監視器系統隨著數位化的演變，許多技術被應用在這個領域。然而監視器也因應社會的變遷不斷的增設，而這樣的需求是無可必免的，主要是要嚇阻犯罪的發生和事後尋找犯罪的證據。
本論文主要目的是開發一個能夠掌握特定目標，在多監視器架設的區域內移動的系統。其中使用貝式模型來建構前景物件偵測的方法，將在監視畫面中在移動的物件抓取出來，並對感興趣的目標以Mean-Shift做追蹤。接著利用該目標出現的特定時間和地點，在下一個可能會出現的鏡頭找尋目標。找尋目標過程中，使用HSV色彩空間計算直方圖，再和目標比較其相似性。
研究中實驗的環境為戶外的監視器畫面。總共抓取三個鄰近的監視器。依照使用者選取的特定物件，對該物件的出現時間、地點和色彩特徵做追蹤，將此將追蹤的結果提供給監視人員。
本論文貢獻是提供能夠在多監視器系統追蹤特定目標的系統，並討論在實現本系統所遇到的問題， 以及解決的方法。

This thesis presents a system for tracking a target of interest across in multi-camera system. The analysis includes three parts: the first part is object segmentation by Bayesian model. The second part is object tracking. Using the object segmentation results and Mean-Shift to track the target we interested in current camera. Last part is collaborate information of each camera for tracking the target in multi-camera.
 Developing system provides users define the multi-camera system environment as they want, and video browsing interface lets users choose the interested target, finally showing the result helps them to know the target trajectories quickly. 
Experiment is used for three surveillance cameras in outdoor environment that recorded for one hour. And we will discuss the problems and solutions in realizing our system.

第一章 概論	1
1.1 研究背景	1
1.2 論文組織與架構	3
第二章 文獻探討	5
2.1 監控系統	5
2.2 型態學運算	7
2.3 顏色特徵比對	9
2.4 人物追蹤	14
2.4.1 前景物件偵測	14
2.4.2 Mean Shift	17
第三章 多攝影機人物追蹤	19
3.1 物件偵測	19
3.1.1 前景分割	20
3.1.2 物件標示與追蹤	28
3.2物件特徵比對	39
3.3多攝影機監控	42
第四章 系統介紹與實驗結果	54
4.1 系統流程與實測影片資料	54
4.2 系統介紹	57
4.3 系統結果討論	62
第五章 結論與未來展望	66
參考文獻	68
附錄-英文論文	72


圖目錄
圖 1 監控系統架構圖	5
圖 2 RGB色彩空間示意圖	9
圖 3 HSV色彩空間表示圖	10
圖 4 影像直方圖	12
圖 5 背景相減示意圖	15
圖 6 Mean Shift 運算過程圖	18
圖 7 前景分割流程圖	22
圖 8 斷開、閉合示意圖	25
圖 9 前景分割圖	28
圖 10 連通區域標示結果圖	30
圖 11 追蹤結果圖	32
圖 12 物件追蹤流程圖	33
圖 13 Mean Shift 示意圖	36
圖 14 Bhattacharyya Coefficient表示圖	38
圖 15 物件選取示意圖	40
圖 16 物件選取示意圖2	41
圖 17 物件比對示意圖	42
圖 18 攝影鏡頭設定表示圖	44
圖 19 攝影鏡頭設定表示圖2	44
圖 20 搜尋目標示意圖	46
圖 21 搜尋目標示意圖2	48
圖 22 搜尋物件標示示意圖	50
圖 23 使用者選擇目標示意圖	51
圖 24 搜尋過程結果圖	52
圖 25 系統流程圖	55
圖 26 攝影機之相對位置表示圖	56
圖 27 攝影機畫面圖	56
圖 28 設定檔編輯畫面	58
圖 29 瀏覽攝影機畫面介面圖	59
圖 30 選取物件介面圖	60
圖 31 追蹤結果介面圖	60
圖 32 結果介面圖	61
圖 33 系統結果資訊圖	61
圖 34 結果示意圖	62
圖 35 物件前後顏色不一示意圖	63

