近來國際上的公共安全問題頻傳，如何預防或發現異常事件變成很重要的一件議題，監視攝影機是關鍵的設備，監視人員不一定能一直專心在盯著多個監視設備，電腦視覺領域因而在此議題中扮演重要的角色，透過影像去偵測異常事件能夠減少人力需求與避免人為的失誤。此論文中我們提出一種基於動態與靜態模型之人群聚集與騷動偵測演算法，此方法使用改進後的背景消除演算法找出前景的人群，改進後的背景消除算法會依據前景區塊去更新背景模型，改善了人群長期滯留造成被誤認為背景的問題，之後再使用光流法來計算人群的靜止程度與動量累積，並利用漏桶模型來累積靜止程度用以判斷人群是否真為靜止狀態，如果有靜止狀態存在則使用群集算法對靜止狀態的人做群集，透過閥值分析偵測人群聚集的事件，當聚集事件發生後，再透過動量累積去偵測該人群是否發生騷動。實驗中使用公開的人群聚集影片做測試，在此實驗中準確度達97%。

The abnormal event detection become an important topic recently. This paper present a method to detect the crowd gathering and commotion event after crowd gathering. The proposed stillness model and motion model is based on improved background subtraction and optical flow. We construct a stillness level by the break bucket model and clustering the stillness level. The clustering data allow to detecting the gathering event by threshold analysis. Furthermore, motion model allow to detecting commotion after crowd gathering. In the experiment, we used the dataset of PET2009. The proposal method is verified by the experiment with 97% accuracy.

[1] N.G.L. Vigne, S.S. Lowry, J. Markman, Allison Dwyer (2011). Evaluating the Use of Public Surveillance Cameras for Crime Control and Prevention - A Summary [Online]. Available: https://www.urban.org/research /publication/evaluating-use-public-surveillance-cameras-crime-control-and-prevention-summary.
[2] A. Tavanai, M. Sridhar, F. Gu, A.G. Cohn, D.C. Hogg, “Carried Object Detection and Tracking Using Geometric Shape Models and Spatio-temporal Consistency,”, International Conference on Computer Vision Systems, 16-18 July 2013, pp. 223-233.
[3] Y. Qi, G. Huang, and Y. Wang, "Carrying Object Detection and Tracking Based on Body Main Axis," International Conference on Wavelet Analysis and Pattern Recognition, Vol. 3, Beijing, China, 2-4 Nov. 2007, pp. 1237-1240.
[4] W. Du, J. Piater, “Multi-camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration,” Asian Conference on Computer Vision, Tokyo, Japan 18-22 Nov. 2007, pp. 365-374.
[5] M. Liem, D.M. Gavrila, “Joint Multi-person Detection and Tracking from Overlapping Cameras,” Computer Vision and Image Understanding, Vol. 128, pp. 36-50, 2014.
[6] Y. Shi, Y. Gao, R. Wang, “Real-time abnormal event detection in complicated scenes,” International Conference on Pattern Recognition, Istanbul, Turkey, 23-26 Aug. 2010, pp. 3653-3656.
[7] Y. Cong, J. Yuan, J. Liu, “Sparse Reconstruction Cost for Abnormal Event Detection,”, IEEE Computer Vision and Pattern Recognition , 20-25 June 2011, pp. 3449-3456.
[8] A. Li, Z. Miao, Y. Cen, Q. Liang, “Abnormal Event Detection in Crowded Scenes using Sparse Representation,” IEEE International Conference on Acoustics, Speech and Signal Processing, Shanghai, China, 20-25 March 2016, pp. 1786-1790.
[9] V.J. Kok, M.K. Lim, C.S. Chan, “Crowd Behavior Analysis: A Survey,” Conference on Recent Advances in Electronics and Communication Technology International (ICRAECT), Bangalore, India, 16-17 March 2017, pp.169-178.
[10] T. Li, H. Chang, M. Wang, B. Ni, R. Hong, S. Yan, “Crowded Scene Analysis: A Survey”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 25, March 2015, pp. 367-386.
[11] S.A.M. Saleh, S.A. Suandi, H. Ibrahim, “Recent Survey on Crowd Density Estimation and Counting for Visual Surveillance,” Engineering Applications of Artificial Intelligence, Vol. 41, pp. 103-114, May 2015.
[12] T. Zhao, R. Nevatia, B. Wu, “Segmentation and Tracking of Multiple Humans in Crowded Environments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, pp. 1198-1211, July 2008.
