2017). https://doi.org/10.1016/j.cjtee.2016.08.005
Helbing, D., Mukerji, P.: Crowd disasters as systemic failures: analysis of the Love Parade disaster. EPJ Data Sci. 1(1), 1–40 (2012). https://doi.org/10.1140/epjds7
Johansson, A., Helbing, D., Al-Abideen, H.Z., Al-Bosta, S.: From crowd dynamics to crowd safety: a video-based analysis (2008) [Online]. http://arxiv.org/abs/0810.4590
Cong, Y., Yuan, J., Liu, J.: Sparse reconstruction cost for abnormal event detection. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 3449–3456 (2011). https://doi.org/10.1109/CVPR.2011.5995434
Wu, S., Wong, H.S., Yu, Z.: A bayesian model for crowd escape behavior detection. IEEE Trans. Circuits Syst. Video Technol. 24(1), 85–98 (2014). https://doi.org/10.1109/TCSVT.2013.2276151
Chen, C.Y., Shao, Y.: Crowd escape behavior detection and localization based on divergent centers. IEEE Sens. J. 15(4), 2431–2439 (2015). https://doi.org/10.1109/JSEN.2014.2381260
https://www.oasys-software.com/products/pedestrian-simulation/massmotion/
Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1981), 185–203 (1981)
Brox, T., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. Comput. Vis.—ECCV 2004(4), 25–36 (2004). https://doi.org/10.1007/978-3-540-24673-2_3
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. Proc. Imaging Underst. Work. 130, 121–130 (1981)
Fortun, D., Bouthemy, P., Kervrann, C., Fortun, D., Bouthemy, P., Kervrann, C.: Optical flow modeling and computation : a survey. Comput. Vis. Image Underst. 134, 1–21 (2015)
Lawal, I.A., Poiesi, F., Anguita, D., Cavallaro, A.: Support vector motion clustering. IEEE Trans. Circuits Syst. Video Technol. 27(11), 1–1 (2016). https://doi.org/10.1109/TCSVT.2016.2580401
Cheriyadat, A.M., Radke, R.J.: Detecting dominant motions in dense crowds. IEEE J. Sel. Top. Signal Process. 2(4), 568–581 (2008). https://doi.org/10.1109/JSTSP.2008.2001306
Benabbas, Y., Ihaddadene, N., Djeraba, C.: Motion pattern extraction and event detection for automatic visual surveillance. Eurasip J. Image Video Process. 2011, 1–15 (2011)
Ali, S., Shah, M.: A Lagrangian particle dynamics approach for crowd flow simulation and stability analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, pp. 1–6 (2007). https://doi.org/10.1109/CVPR.2007.382977
Hu, M.H.M., Ali, S., Shah, M.: Learning motion patterns in crowded scenes using motion flow field. In: 2008 19th Int. Conf. Pattern Recognit., pp. 2–6 (2008). https://doi.org/10.1109/ICPR.2008.4761183
Solmaz, B., Moore, B.E., Shah, M.: Identifying behaviors in crowd scenes using stability analysis for dynamical systems. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2064–2070 (2012). https://doi.org/10.1109/TPAMI.2012.123
Chen, D.Y., Huang, P.C.: Motion-based unusual event detection in human crowds. J. Vis. Commun. Image Represent. 22(2), 178–186 (2011). https://doi.org/10.1016/j.jvcir.2010.12.004
Hu, W., Xiao, X., Fu, Z., Xie, D., Tan, T., Maybank, S.: A system for learning statistical motion patterns. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1450–1464 (2006). https://doi.org/10.1109/TPAMI.2006.176
Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work, pp. 1446–1453 (2009). https://doi.org/10.1109/CVPRW.2009.5206771
Kratz, L., Member, S., Nishino, K.: Spatio-temporal motion patterns in extremely crowded scenes. Analysis 34(5), 987–1002 (2012)
Cong, Y., Yuan, J., Tang, Y.: Video anomaly search in crowded scenes via spatio-temporal motion context. IEEE Trans. Inf. Forens. Secur. 8(10), 1590–1599 (2013). https://doi.org/10.1109/TIFS.2013.2272243
Wu, Y., Ye, Y., Zhao, C.: Coherent motion detection with collective density clustering. In: Proceedings of the 23rd ACM international conference on Multimedia—MM’15, 2015, vol. 1, no. 1, pp. 361–370. https://doi.org/10.1145/2733373.2806227
Ali, S., Shah, M.: A Lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–6 (2007)
Zitouni, M.S., Bhaskar, H., Dias, J., Al-Mualla, M.E.: Advances and trends in visual crowd analysis: a systematic survey and evaluation of crowd modelling techniques. Neurocomputing 186, 139–159 (2015). https://doi.org/10.1016/j.neucom.2015.12.070
Wu, S., Moore, B.E., Shah, M.: Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2054–2060 (2010)
Wang, X., Gao, M., He, X., Wu, X., Li, Y.: An abnormal crowd behavior detection algorithm based on fluid mechanics. J. Comput. 9(5), 1144–1149 (2014). https://doi.org/10.4304/jcp.9.5.1144-1149
Wang, X., Yang, X., He, X., Teng, Q., Gao, M.: A high accuracy flow segmentation method in crowded scenes based on streakline. Opt.—Int. J. Light Electron Opt. 125(3), 924–929 (2014). https://doi.org/10.1016/j.ijleo.2013.07.166
Mehran, R., Moore, B.E., Shah, M.: A streakline representation of flow in crowded scenes. Lect. Notes Comput. Sci. (incl. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinf.) 6313 LNCS(PART 3), 439–452 (2010). https://doi.org/10.1007/978-3-642-15558-1_32
Pereira, E.M., Cardoso, J.S., Morla, R.: Long-range trajectories from global and local motion representations. J. Vis. Commun. Image Represent. 40, 265–287 (2016). https://doi.org/10.1016/j.jvcir.2016.06.020
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Huang, S., Huang, D., Zhou, X.: Learning multimodal deep representations for crowd anomaly event detection. Math. Probl. Eng. (2018). https://doi.org/10.1155/2018/6323942.
