近年來公共安全議題不斷，人群異常行為偵測在電腦視覺領域中變成了相當重要的研究議題，自動的人群異常行為偵測可以幫助監視人員快速察覺特殊事件的發生以減少事件處理的延遲時間。於此論文中我們提出一種基於前景靜態模型的演算法來偵測人群聚集的異常行為，此方法利用前景遮罩與稠密光流法來估算瞬間的人群靜止程度，接著利用漏桶模型來累計瞬間的人群靜止程度以獲得長期的人群靜止程度，最後透過閥值分析即可獲得人群聚集的警示。實驗結果顯示出我們所提出的方法能夠有效於偵測人群聚集事件與定位聚集位置，且於公開的人群聚集影片中測試準確度達84%，

The abnormal crowd behavior detection is an important research topic in computer vision to improve the response time of critical events. In this thesis, we introduce a novel method to detect and locate the crowd gathering in surveillance videos. The proposed foreground stillness model is based on the foreground object mask and the dense optical flow to measure the instantaneous crowd stillness level. Further, we obtain the long-term crowd stillness level by the break bucket model, and the crowd gathering behavior can be detected by the threshold analysis. Experimental results indicate that our proposed approach can detect and locate crowd gathering events, and it is capable of distinguishing between standing and walking crowd. The experiments in realistic scenes with 84% accuracy for detection of gathering frames show that our method is effective for crowd gathering behavior detection.

[1] A. Prati, R. Vezzani, M. Fornaciari, and R. Cucchiara, “Intelligent Video Surveillance as a Service,” in Intelligent Multimedia Surveillance - Current Trends and Research, ed. P. K. Atrey, M. Kankanhalli, A. Cavallaro, pp. 17-36, Springer-Verlag Berlin, 2013.
[2] N. G. L. Vigne, S. S. Lowry, J. A. Markman, A. M. Dwyer, “Evaluating the Use of Public Surveillance Cameras for Crime Control and Prevention,” COPS office, [Online]. Available: http://www.urban.org/sites/default/files/alfresco/publication-pdfs/412403-Evaluating-the-Use-of-Public-SurveillanceCameras-for-Crime-Control-and-Prevention.PDF.
[3] N. Jenkins, “North American Security Camera Installed Base to Reach 62 Million in 2016,” IHS Markit Insight, September 01, 2016, [Online]. Available: https://technology.ihs.com/583114/north-american-security-camera-installed-baseto-reach-62-million-in-2016.
[4] “The Video Surveillance Report 2017,” IFSEC Global, [Online]. Available: https://www.ifsecglobal.com/video-surveillance-report-2017/.
[5] J. x. Wang, “Research and Implementation of Intrusion Detection Algorithm in Video Surveillance,” in Proc. International Conference on Audio, Language and Image Processing(ICALIP), Shanghai, pp. 345-348, 2016.
[6] R. Firdous, S. Aherrao, B. Narute, and V. Borkar, “Fault Detection and Analysis of Kapton Film in Fuel Cells using Image Processing,” in Proc. International Conference on Computing, Analytics and Security Trends (CAST), Pune, pp. 567-571, 2016.
[7] J. Wen, Z. Lai, Z. Ming, W. K. Wong, and Z. Zhong, “Directional Gaussian Model for Automatic Speeding Event Detection,” IEEE Transactions on Information Forensics and Security, vol. 12, no. 10, pp. 2292-2307, May 2017.
[8] C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, “Robust Video Surveillance for Fall Detection Based on Human Shape Deformation,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, no. 5, pp. 611-622, May 2011.
[9] K. Lin, S. C. Chen, C. S. Chen, D. T. Lin, and Y. P. Hung, “Abandoned Object Detection via Temporal Consistency Modeling and Back-Tracing Verification for Visual Surveillance,” IEEE Transactions on Information Forensics and Security, vol. 10,
no. 7, pp. 1359-1370, July 2015.
[10] J. C. Sanmiguel, L. Caro and J. M. Martinez, “Pixel-based Colour Contrast for Abandoned and Stolen Object Discrimination in Video Surveillance,” in Electronics Letters, vol. 48, no. 2, pp. 86-87, January 2012.
[11] B. Zhan, D. N. Monekosso, P. Remagnino, S. A. Velastin, L.-Q. Xu, “Crowd Analysis: a Survey,” Machine Vision and Applications, vol. 19, pp. 345-357, October 2008.
[12] T. Li, H. Chang, M. Wang, B. Ni, R. Hong and S. Yan, “Crowded Scene Analysis: a Survey,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 25, no. 3, pp. 367-386, March 2015.
[13] 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, ed. P. K. Atrey, M. Kankanhalli, A. Cavallaro, pp. 17-36, Springer-Verlag Berlin, 2013.
[14] S. M. Khan and M. Shah, “Tracking Multiple Occluding People by Localizing on Multiple Scene Planes,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 31, no. 3, pp. 505-519, March 2009.
[15] R. Mehran, A. Oyama and M. Shah, “Abnormal Crowd Behavior Detection using Social Force Model,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, pp. 935-942, 2009.
[16] G. Xiong, X. Wu, Y. L. Chen and Y. Ou, “Abnormal Crowd Behavior Detection Based on the Energy Model,” in Proc. IEEE International Conference on Information and Automation, Shenzhen, pp. 495-500, 2011.
[17] G. Xiong, J. Cheng, X. Wu, Y. L. Chen, Y. Ou, Y. Xu, “An Energy Model Approach to People Counting for Abnormal Crowd Behavior Detection,” Neurocomputing, vol. 83, pp. 121-135, 2012.
[18] J. Ferryman and A. Shahrokni, “PETS2009: Dataset and Challenge,” in Proc.12th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Snowbird, UT, pp. 1-6, 2009.
[19] C. Stauffer and W. E. L. Grimson, “Adaptive Background Mixture Models for Real-time Tracking,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, vol. 2, pp. 252, 1999.
[20] Z. Zivkovic, F. V. D. Heijden, “Efficient Adaptive Density Estimation per Image Pixel for the Task of Background Subtraction,” Pattern Recognition Letters, vol. 27, pp. 773-780, 2006.
[21] A. Yilmaz, O. Javed and M. Shah, “Object Tracking: A Survey,” ACM Computing Surveys, vol. 38, No. 4, Article 13, December 2016.
[22] Y.-Q. Jiang, P. Zhang, S.C.Wong and R.-X. Liu, “A Higher-order Macroscopic Model for Pedestrian Flows,” Physica A: Statistical Mechanics and its Applications, vol. 389, pp. 4623-4635, November 2010.
[23] B. K. P. Horn and B. G. Schunck, “Determining Optical Flow,” Artificial Intelligence, vol. 17, pp. 185-203, August 1981.
[24] B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” in Proc. International Joint Conference on Artificial Intelligence, Vancouver, BC, Canada, pp. 674-679, 1981.
[25] Gunnar Farnebäck, “Two-Frame Motion Estimation Based on Polynomial Expansion,” in Proc. Scandinavian Conference on Image Analysis, pp. 363-370, June 2003.
[26] I. Saleemi, L. Hartung and M. Shah, “Scene understanding by statistical modeling of motion pattern,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, pp. 2069-2076, 2010.
[27] S. Ali and M. Shah, “Floor Fields for Tracking in High-Density Crowd Scenes,” in Proc. European Conference on Computer Vision, Marseille, France, pp. 1-14, 2008.
[28] L. Kratz and K. Nishino, “Spatio-Temporal Motion Pattern Modeling of Extremely Crowded Scenes,” The 1st International Workshop on Machine Learning for Vision based Motion Analysis, Marseille, France, 2008.
[29] L. Kratz and K. Nishino, “Anomaly Detection in Extremely Crowded Scenes Using Spatio-temporal Motion Pattern Models,” in Proc. Conference on Computer Vision and Pattern Recognition, Miami, FL, pp. 1446-1453, 2009.
[30] S. Vishwakarma and A. Agrawal, “A Survey on Activity Recognition and Behavior Understanding in Video Surveillances,” The Visual Computer, vol. 29, pp. 983–1009, October 2013.
[31] J. C. Silveira Jacques Junior, S. R. Musse and C. R. Jung, “Crowd Analysis Using Computer Vision Techniques,” in IEEE Signal Processing Magazine, vol. 27, no. 5, pp. 66-77, September 2010.
[32] T. Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, vol. 27, pp. 861-874, 2006.