在單攝影機有限的視頻監控中，使用大量重疊視野的攝影機覆蓋所有監控區域，在經濟與計算量等方面的考量下，已無法滿足廣域視頻監控的需求，因此近年來，非重疊視野多攝影機間移動物體的訊息傳遞與融合之研究已成為視頻監控領域中一個熱門的研究焦點。由於攝影機空間上的不連續，以及攝影機擺放角度與環境的不同，使得攝影機所拍攝到之物體因為外在條件因素的影響，進而造成物體比對上的困難。
在本篇論文，我們提出了一套整合系統，利用多個非重疊攝影機在不同亮度與角度之場景下，對物體進行廣域的長程追蹤。首先利用高斯混合背景建模與背景相減法，藉由陰影濾除與形態學等前處理後，進而提取出完整的前景物體，在追蹤部分，我們採用物體方框相交集的方式進行追蹤，而為了解決多個物體產生遮蔽的現象，我們結合了均值飄移與卡爾曼濾波器來進一步追蹤物體。在訓練的階段，藉由觀察者手動決定攝影機間的連結關係，透過數對已知配對且連續穿越不同攝影機視野的移動物體，統計並估算物體在穿越盲區時所需花費時間的高斯分布，進而得到物體在盲區所需花費的最大與最小時間；且利用亮度轉換函式取得不同視野間的亮度關係。而藉由訓練階段取得的亮度關係，對物體進行色彩校正後，擷取物體主要色彩做為物體外在特徵；接著，結合所估算出的時間關係，篩選出可能之物體，進行物體的特徵比對。
實驗的部份我們針對不同燈光、角度之場景進行分析，如室內走廊兩台攝影機、室外廣場兩台攝影機與室內走廊三台攝影機。我們提出的方法可以正確對移動物體進行識別，在室內走廊兩台攝影機的準確性是97.5％，在室外廣場兩台攝影機是94.4％，在室內走廊三台攝影機是94.6％，且整體畫面更新率，約15到30。

Due to single camera finite surveillance, using amount of overlapping multi-cameras to monitor region cannot satisfy the demand of wide region video surveillance in the considerations of economic and computational aspects. In recent years, messages transformation and fusion of moving object in non-overlapping multi-cameras have become popular research in video surveillance. The difficult part of target tracking in non-overlapping multi-cameras is the spatial discontinuous of cameras, the difference of setting angles and environment of camera. Besides, people are non-rigid objects; it’s difficult for cameras to do object matching because of the external condition and the inherent psychological impact.
In this thesis, we propose an integrated system by using non-overlapping multi-cameras for different brightness and viewing angles environments to long-range tack object. The first thing is to detect the moving objects by Gaussian Mixture Model (GMM), shadow removal and morphological etc. preprocess, and then adoptive blob intersection to track moving objects. In order to deal with the objects occlusion case , we use mean shift algorithm with Kalman filter to track these moving objects. In training phase, setting up the link relation of cameras manually by the observer and using a number of known pair objects across different field of views continuously to statistics and estimate the Gaussian distribution of travel time of the objects across blind region, and further obtain the maximum/minimum travel time of the object moving through the blind region, and using cumulative BTF to get the brightness relation between different field of views. After calibrating the color of object by BTF, extract the major color of object to be the feature of object ; then combine the estimated time relation to select likely objects and match the feature of objects.
For the experiment part, we use the scenes of different illustration and view angle to analyze, such as two cameras set indoor hallway and outdoor square, three cameras set indoor hallway. The system based on the proposed method can identify objects with the accuracy of 97.5% for two cameras set indoor hallway, 94.4% set outdoor square, and 94.6% for three cameras set indoor hallway. The frame rate is about 15 to 30 fps.

[1] R.Collins, A. Lipton, H. Fujiyoshi, and T. Kanade, “Algorithms for Cooperative Multisensor Surveillance,” Proceedings of the IEEE, vol. 89, no. 10, pp.1456-1477, 2001.
