Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures

Machine Vision and Applications - Tập 28 - Trang 361-371 - 2017
Kaelon Lloyd1, Paul L. Rosin1, David Marshall1, Simon C. Moore2
1School of Computer Science, Cardiff University, Cardiff, UK
2Violence and Society Research Group, Applied Clinical Research and Public Health, School of Dentistry, Cardiff University, Cardiff, UK

Tóm tắt

The severity of sustained injury resulting from assault-related violence can be minimised by reducing detection time. However, it has been shown that human operators perform poorly at detecting events found in video footage when presented with simultaneous feeds. We utilise computer vision techniques to develop an automated method of abnormal crowd detection that can aid a human operator in the detection of violent behaviour. We observed that behaviour in city centre environments often occurs in crowded areas, resulting in individual actions being occluded by other crowd members. We propose a real-time descriptor that models crowd dynamics by encoding changes in crowd texture using temporal summaries of grey level co-occurrence matrix features. We introduce a measure of inter-frame uniformity and demonstrate that the appearance of violent behaviour changes in a less uniform manner when compared to other types of crowd behaviour. Our proposed method is computationally cheap and offers real-time description. Evaluating our method using a privately held CCTV dataset and the publicly available Violent Flows, UCF Web Abnormality and UMN Abnormal Crowd datasets, we report a receiver operating characteristic score of 0.9782, 0.9403, 0.8218 and 0.9956, respectively.

