隨著科技的發展以及居家安全的意識上漲，越來越多場所架設監控系統，以確保私人及公共場所的安全。因此本論文提出一套由靜態攝影機及動態攝影機組成的主動式監控系統，使用靜態攝影機偵測出入口，判斷是否有物體進出，並由動態攝影機分別對環境中的物體進行追蹤。
在本論文的重點在於攝影機與攝影機之間的溝通及對應，以及分派適當的攝影機追蹤物體。當動態攝影機在追蹤物體時，利用已知的Pan值，及Tilt值將物體的位置定位。並且計算物體的顏色直方圖（Color Histogram）將不同的物體作區分。在分派動態攝影機方面，本論文是採用「物體的座標位置」及「物體移動向量和攝影機角度」來決定追蹤的攝影機，當系統計算出其他攝影機具較佳的追蹤結果，便會轉換其他台攝影機繼續追蹤。最後將結果儲存在資料庫中。
經由實驗結果，本論文可以應用在多攝影機為基礎的監控系統上，同時分派多台攝影機追蹤多個物體，讓少數的攝影系統可以同時監控更廣大的場景。當物體由一個空間移動到另一個空間時，也可以及時分派攝影機去追蹤物體。

With the development of science and home security awareness is rising, more and more places set up monitoring system to ensure the security of public and private spaces. This paper proposes an active surveillance system, which comprises a static camera and a number of PTZ camera. Using static cameras to detect object, and PTZ cameras to track.
In this paper we present the method that how camera and camera correspond to each other, and how dominant cameras assign tasks to track object. When a better tracking result is calculated, the system will switch from the original tracking camera to each camera which captures more clear images, and save the calculated data to the database.
According to the experimental results, this paper can be applied to a multi-camera based surveillance system, which assign multiple cameras to track multiple objects. As a consequence, fewer monitoring systems are needed to simultaneously monitor the wider space. When an object move from one area to another area, this system can assign cameras to track the object immediately, ensuring the security of the monitored space.

[1] J. Black, T. Ellis, “Multi camera image tracking.” Image and Vision Computing, vol.24, no.11, pp. 1256-1267, 2006.
[2] A. D. Bimbo, F. Dini, G. Lisanti, F. Pernici, “Exploiting distinctive visual landmark maps in pan-tilt-zoom camera network.” Computer Vision and Image Understanding, vol.114, no.6, pp. 611-623, 2010.
[3] F. Z. Qureshi, D. Terzopoulos, “Planning ahead for PTZ camera assignment and handoff.” Proceedings of the Third ACM/IEEE International Conference on Distributed Smart Cameras, pp. 1-8, 2009.
[4] L. Liyuan, H. Weimin, Y. H. G. Irene, T. Qi, “Foreground object detection from videos containing complex background.” Proceedings of the eleventh ACM international conference on MultiMedia, pp. 2-10, 2003.
[5] A. Bhattacharyya, “On a measure of divergence between two statistical populations defined by their probability distributions.” Bulletin of the Calcutta Mathematical Society, vol.35, pp. 99-109, 1943.
[6] K. Jiman, K. Daijin, “Probabilistic camera hand-off for visual surveillance.” Proceeding of the IEEE/ACM International Conference on Distributed Smart Cameras, pp. 1-8, 2009.
[7] S. Calderara, A. Prati, R. Cucchiara, R. Cucchiara, “Consistent labeling for multi-camera object tracking.” International conference on Image Analysis and Processing, vol.3617, pp. 1206-1214, 2005.
[8] S. Calderara, R. Cucchiara, A. Prati, “Bayesian-competitive consistent labeling for people surveillance.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, no.2, pp. 354-360, 2008.
[9] J. Y. Choi, J. W. Choi, Y. K. Yang, “Improved tracking of multiple vehicles using invariant feature-based matching.” Proceeding of the International Conference on Pattern Recognition and Machine Intelligence, pp. 649-656, 2007.
[10] Y. Soh, H. I. Kang, D. Kim, J. Song, “New methods for 3-D measurement for PTZ camera control on a flat road surface.” International Conference on Intelligent Computation Technology and Automation, vol.2, pp. 773-776, 2010.
[11] D. G. Lowe, “Distinctive image features from scale-invariant keypoints.” International Journal of Computer Vision, vol.60, no.2, pp. 91-110, 2004.
[12] H. Bay, A. Ess, T. Tuytelaars, L. V. Gool, “SURF: speeded up robust features.” Computer Vision and Image Understanding, Vol.110, No.3, pp. 346-359, 2008.
[13] N. Dalal, B. Triggs, “Histograms of oriented gradients for human detection.” Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, vol.1, pp. 886-893, 2005.
[14] F. Suard, A. Rakotomamonjy, A. Bensrhair, A. Broggi, “Pedestrian detection using infrared images and histograms of oriented gradients.” Proceedings of IEEE International Conference on Intelligent Vehicles Symposium, pp. 206-212, 2006.
[15] A. Cichowski, C. Madden, H. Detmold, A. Dick, A. van den Hengel, and R. Hill, “Tracking hand-off in large surveillance networks.” Proceedings of IEEE International Conference on Image and Vision Computing New Zealand, pp. 276-281, 2009.
[16] T. Kanade, A. Yoshida, K. Oda, H. Kano, M. Tanaka, “A stereo machine for video-rate dense depth mapping and its new applications.” Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 1996.
[17] Haralick, Robert M., and Linda G. Shapiro, “Optimizing two-pass connected-component labeling algorithms.” Pattern Analysis and Applications, Vol.12, no.2, pp. 117-135, 2009
[18] A. Hampapur, L. Brown, J. Connell, A. Ekin, N. Haas, M. Lu, H. Merkl, S. Pankanti, “Smart video surveillance: exploring the concept of multiscale spatiotemporal tracking.” IEEE Signal Processing Magazine, vol.22, no.2, pp. 38-51, 2005.
[19] N. Bellotto , B. Benfold , H. Harland , H. H. Nagel, N. Pirlo, I. Reid, E. Sommerlade, C. Zhao, “Cognitive visual tracking and camera control.” Computer Vision and Image Understanding, vol.116, no.3, pp. 457-471, 2012.
[20] X. Zhou, R. T. Collins, T. Kanade, P. Metes, “A master-slave system to acquire biometric imagery of humans at distance.” First ACM SIGMM international workshop on Video surveillance, pp. 113-120, 2003.
[21] Y. Lu, S. Payandeh, “Cooperative hybrid multi-camera tracking for people surveillance.” Canadian Journal of Electrical and Computer Engineering, vol.33, no.3, pp. 145-152, 2008.
[22] Y. Jo, J. Han, “A new approach to camera hand-off without camera calibration for the general scene with non-planar ground.” Proceedings of the ACM International Workshop on Video Surveillance and Sensor Networks, pp. 195-202, 2006.