攝影機的數量隨著居家保全、公共場所維安、道路監控甚至國家安全相關應用的要求下大幅增加，視訊監控系統的監視畫面保持清晰以及視野正確(correct field of view, FOV)的畫面是非常重要的，而監視人員面對大量的畫面往往無法即時察覺是否拍攝到無效的畫面，有鑑於此視訊監控系統必需擁有自動偵測攝影機異常的能力以即時排除各種異常狀況。本論文提出一個不受移動物件及搖晃影響之攝影機異常偵測演算法，以馬可夫隨機場尋找不受移動物件影響之顯著區域並在內擷取全面性(holistic)特徵以做線上異常偵測，在不被移動物件和搖晃影響下判斷目前畫面是否保持清晰以及正確的視野，過程中以線上卡爾曼濾波器去除時間軸上的雜訊，並以有限狀態機累積時間軸上特徵值的資訊做最後的判斷。實驗結果證明提出的方法相較於其他攝影機異常偵測演算法更為穩定，且在可容許的延遲時間內大幅降低誤報率同時擁有更快的執行速度。

The number of cameras is greatly increased due to security, road monitoring, and home-care demanded. Images remained clear and correct field of view (FOV) are very important for video surveillance, and yet a large-scale system installed with a huge amount of cameras is hard to maintain. This paper presents a camera anomaly detection method based on holistic feature analysis over time in salient regions for automatically online determination. The salient regions are constructed from a Markov Random Field framework, which is modeled by pixel-based accumulated movement. There are a handful of holistic features extracted from salient regions, and an online Kalman filter is introduced for recursive smoothing uncertain features. A finite state machine, then, is further designed for real-time event detection. The proposed method yields a robust solution for reducing noise produced from real-world complexities. Experiments are conducted on a set of recorded videos simulating various challenging situations. The test results show that the camera anomaly detection method is superior to other methods in terms of precision rate, false alarm rate, and time complexity.

摘要 .................................................... i
英文摘要 ............................................... ii
誌謝 .................................................. iii
目錄 ................................................... iv
表目錄 ................................................. vi
圖目錄 ................................................ vii
第1章 簡介 .............................................. 1
1.1研究背景 ............................................. 1
1.2研究動機 ............................................. 3
1.3研究目的 ............................................. 3
1.4研究方法 ............................................. 4
1.5論文架構 ............................................. 6
第2章 文獻探討 .......................................... 7
2.1影像品質判斷 ......................................... 7
2.2移動偵測 ............................................. 9
2.3異常偵測 ............................................ 10
2.4顯著區域 ............................................ 12
第3章 顯著區域 ......................................... 14
3.1 Variance Map ....................................... 15
3.2 Graph Cut .......................................... 22
第4章 特徵值擷取與異常事件判斷 ......................... 29
4.1影像品質特徵擷取 .................................... 29
4.1.1 Salient Region Based 邊緣強度 .................... 30
4.1.2 Salient Region Based 標準差 ...................... 32
4.1.3 Salient Region Based 區域標準差 .................. 33
4.2 位移特徵擷取 ....................................... 35
4.3 線上卡爾曼濾波器 ................................... 37
4.4特徵值更新與異常事件判斷 ............................ 39
第5章 實驗討論 ......................................... 44
5.1模擬影片實驗 ........................................ 44
5.1.1異常事件模擬 ...................................... 46
5.1.2正常易誤判事件模擬 ................................ 54
5.2實際影片實驗 ........................................ 60
5.3執行時間分析 ........................................ 69
第6章 結論 ............................................. 73
參考文獻 ............................................... 75

[1]A. Aksay, A. Temizel and A. E. Cetin, "Camara tamper detection using wavelet analysis for video surveillance," Proc. IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 558-562, 2007.
[2]E. Ribnick, S. Atev, O. Masoud, N. Papanikolopoulos and R. Voyles, "Real-time detection of camera tampering," Proc. IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 10-15, 2006.
[3]P. Gil-Jimenez, R. Lopez-Sastre, P. Siegmann, J. Acevedo-Rodriguez and S. Maldonado-Bascon, "Automatic control of video surveillance camera sabotage," Proc. Nature Inspired Problem-Solving Methods in Knowledge Engineering, pp. 222-231, 2007.
[4]U. Engelke, M. Kusuma, H. J. Zepernick and M. Caldera, "Reduced-reference metric design for objective perceptual quality assessment in wireless imaging," Proc. Signal Processing: Image Communication, vol. 24, pp. 525-547, 2009.
[5]G. Cheng and L. Cheng, "Reduced reference image quality assessment based on dual derivative priors," Proc. Electronics Letters, vol. 45, pp. 937 - 939, 2009.
[6]B. Thompson and C. Stone, "Kalman filters," Student Tutorials of COSC453 in 2007, 2002.
[7]J. D. Schutter, J. D. Geeter, T. Lefebvre and H. Bruyninckx, "Kalman filters: a tutorial," Coden JRNAD, vol. 40, pp. 52-59, 1999.
[8]G. Welch and G. Bishop, "An introduction to the kalman filter," Tech. Rep., Department of computer science of TR 95-041, 2006.
[9]Y. Boykov, O. Veksler and R. Zabih, "Fast approximate energy minimization via graph cuts," IEEE Transactions on Pattern Analysis And Machine Intelligence, vol. 23, pp. 1222-1239, 1999.
[10]Y. Boykov and O. Veksler, "An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision," IEEE Transactions on Pattern Analysis And Machine Intelligence, vol. 26, pp. 1124-1137, 2004.
[11]D. V. Weken, M. Nachtegael and E. Kerre, "Combining neighbourhood-based and histogram similarity measures for the design of image quality measures," Image and Vision Computing, vol. 25, pp. 184-195, 2007.
[12]P. Shivakumara, B. S. Anami and G. H. Kumar, "A new structural no-reference rule based blur metric for classification of blurred home photos," ECTI Transactions on Electrical Eng., Electronics and Communications, vol. 7, pp. 73-81, 2009.
[13]A. Elgrnmal and R. Duraiswami, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance," Proceedings of the IEEE, vol. 90, pp. 1151-1163, 2002.
[14]C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 2001.
[15]A. Saglam and A. Temizel, "Real-time adaptive camera tamper detection for video surveillance," Proc. IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 430-435, 2009.
[16]V. Chandola, A. Banerjee and V. Kumar, "Anomaly detection for discrete sequences: a survey," IEEE Transactions on Knowledge and Data Engineering, 2010.
[17]X. Xu, "Sequential anomaly detection based on temporal-difference learning: Principles, models and case studies," Applied Soft Computing, vol. 10, pp. 859-867, 2010.
[18]A. Banerjee, V. Chandola, V. Kumar and J. Srivastava, "Anomaly detection: a tutorial," Proc. SIAM International Conference on Data Mining, 2008.
[19]V. Chandola, A. Banerjee and V. Kumar, "Anomaly detection: a survey," acm computing surveys, Proc. ACM Comput. Surv., vol. 41, pp. 15:1-15:58, 2009.
[20]N. Jacobs, N. Roman and R. Pless, "Toward fully automatic geo-location and geo-orientation of static outdoor cameras," Proc. IEEE Workshop on Applications of Computer Vision, 2008.
[21]C. Ridder, O. Munkelt and H. Kirchner, "Background estimation and foreground detection using kalman-filter," Proc. Int. Conf. Recent Advances in Mechatronics, pp. 193-199, 1995.
[22]C. Stauffer and W. E. L. Grimson, "Learning patterns of activity using real-time tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 747-757, 2000.
[23]D. R. Magee, "Tracking multiple vehicles using foreground, background and motion models," Image and Vision Computing, vol. 22, pp. 143-155, 2004.
[24]C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 246-252, 1999.
[25]R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt and L. Wixson, "A system for video surveillance and monitoring," Tech. Rep., The Robotics Institute, Carnegie Mellon University CMU-RI-TR-00-12, 2000.
[26]R. Achanta, F. Estrada, P. Wils and S. Süsstrunk, "Salient region detection and segmentation," Proc. International Conference on Computer Vision Systems, pp. 66-75, 2008.
[27]W. Skarbek and A. Koschan, "Colour image segmentation - a survey -," Tech. rep., Institute for Technical Informatics, Technical University of Berlin, 1994.
[28]Y. Zhai, Z. Rasheed and M. Shah, "Semantic classification of movie scenes using finite state machines," IEE Proceedings - Vision, Image, and Signal Processing, vol. 152, pp. 896-901, 2005.