[2] Q. Cai and J.K. Aggarwal, “Tracking Human Motion in Structured Environments Using a Distributed-Camera System.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no.12, pp.1241-1247, 1990.
[3] W. Hassan, N. Bangalore, P. Birch, R. Young and C. Chatwin , “Object Tracking in a Multi Camera Environment,” IEEE International Conference on Signal and Image Processing Applications, pp. 289-294, 2011.
[4] X. C. He, S. C. Yuk, T. Luo, K. P. Chow, K.-Y. K. Wong and R. H. Y. Chung, “Human Face Tracking System with Multiple Non-overlapping Cameras,” Data Mining and Intelligent Information Technology Applications, pp. 176-179, 2011.
[5] D. Makris, T. Ellis, and J. Black, “Bridging the Gaps between Cameras,” Computer Vision and Pattern Recognition, vol. 2, pp. 205-210, 2004.
[6] B. Prosser, S. Gong, T. Xiang, “Multi-camera Matching using Bi-directional Cumulative Brightness Transfer Functions,” British Machine Vision Conference, 2008.
[7] C. Stauffer and K. Tieu, “Automated multi-camera planar tracking correspondence modeling,” Computer Vision and Pattern Recognition, 2003.
[8] S. Khan and M. Shah, “Consistent Labeling of Tracked Objects in Multiple Cameras,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no.10, pp. 1355-1360, 2003.
[9] S. Calderara, A. Prati, R. Vezzani1 and R. Cucchiara1, “Consistent Labeling for Multi-camera Object Tracking,” International conference on Image Analysis and Processing, pp.1206-1214, 2005.
[10] Y. Shan, H. S. Sawhney and R. Kumar, “Unsupervised Learning of Discriminative Edge Measures for Vehicle Matching between Non-overlapping Cameras,” Computer Vision and Pattern Recognition, vol. 1, pp. 894-901, 2005.
[11] Y. Shan, H. S. Sawhney and R. Kumar, “Vehicle Identification between Non-overlapping Cameras without Direct Feature Matching,” Proceedings of the Tenth IEEE International Conference on Computer Vision, vol. 1, pp. 378-385, 2005.
[12] Y. Guo, S. Hsu, Y. Shan, H. Sawhney and R. Kumar, “Vehicle Fingerprinting for Reacquisition & Tracking in Videos,” Computer Vision and Pattern Recognition, vol. 2, pp. 761-768, 2005.
[13] Y. Guo, Y. Shan, H. Sawhney and R. Kumar, “Prototype embedding and embedding transition for matching vehicles over disparate viewpoints,” Computer Vision and Pattern Recognition, pp.1-8, 2007.
[14] E. D. Cheng, C. Madden and M. Piccardi, “Mitigating the Effects of Variable Illumination for Tracking across Disjoint Camera Views,” Video and Signal Based Surveillance, 2006.
[15] E. D. Cheng and M. Piccardi, “Matching of Objects Moving across Disjoint Cameras,” International conference on Image Processing, pp. 1769-1772, 2006.
[16] E. D. Cheng and M. Piccardi, “Disjoint Camera Track Matching by an Illumination Effects Reduction and Major Colour Spectrum Histograms Representation Algorithm,” 2007.
[17] C. Madden and M. Piccardi, “Height Measurement as a Session-based Biometric for People Matching across Disjoint Camera Views,” Proceedings of Image and Vision Computing, 2005.
[18] A. Gilbert and R. Bowden, “Incremental Modeling of the Posterior Distribution of Objects for Inter and Intra Camera Tracking,” Proceedings of the European Conference on Computer Vision, 2006.
[19] A. Gilbert and R. Bowden, “Tracking objects across cameras by incrementally learning inter-camera colour calibration and patterns of activity,” Proceedings of the European Conference on Computer Vision, pp. 125-136, 2006.
[20] U. Park, A. K. Jain, I. Kitahara, K. Kogure and N. Hagita, “Visual search engine using multiple networked cameras,” International Conference on Pattern Recognition, vol. 3, pp. 1204-1207, 2006.
