本研究使用二台PTZ網路攝影機來自動偵測以及追蹤進入監控環境為室內的目標。使用雙PTZ攝影機的室內即時監控系統的優點在於攝影機的功能能夠彼此交換。其中一台攝影機用於定位，主要負責偵測出監控環境內的目標位置。另外一台攝影機用於特寫及追蹤，主要負責對目標進行臉部的特寫並進行影像的儲存。對監控系統而言，儘可能的擷取出進入者的臉部影像非常重要，特別是在發生危險事件後，此影像利於人工對進入者進行辨識或是系統自動辨識皆可。由於進入監控環境的人可在監控環境內任意移動，因此使用二台可交換功能的攝影機系統能讓攝影機更容易得到適合辨識臉部的照片。此外，3D空間的追蹤能幫助我們分析進入者的行為，包括進入者進入的時間以及在監控環境內移動的位置狀況等。我們相亯利用攝影機間功能的交換性，可以增加完成這些監控系統要求的可能性。因此本研究提出了一種攝影機功能交換區域的方法，實驗結果顯示這種方法也能在即時系統上面穩定的運作。

This paper presents a method using dual PTZ network cameras to automatically detect and track the invaders which intrude into an indoor surveillance space. The main advantage of using dual PTZ cameras in the indoor surveillance system is their assignment swap ability. Initially, one PTZ (called orientation camera) can be used to monitor the surveillance space to detect the invaders and the other (called zoom camera) then can track them. In the surveillance system, to obtain the front face picture of invaders as clear as possible is very important since the invader should be manually or automatically recognized after the events. However, the invaders may arbitrarily move in the surveillance space, thus the tracker which should extract the detail information of the invaders may never obtain the suitable pictures. Moreover, 3D tracking can help us to analyze the behavior of the invader, including when and what the invader has down in the surveillance space, in the future. We believe to swap the assignments of monitor and tracker can greatly increase the possibility to accomplish these kinds of surveillance demands. This paper proposes an assignment swap strategy applying dual PTZ cameras in the surveillance system. The experimental results show the method can work robustly in real-time.

[Amn06] P. Amnuaykanjanasin, S. Aramvith, and T. H. Chalidabhongse, “Real-Time Face Identification Using Two Cooperative Active Cameras,” Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision, Singapore, pp. 1 – 6, 2006. [Azz05] P. Azzari, L. D. Stefano, and A. Bevilacqua, “An Effective Real-time Mosaicing Algorithm Apt to Detect Motion Through Background Subtraction Using a PTZ Camera,” Proceedings of IEEE Conference on Video and Signal Based Surveillance, Como, Italy, pp. 511 – 516, 2005. [Bao05] P. T. Bao, J. Y. Kim, and S. