為了維持社會的治安，到處可見的攝影機已經成為街道巷弄中不可或缺的風景，一方面嚇阻了犯罪，一方面也提升民眾的安全感，以及提供亡羊補牢的方法已備不時之需。但是，一直由監視者全天候地盯著監控畫面不只耗時耗力，往往也缺乏效率，所以擁有即時異常偵測的智慧型監控系統儼然是一門重要的課題。
雖然現在智慧型監控系統已經不是新的技術，但以往的異常偵測系統為提升準確度通常需要預先嚴謹地定義異常行為或是複雜的物體特徵和大量的計算。監督式學習的監控系統需要透過人為的參與來定義異常事件，費時費力且無法達到全自動的效果，但若完全由機器學習來做異常偵測的非監督式學習監控系統雖然省去了人力介入但卻很難包含到所有的異常事件，以致錯失了重點畫面，所以若能結合以上兩種系統的優點，並且在異常事件出現時提醒可能的異常原因才是智慧型監控系統關鍵的成功之道。
故本論文提出一個混合式監督學習的即時自動智慧型監控系統，擷取移動物體局部的軌跡特徵，在非監督式學習部分使用一般的分群演算法輔以特殊的結構將軌跡特徵分類，作為其後監督式學習分類器的異常偵測訓練資料，來實現全自動的效果，此種架構稱為混合式監督學習法。若偵測到異常行為還能告知可能的異常原因，實際運作時，操作人員若發現自動異常偵測有錯誤時，可以透過人為的參與來標記修正判讀結果，並反饋資料給系統作更正的依據，如此一來不但可以節省監控者的精力，也能提升異常偵測的準確度。

In order to maintain social security, everywhere the camera has become an integral part of the street scenery. On the one hand it deters crime, but it is also to enhance the people's sense of security, and to provide a method to remedy the situation have been a rainy day. However, those who have been staring at the monitor screen all day by the monitor not only time-consuming, often inefficient. So have real time anomaly detection of intelligent surveillance system is an important issue. Although intelligent surveillance system is not a new technology, but the previous systems usually need to pre-defined the abnormal behavior or require complex object features and lots of calculations to achieve high accuracy. Supervised learning monitoring system needs to define the abnormal event through human involvement, time-consuming and cannot achieve fully automatic. Unsupervised learning surveillance system which using machine learning, while avoid human intervention, but could not contain all the unusual events that missed the focus screen. If we can combine the advantages of these two systems and show the abnormal reason when anomaly happened will be the most critical success for the intelligent surveillance system. In this thesis, we presents a hybrid supervised learning real time automatic intelligent surveillance system. Capturing local features of moving objects’ trajectory. Using common clustering algorithms combined with a special structure which is the unsupervised part to train the supervised learning classifier for automatic abnormal motion detection. This kind of structure which combining the supervised learning part and unsupervised learning part is called hybrid supervised learning. When anomaly detected, the system can show the abnormal reason. If there are some error results, the supervisor can also remark the results and feedback information to the system as a basis for correction. In this way the supervisor can not only save energy, but also can improve the accuracy of abnormal detection.

[1] “台北市政府警察局網站 新建置之監視器成效,” [Online]Available access on 7/22: http://www.tcpd.taipei.gov.tw/ct.asp?xItem=69589798 &ctNode=67726&mp=10800G.
[2] “台北市社區鄰里監視系統在犯罪預防上成效評估之研究,” [Online]Available access on 7/22: https://www.cib.gov.tw/Upload/Files /778.pdf
[3] H. Li, Y. Zhang, M. Yang, Y. Men, and H. Chao, “A rapid abnormal event detection method for surveillance video based on a novel feature in compressed domain of HEVC,” in Proceedings of the IEEE International Conference on Multimedia and Expo, Chengdu, China, pp. 1-6, 2014.
[4] J. G. Ko and J. H. Yoo, “Rectified Trajectory Analysis Based Abnormal Loitering Detection for Video Surveillance, ” in Proceedings of the First International Conference on Artificial Intelligence, Modelling and Simulation, Daejeon, Korea, pp. 289-293, 2013.
[5] J. Ajmera and C. Wooters, “A robust speaker clustering algorithm, ” in Proceedings of IEEE International Workshop on Automatic Speech Recognition and Understanding, Beijing, China, pp. 411-416, 2003.
[6] F. Porikli and T. Haga, “Event detection by eigenvector decomposition using object and frame features, ” in Proceedings of the International Workshop on Computer Vision and Pattern Recognition, Washington, DC, pp. 114-114, 2004.
[7] D. Zhang, D. Gatica-Perez, S. Bengio, and I. McCowan, “Semi-supervised adapted hmms for unusual event detection,” in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Reno, MN, vol. 1, pp. 611-618, 2005.
[8] T. Xiang and S. Gong, “Video behaviour profiling and abnormality detection without manual labelling, ” in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Beijing, China, pp. 1238-1245, 2005.
[9] F. Jiang, Y. Wu, and A. K. Katsaggelos, “Abnormal event detection from surveillance video by dynamic hierarchical clustering, ” in Proceedings of the IEEE International Conference on Image Processing, San Antonio, TX, pp. V-145-V-148, 2007.
[10] L. Cui, K. Li, J. Chen, Z. Li “Abnormal Event Detection in Traffic Video Surveillance Based on Local Features,” in Proceedings of the 4th International Congress on the Image and Signal Processing, Shanghai, China , vol. 1, pp 362-366, 2011.
[11] Y. Zou, G. Shi, H. Shi, and Y. Wang, “Image sequences based traffic incident detection for signaled intersections using HMM, ” in Proceedings of the 9th IEEE International Conference on Hybrid Intelligent Systems, Shenyang, China, pp. 257-261, 2009.
[12] C. Piciarelli and G. L. Foresti, “On-line trajectory clustering for anomalous events detection, ” Pattern Recognition Letters, vol. 27, no.11, pp. 1835-1842, 2006.
[13] C. T. Hsieh, S. B. Hsu, C. C.Han and K, C, Fan, “Abnormal Event Detection Using Trajectory Features,” Journal of Information Technology and Applications, vol. 5, no. 1, pp. 21-27, 2011.
[14] N. Kiryati, T. R. Ravivt, Y. Ivanchenko, and S. Rochel “Real-time Abnormal Motion Detection in Surveillance Video, ” in Proceedings of the 19th IEEE International Conference on Pattern Recognition, Tampa, FL, 2008
[15] T. Sandhan, T. Srivastava, A. Sethi and Y. C. Jin “Unsupervised learning approach for abnormal event detection in surveillance video by revealing infrequent patterns, ” in Proceedings of the 28th IEEE International Conference on Image and Vision Computing, pp. 494-499, Wellington, New Zealand, 2013
[16] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking, ” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, pp 246-252, 1999.
[17] P. K. Tra, K. Pong, and R. Bowden. “An improved adaptive background mixture model for real-time tracking with shadow detection,” Video-Based Surveillance Systems, vol. 3, no. 5, pp. 135-144, 2002.
[18] Z. Zivkovic and F. van der Heijden, “Efficient adaptive density estimation per image pixel for the task of background subtraction, ” Pattern recognition letters, vol. 27, no. 7, pp. 773-780, 2006.
[19] R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using MATLAB, Pearson Education, Upper Saddle River, NJ, 2004.
[20] K. Suzuki, I. Horiba, and N. Sugie, “Linear-time connected-component labeling based on sequential local operations, ” Computer Vision and Image Understanding, vol. 89, no.1, pp. 1-23, 2003.
[21] G. R. Bradski, “Computer vision face tracking for use in a perceptual user interface,” Intel Technology Journal, vol. 2, no.2, pp. 12-21, 1998.
[22] K. Fukunaga, “Introduction to Statistical Pattern Recognition,” Academic Press, San Diego, CA, 1990.
[23] D. Comaniciu, V. Ramesh and P. Merr, “Real-time tracking of non-rigid objects using mean shift,” in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Hilton Head Island, SC, vol. 2, pp. 142-149, 2000.
[24] D. Comaniciu and P. Meer, “Robust analysis of feature spaces: color image segmentation, ” in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, pp. 750-755, 1997.
[25] I. Slobodan “Tracking and Detection in Computer Vision Mean Shift Tracking,“ [Online] (Available access on 7/22): http://campar.in.tum.de/twiki/pub/Chair/TeachingWs12TDCV/mean_shift.pdf
[26] G. R. Bradski, “Computer vision face tracking for use in a perceptual user interface, ” Intel Technology Journal, vol. 2, pp. 12-21, 1998
[27] J. B. MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability. California, vol. 1, no. 14, pp 281-297, 1967.
[28] G. Cybenko, “Approximation by superpositions of a sigmoidal function, ” Mathematics of Control, Signals and Systems, vol. 2, no. 4, pp. 303-314, 1989.
[29] C. C. Chiang and H. C. Fu, “A variant of second-order multilayer perceptron and its application to function approximations, ” in Proceedings of the IEEE International Joint Conference on Neural Networks, Baltimore, MD, vol. 3, pp. 887-892, 1992.
[30] K. Y. Huang, L. C. Shen, K. J. Chen, and M. C. Huang, “Multilayer perceptron learning with particle swarm optimization for well log data inversion, ” in Proceedings of the IEEE International Joint Conference on Neural Networks, Brisbane, Australia, pp. 1-6, 2012.
[31] S. S. Huang, “A Tracking Approach to the Same Moving Object across Non-overlapping Multi-cameras,” Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2012.
[32] H. W. Huang, “Abnormal Moving Object Detection under Various Environments Using Self-Organizing Incremental Neural Networks,” Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2012.
[33] ”connected component,” [Online] (Available access on 7/22): http://users.ics.aalto.fi/ahonkela/dippa/node41.html.
[34]“WEKA”, [Online] (Available access on 7/22): http://www.cs.waikato.ac.nz/ml/ weka/.