[1] Datong Chen, A.J. Bharucha, H.D. Wactlar. “Intelligent Video Monitoring to Improve Safety of Older Persons,” Proceeding IEEE Conference on Engineering in Medicine and Biology Society, pp.22-26, August 2007.
[2] Yuan-Fang Wang, Edward Y. Chang Ken P. Cheng. “A Video Analysis Framework for Soft Biometry Security Surveillance,” Proceedings of the third ACM international workshop on Video surveillance & sensor networks, pp.71-78, 2005.
[3] Tao Yang, Francine Chen, Don Kimber, Jim Vaughan, “Robust People Detection And Tracking In A Multi-Camera Indoor Visual Surveillance System,” Proceeding IEEE International Conference on Multimedia and Expo, pp.675-678, July 2007.
[4] Theo Gevers, Arnold W.M. Smeulders. “Color-based object recognition,” Proceeding ACM Conference on Image Analysis and Processing, Vol. 1, pp.319-326, 1997.
[5] Thomas Wiegand, Gary J.Sullivan, Gisle Bjontegaard,Luthra. “Overview of the H.264/AVC Video Coding Standard,” IEEE Transactions on Circuits and Systems for Video Technology, 2003.
[6] I. Haritaoglu, D. Harwood, and L. Davis. “W4: Real-time surveillance of people and their activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Issue 8, pp.809–830 , August 2000.
[7] C. Stauffer and W. Grimson. “Learning patterns of activity using real-time tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Issue 8, pp.747–757, August 2000.
[8] K. Karmann and A. V. Brandt. “Moving object recognition using an adaptive background memory,” Time-Varing Image Processing and Moving Object Recognition, Elsevier Science Publishers, Vol. 2, pp.289–296, 1990.
[9] D. Koller, J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao, and S. Russel. “Toward robust automatic traffic scene analysis in real-time,” Proceeding IEEE Conference on Pattern Recognition, pp.126–131 Vol. 1, 1994.
[10] C. Wren, A. Azarbaygaui, T. Darrell, and A. Paul Pentland. “Real-time tracking of the human body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.19, Issue 7, pp.780–785, July 1997.
[11] Chris Stauffer, W.E.L Grimson. “Adaptive background mixture models for real-time tracking,” Proceeding IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, p.205, 1999.
[12] Jwu-Shen Hu, Shr-Chi Jeng. A GMM-based Method For Dynamic Background Image Model Construction with Shadow Removal, Dissertations and Theses, Department of Electrical and Control Engineering, National Chiao Tung University, 2005.
[13] Jui-Hsiang Hsu, Moving Object Detection Using Gaussian Mixture Models, Dissertations and Theses, Department of Electrical Engineering, National Taiwan University of Science and Technology, January 2007.
[14] Mohammad Reza Javan, Seyed Mahdi Bouzari, Ahmad Salahi. “An Efficient Object Segmentation Algorithm for Surveillance Systems,” Proceeding IEEE Symposium on Signals, Circuits and Systems, Vol. 2, pp.1-4, 2007. 
[15] Liyuan Li, Weimin Huang, Irene Y. H. Gu, Qi Tian, “Foreground Object Detection from Videos Containing Complex Background,” Proceeding of the eleventh ACM international conference on Multimedia, pp.2-10, 2003.
[16] Comaniciu, D., Ramesh, V., Meer, P., “Real-time tracking of non-rigid objects using mean shift,” Proceeding IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, pp.13-15, June 2000.
[17] Rafael C. G, Richard E. W., Digital Image Processing, Pearson Prentice Hall, 2001.
[18] From Wikipedia, the free encyclopedia, http://en.wikipedia.org/wiki/Rgb , visit time: 15 November 2009.
[19] From Wikipedia, the free encyclopedia, http://en.wikipedia.org/wiki/HSL_and_HSV , visit time: 15 November 2009.
[20] Yaron Ukrainitz & Bernard Sarel. “Mean Shift Theory and Application” http://www.wisdom.weizmann.ac.il/~vision/courses/2004_2/files/mean_shift/mean_shift.ppt , visit time: 15 November 2009.