[13] A.M. Cheriyadat, B.L. Bhaduri, R.J. Radke, “Detecting multiple moving objects in crowded environments with coherent motion regions,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops, Anchorage, AK, USA, 23-28 June 2008.
[14] N. Hussain, H.S.Md. Yatima, N.L. Hussaina, J.L.S. Yana, F. Haronb, “CDES: A pixel-based crowd density estimation system for Masjid al-Haram”, Safety Science, Vol. 49, pp. 824-833, July 2011.
[15] Z. Zhang, M. Li, “Crowd density estimation based on statistical analysis of local intra-crowd motions for public area surveillance,” Optical Engineering, Vol. 51, April 2012.
[16] A. Albiol, A. Albiol, J. Silla, “Statistical video analysis for crowds counting,” IEEE International Conference on Image Processing, Cairo, Egypt, 7-10 Nov. 2009, pp. 2572-2569.
[17] R. Khatoon, S.M. Saqlain, S. Bibi, “A Robust and Enhanced Approach for Human Detection in Crowd,” International Multitopic Conference, Islamabad, Pakistan, 13-15 Dec. 2012, pp. 170-178.
[18] M. Thida, Y. L. Yong, P. Climent-Pérez, H.-L. Eng, and P. Remagnino, “A Literature Review on Video Analytics of Crowded Scenes,” in Intelligent Multimedia Surveillance - Current Trends and Research, Springer-Verlag Berlin, 2013, pp.17-36.
[19] C.R. Wren, A. Azarbayejani, T. Darrell, A.P. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, pp. 780-785, Jul 1997.
[20] C. Stauffer, W.E.L. Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, USA, 23-25 June 1999, pp. 246-252.
[21] P. KaewTraKulPong, R. Bowden, “An Improved Adaptive Background Mixture Model for Realtime Tracking with Shadow Detection,” Video-Based Surveillance Systems, pp. 135-144, 2002.
[22] Z. Zivkovic, “Improved Adaptive Gaussian Mixture Model for Background Subtraction,” International Conference on Pattern Recognition, Vol. 2, Cambridge, UK, 26-26 Aug. 2004, pp 28-31.
[23] M. Heikkila, M. Pietikainen, ”A Texture-Based Method for Modeling the Background and Detecting Moving Objects,” IEEE Transactions on Pattern Analysis and Machine Intelligencem, Vol. 28, pp. 657-662, April 2006.
[24] D. Tsai, S. Lai, “Independent Component Analysis Based Background Subtraction for Indoor Surveillance,” Independent Component Analysis Based Background Subtraction for Indoor Surveillance, Vol. 18, pp. 158-167. Jan. 2009.
[25] O. Barnich, M.V. Droogenbroeck, “ViBe: A Universal Background Subtraction Algorithm for Video Sequences,” IEEE Transactions on Image Processing, Vol. 20, pp. 1709-1724, June 2011.
[26] B.K.P. Horn, B.G. Schunck, “Determining Optical Flow,” Artificial Intelligence, Vol. 17, pp. 185-203, Aug. 1981.
[27] D.J. FleetAllan, D. Jepson, Computation of Component Image Velocity from Local Phase Information,” International Journal of Computer Vision, Vol. 5, pp. 77-104, Aug. 1990.
[28] An Iterative Image Registration Technique with an Application to Stereo Vision,” International Joint Conference on Artificial Intelligence, Vol.2, Vancouver, BC, Canada, 24 – 28 Aug. 1981, pp 674-679.
[29] BF Buxton, H Buxton, “Computation of Optical Flow from the Motion of Edge Features in Image Sequences,” Image and Vision Computing, Vol. 2, pp. 59-75, May 1984.
[30] G. Farnebäck, “Two-Frame Motion Estimation Based on Polynomial Expansion,” Scandinavian Conference on Image Analysis, Gothenburg, Sweden, June 29 - July 02 2003, pp. 363-370.
[31] C. Harris, M. Stephens, “A Combined Corner and Edge Detector,” Alvey Vision Conference, 1988, pp. 147-151.
[32] C.Y. Liu, W.H. Liao, S.J. Ruan, “Crowd Gathering Detection Based on the Foreground Stillness Model,” IEICE Transactions on Information and Systems, pp. 1968-1971, July 2018.
[33] S. Suzuki, “Topological Structural Analysis of Digitized Binary mages by Border Following,” Computer Vision, Graphics, and Image Processing, Vol. 30, pp. 32-46, April 1985.
[34] T. Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, Vol. 27, pp. 861-874, June 2006.