近年來隨著犯罪等社會事件層出不窮，「安全」的議題越來越受現代人的重視，也造就監視器系統的蓬勃發展與普及。日常生活中，我們可以在住家、機場、車站、百貨公司等場所看到監視系統林立，但是傳統的攝影已經無法符合現代人對於便捷的渴望，所以智慧化的監視系統因此孕育而生。
物體追蹤在電腦視覺領域是一個很熱門的議題。尤其在擁擠的環境中，監視畫面的遮蔽問題往往是物體追蹤的一大挑戰。傳統的平均位移法無法隨著物體的放大或縮小隨之改變，這個缺點大大影響了追蹤的效能，這幾年開始有許多人想辦法加以改進，而本篇論文提出的方法是結合平均位移法和卡爾曼濾波器進行物體的追蹤，這個方法可以有效地隨著物體的縮放或旋轉進行物體模型的調整。此外，我們結合上述的追蹤演算法和合作追蹤觀念來解決物體遮蔽問題。過去很多研究都是利用多台攝影機同時進行物體追蹤，以解決遮蔽問題，但是多台攝影機需要付出昂貴的成本和安裝上的麻煩，因此我們希望利用單一攝影機就能解決遮蔽問題。假定在多人的環境中，本系統中每個被追蹤的物體都會同時得到其他人的位置及顏色統計資訊，利用這些相對關係我們就可以偵測是否有那個物體被遮擋，然後找出是誰遮擋了該物體因而當被遮擋物體再次出現在畫面時，我們可以重新加以追蹤，此方法可以成功地解決單一鏡頭多人可能產生的遮蔽問題。
最後，我們進行了相當多的實驗來驗證我們所提出的追蹤系統效能較佳，也能夠成功解決多人的遮蔽問題。

[1] Horn BKP, Schunck BG: Determining Optical Flow. Artif Intelligence; 17:185-203, 1981.
[2] V.P. Kumar, T. Poggio, “Learning-based approach to real time tracking and analysis of faces”, Automatic Face and Gesture Recognition, 2000. Proceedings Fourth IEEE International Conference on, pp. 96-101, March 2000.
[3] A. Tannenbaum, “Robust Control and Tracking”, Decision and Control, 2000. Proceedings Of the 39 th IEEE Conference on, Vol. 3, pp. 2539-2544, Dec. 2000.
[4] S. Avidan, ”Support Vector Tracking”, Computer Vision and Pattern Recognition, 2001. Proceedings Of the 2001 IEEE Computer Society Conference on, Vol. 1, pp. 184-191, Dec. 2001.
[5] A. D. Jepson, D. J. Fleet ,and T. F. El-Maraghi, “Robust Online Appearance Models for Visual Tracking ”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 25, No. 10, pp. 1296-1311, October 2003.
[6] Y. Wang, J. Ostermann, and Y. Q. Zhang, “Video Processing and Communications”, 2001.
[7] L. Jongwoo, K. David, “Tracking humans using prior and learned representations of shape and appearance”, IEEE International Conference on Automatic Face and Gesture Recognition.2004.
[8] A.D. Jepson, D. J. Fleet, T.F. El-Maraghi, “Robust on-line appearance models for visual tracking”, IEEE Conference on Computer Vision and Pattern Recognition, Volume1, pp. 415–422, 2001.
[9] C. Guaragnella, E. Di Sciascio, “Object Oriented Motion Estimation by Sliced-Block Matching Algorithm”, Pattern Recognition, 2000. Proceedings 15 th International Conference on, Vol. 3, pp. 857-860, Sept. 2000.
[10] L. Raffo, M.P. Zizola, “Block-Matching Evaluation in digital architectures for motion estimation”, Circuits and Systems, 2000. Proceedings. The 2000 IEEE International Symposium on, Vol.4, pp. 305-308, May 2000.
[11] Wen-Nung Lie, Wei-Chuan Hsiao, “Content-Based Video Retrieval based on object motion trajectory”, Multimedia Signal Processing, 2002 IEEE Workshop on, pp. 237-240, 2002.
[12] N. Papanikolopoulos, P. Khosla, T. Kanade, “1993. Visual tracking of a moving target by a camera mounted on a robot: A combination of control and vision.”, IEEE Trans. Robot. Automat. 9, pp.14–15, 1993.
[13] D. Comaniciu, V. Ramesh , P. Meer, “Kernel-based object tracking”, in Proc. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-575, May 2003.
[14] Isard, M., MacCormick, J.: Brammble: A Bayesian Multiple Blob Tracker. In: Proc. IEEE International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 34–41, 2001.
[15] Bose, B., Wang, X., Grimson, E.: Detecting and Tracking Multiple Interacting Objects Without Class-Specifc Models. Technical report MIT-CSAIL-TR-2006-027 Massachusetts Institute of Technology, 2006.
[16] Okuma, K., Taleghani, A., DeFreitas, N., Little, J., Lowe, D.: A Boosted Particle Filter. In: Proc. European Conference on Computer Vision, 2004.
[17] Fukunaga, K., “Introduction to Statistical Pattern Recognition”, 2nd Edition. Academic Press, New York, 1990.
[18] Cheng, Y., “Mean shift, mode seeking, and clustering” , IEEE Trans. Pattern Anal. Machine Intell., 17:790-799, 1995.
[19] D. Comaniciu, P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24 n.5, pp. 603-619, May2002.
[20] R.T. Collins, "Mean-shift blob tracking through scale space," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.2, pp.234-240, 18-20 June 2003
[21] D. Comaniciu, V. Ramesh, and P. Meer,“Real-Time Tracking of Non-Rigid Objects using Mean Shift,”IEEE Computer Vision and Pattern Recognition, Vol. 2, pp. 142-149, 2000.
[22] R. E. Kalman. 1960. “A New Approach to Linear Filtering and Prediction Problems,” Transaction of the ASME, Journal of Basic Engineering, pp. 35-45, March 1960.
[23] R. Harpaz and R. Haralick, “The EM algorithm as a lower bound optimization technique”, CUNY Ph.D. Program in Computer Science Technical Reports, pp. 1-14, 2006.
[24] Zhuo-Lin Jiang, Shao-Fa Li, Dong-Fa Gao ,” An adaptive mean shift tracking method using multiscale images”, Wavelet Analysis and Pattern Recognition, ICWAPR '07. International Conference on, Vol3, pp. 1060-1066, 2007.
[25] http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/
[26] K. Bernardin, A. Elbs, and R. Stiefelhagen, "Multiple object tracking performance metrics and evaluation in smart room environment," in Proceedings of the 6th IEEE International Workshop on Visual Surveillance (VS '06), pp. 53-68, Graz, Austria, May 2006.