Tài liệu tham khảo

Ali, S., Shah, M.: A Lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2007) Bahrami, K., Kot, A.C.: A fast approach for no-reference image sharpness assessment based on maximum local variation. IEEE Signal Process. Lett. 21(6), 751–755 (2014) Bansal, A., Venkatesh, K.S.: People counting in high density crowds from still images. CoRR (2015). arXiv:1507.08445 Biswas, S., Gupta, V.: Abnormality detection in crowd videos by tracking sparse components. Mach. Vision Appl. 28, 35–48 (2016). doi:10.1007/s00138-016-0800-8 Breiman, L.: Random Forests. Mach. Learn. 45(1), 5–32 (2001) Chen, C., Shao, Y., Bi, X.: Detection of anomalous crowd behavior based on the acceleration feature. IEEE Sensors J. 15(12), 7252–7261 (2015) Ryan, D., Denman, S., Fookes, C., Clinton, B., Sridharan, S.: Textures of optical flow for real-time anomaly detection in crowds. In: 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 230–235 (2011). doi:10.1109/AVSS.2011.6027327 Conte, D., Foggia, P., Percannella, G., Tufano, F., Vento, M.: Counting moving people in videos by salient points detection. In: Proceedings of International Conference on Pattern Recognition, pp. 1743–1746 (2010) Florence, C., Shepherd, J., Brennan, I., Simon, T.: Effectiveness of anonymised information sharing and use in health service, police, and local government partnership for preventing violence related injury: experimental study and time series analysis. BMJ (Clin. Res. ed.) 342, d3313 (2011) Florence, C., Shepherd, J., Brennan, I., Simon, T.R.: An economic evaluation of anonymised information sharing in a partnership between health services, police and local government for preventing violence-related injury. J. Int. Soc. Child Adolesc. Inj. Prev. 20(2), 108–114 (2014) Gao, Y., Liu, H., Sun, X., Wang, C., Liu, Y.: Violence detection using oriented violent flows. Image Vision Comput. 48–49(2015), 37–41 (2015) Gerrard, G., Thompson, R.: Two million cameras in the UK. CCTVImage 42(42), 10–12 (2011) Gracia, I.S., Suarez, O.D., Garcia, G.B., Kim, T.K.: Fast fight detection. PLoS ONE 10(4), 1–19 (2015) Grundmann, M., Kwatra, V., Essa, I.: Auto-directed video stabilization with robust L1 optimal camera paths. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 225–232 (2011) Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC–3(6), 610–621 (1973) Hasler, D., Suesstrunk, S.E.: Measuring colourfulness in natural images. Electron. Imag. 5007, 87–95 (2003) Hassner, T., Itcher, Y., Kliper-Gross, O.: Violent flows: real-time detection of violent crowd behavior. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 1–6 (2012) Immerkær, J.: Fast noise variance estimation. Comput. Vision Image Underst. 64(2), 300–302 (1996) Kratz, L., Nishino, K.: Tracking pedestrians using local spatio-temporal motion patterns in extremely crowded scenes. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 987–1002 (2012) Machado, P., Cardoso, A.: Computing aesthetics. In: de Oliveira, F.M. (ed.) Advances in Artificial Intelligence: 14th Brazilian Symposium on Artificial Intelligence, Proceedings, pp. 219–228. Springer, Berlin (1998) Mahadevan, V., Li, W., Bhalodia, V., Vasconcelos, N.: Anomaly detection in crowded scenes. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1975–1981 (2010) Marana, A., Costa, L.d., Lotufo, R., Velastin, S.: On the efficacy of texture analysis for crowd monitoring. In: Proceedings of the International Symposium on Computer Graphics, Image Processing, and Vision, SIBGRAPHI, pp. 354. IEEE Computer Society, Washington, DC (1998) Marques, J.S., Jorge, P.M., Abrantes, A.J., Lemos, J.M.: Tracking groups of pedestrians in video sequences. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 9, 101–101 (2003) Marsden, M., McGuinness, K., Little, S., O’Connor, N.E.: Holistic features for real-time crowd behaviour anomaly detection. IEEE International Conference on Image Processing, pp. 918–922 (2016) Matkovic, K., Neumann, L., Neumann, A., Psik, T., Purgathofer, W.: Global contrast factor—a new approach to image contrast. In: Computational Aesthetics in Graphics, Visualization and Imaging, pp. 159–168 (2005) Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behaviour detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 935–942 (2009) Metcalfe, E.: A surveillance society? In: Human Rights, April, p. 7. London: The Stationery Office Limited (2007) Raghavendra, R., Del Bue, A., Cristani, M., Murino, V.: Optimizing interaction force for global anomaly detection in crowded scenes. Proc. IEEE Int. Conf. Comput. Vision 1, 136–143 (2011) Rao, A.S., Gubbi, J., Rajasegarar, S., Marusic, S., Palaniswami, M.: Detection of anomalous crowd behaviour using hyperspherical clustering. In: International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1–8 (2014) Ribeiro, P.C., Audigier, R., Pham, Q.C.: RIMOC, a feature to discriminate unstructured motions: application to violence detection for video-surveillance. Comput. Vision Image Underst. 144, 121–143 (2016) Sivarajasingam, V., Shepherd, J.P., Matthews, K.: Effect of urban closed circuit television on assault injury and violence detection. Injury Prev. 9(4), 312–316 (2003) Voorthuijsen, G.V., Hoof, H.V., Klima, M., Roubik, K., Bernas, M., Pata, P.: CCTV effectiveness study. In: Proceedings 39th Annual International Carnahan Conference on Security Technology, pp. 105–108 (2005) Wang, B., Bao, H., Yang, S., Lou, H.: Crowd density estimation based on texture feature extraction. J. Multimed. 8(4), 331–337 (2013) Wang, J., Xu, Z.: Spatio-temporal texture modelling for real-time crowd anomaly detection. Comput. Vision Image Underst. 144, 177–187 (2016) Wang, T., Snoussi, H.: Detection of abnormal events via optical flow feature analysis. Sensors 15(4), 7156–7171 (2015) 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) Xu, L., Gong, C., Yang, J., Wu, Q., Yao, L.: Violent video detection based on MoSIFT feature and sparse coding. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings, pp. 3538–3542 (2014) Yang, H., Cao, Y., Wu, S., Lin, W., Zheng, S., Yu, Z.: Abnormal crowd behavior detection based on local pressure model. In: Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC) Asia-Pacific, pp. 1–4 (2012) Yang, H., Shao, L., Zheng, F., Wang, L., Song, Z.: Recent advances and trends in visual tracking: a review. Neurocomputing 74(18), 3823–3831 (2011) Zhou, S., Shen, W., Zeng, D., Zhang, Z.: Unusual event detection in crowded scenes by trajectory analysis. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings, pp. 1300–1304 (2015)