Xu, J., Ren, D., Zhang, L., Zhang, D.: Patch group based bayesian learning for blind image denoising. Lect. Notes Comput. Sci. (incl. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinf.) 10116 LNCS, 79–95 (2017). https://doi.org/10.1007/978-3-319-54407-6_6
Li, X., Shen, H., Li, H., Zhang, L.: Patch matching-based multitemporal group sparse representation for the missing information reconstruction of remote-sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9(8), 3629–3641 (2016). https://doi.org/10.1109/JSTARS.2016.2533547
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: EEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), pp. 886–893 (2005)
Barnich, O., Van Droogenbroeck, M.: ViBe: A universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011). https://doi.org/10.1109/TIP.2010.2101613
Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work, no. 2, pp. 935–942 (2009). https://doi.org/10.1109/CVPRW.2009.5206641
Shadden, S.C., Lekien, F., Marsden, J.E.: Definition and properties of Lagrangian coherent structures from finite-time Lyapunov exponents in two-dimensional aperiodic flows. Phys. D Nonlinear Phenom. 212(3–4), 271–304 (2005). https://doi.org/10.1016/j.physd.2005.10.007
Lipinski, D., Mohseni, K.: A ridge tracking algorithm and error estimate for efficient computation of Lagrangian coherent structures. Chaos Interdiscip. J. Nonlinear Sci. 20(1), 017504 (2010). https://doi.org/10.1063/1.3270049
Peikert, R., Schindler, B., Carnecky, R.: Ridge surface methods for the visualization of Lagrangian coherent structures. Semseg.Org [Online]. http://www.semseg.org/results/_files/2012-ICFD-PeikertEtAl-RidgeSurfaceMethods.pdf%5Cnpapers3://publication/uuid/7F60AE35-CBAF-4E7B-B59F-23A81EADD827
Zeiler, M.D., et al.: On rectified linear units for speech processing New York University, USA Google Inc., USA University of Toronto, Canada. In: IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP 2013), pp. 3–7 (2013)
Krausz, B., Bauckhage, C.: Loveparade 2010: automatic video analysis of a crowd disaster. Comput. Vis. Image Underst. 116(3), 307–319 (2012). https://doi.org/10.1016/j.cviu.2011.08.006
Wu, S., Moore, B.E., Shah, M.: Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2054–2060 (2010)
U. C. F. Crowd Dataset. https://www.crcv.ucf.edu/data/crowd.php
U. M. N. Crowd Dataset. http://mha.cs.umn.edu/proj_events.shtml#crowd
2009 Dataset, PETS. http://www.cvg.reading.ac.uk/PETS2009/a.html
NGSIM. https://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm
Wu, S., Yang, H., Zheng, S., Su, H., Fan, Y., Yang, M.H.: Crowd behavior analysis via curl and divergence of motion trajectories. Int. J. Comput. Vis. 123(3), 1–21 (2017). https://doi.org/10.1007/s11263-017-1005-y
Direkoglu, C.: Abnormal crowd behavior detection using motion information images and convolutional neural networks. IEEE Access 8, 80408–80416 (2020). https://doi.org/10.1109/ACCESS.2020.2990355
Ravanbakhsh, M., Nabi, M., Sangineto, E., Marcenaro, L., Regazzoni, C., Sebe, N.: Abnormal event detection in videos using generative adversarial nets. In: Proceedings—International Conference on Image Processing, ICIP, vol. 2017, pp. 1577–1581 (2018). https://doi.org/10.1109/ICIP.2017.8296547
Ravanbakhsh, M., Nabi, M., Mousavi, H., Sangineto, E., Sebe, N.: Plug-and-play CNN for crowd motion analysis: an application in abnormal event detection. In: Proceedings—2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018, vol. 2018, pp. 1689–1698 (2018). https://doi.org/10.1109/WACV.2018.00188
Ahmed, F., Tarlow, D., Batra, D.: Optimizing expected intersection-over-union with candidate-constrained CRFs. In: Proc. IEEE Int. Conf. Comput. Vis., vol. 2015 Inter, pp. 1850–1858 (2015). https://doi.org/10.1109/ICCV.2015.215
Acknowledgments
We thank Dr. Yasir Salih for sharing high-density crowd dataset and valuable suggestions on motion estimation at high-density crowd. The MassMotion crowd simulation software is supported by the Center for Intelligent Signal for Imaging Research (CISIR) under PO Number 3920089787/30.10.2017.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Farooq, M.U., Saad, M.N.M. & Khan, S.D. Motion-shape-based deep learning approach for divergence behavior detection in high-density crowd. Vis Comput 38, 1553–1577 (2022). https://doi.org/10.1007/s00371-021-02088-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02088-4