[21] O. Javed, Z. Rasheed, K. Shafique and M. Shah, “Tracking Across Multiple Cameras With Disjoint Views,” International Conference on Computer Vision, vol. 2, pp.952-957, 2003.
[22] O. Javed, Z. Rasheed, K. Shafique and M. Shah, “Modeling Inter-camera Space–time and Appearance Relationships for Tracking across Non-overlapping Views,” Computer Vision and Image Understanding, vol. 109, no.2, pp. 146-162, 2008.
[23] O. Javed, K. Shafiqu and M.Shah, “Appearance modeling for tracking in multiple non-overlapping cameras,” Computer Vision and Pattern Recognition, vol. 2, pp. 26-33, 2005.
[24] K. Jeong and C. Jaynes, “Object Matching in Disjoint Cameras using a Color Transfer Approach,” Special Issue of Machine Vision and Applications Journal, vol. 19, pp 5-6, 2008.
[25] Stauffer, Chris, “Adaptive Background Mixture Models for Real-time Tracking,” Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 1999.
[26] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1337-1342, 2003.
[27] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Second Edition, Addison-Wesley , Massachusetts, 1992.
[28] 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.
[29] F. Fazal, E. Guraya, PY Bayle, and F. A. Cheikh, “People Tracking via a Modified CAMSHIFT Algorithm,” Distributed Computing and Algorithms for Business, Engineering, and Sciences, 2009.
[30] F. Shimin, G. Qing, X. Sheng, and T. Fang, “Human Tracking Based on Mean Shift and Kalman Filter,” Artificial Intelligence and Computational Intelligence, vol. 3, pp. 518-522, 2009.
[31] “Kalman filter.” [Online] Available: http://en.wikipedia.org/wiki/Kalman_filter (accessed on March 14, 2013).
[32] G. Bishop and G. Welch, “An introduction to the Kalman filter,” in Universityy of Norh Carolina SIGGRAPH 2001 course notes, North Carolina, Course 8, 2001.
[33] Y. Ukrainitz and B. Sarel, “Mean Shift Theory and Applications,” [Online]Available:http://www.serc.iisc.ernet.in/~venky/SE263/slides/Mean-Shift-Theory.pdf (accessed on May 10, 2012).
[34] H.C. Liao and C.M. Lai, “Seamless Fusion of GPS-VT Service from Outdoor to Indoor Cameras” Awareness Science and Technology, pp.227-232, 2011.
[35] Ilie and G.Welch. “Ensuring color consistency across multiple cameras,” International Conference on Computer Vision, pp. 1268–1275, 2005.
[36] M.J. Swain, D.H. Ballard, “Indexing via Color Histograms,” Computer Vision, pp.390-393, 1990.
[37] E.D. Cheng and M. Piccardi, “Track Matching by Major Color Histograms Matching and Post-matching Integration”, International Conference on Image Analysis and Processing, pp.1148-1157, 2005.
[38] J.B. MacQueen, “Some Methods for classification and Analysis of Multivariate Observations,” Proceedings of fifth Berkeley Symposium on Mathematical Statistics and Probability, pp. 281-297, 1967.
[39] P.L. Mazzeo, L. Giove, G.M. Moramarco, P. Spagnolo and M. Leo, “HSV and RGB color histograms comparing for objects tracking among non-overlapping FOVs, using CBTF,” Advanced Video and Signal-Based Surveillance, pp. 498- 503, 2011.
[40] F. Jiang, Y. Wu, and A. K. Katsaggelos, “Abnormal Event Detection Based on Trajectory Clustering by 2-Depth Greedy Search,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Las Vegas, NV, USA, pp. 2129-2132, Mar. 2008.
[41] F. Jiang, Y. Wu, and A. K. Katsaggelos, “Abnormal Event Detection from Surveillance Video by Dynamic Hierarchical Clustering,” in Proceedings of 2007 IEEE International Conference on Image Processing, San Antonio, TX, USA, vol. 5, pp.145-148, Sep. 2007.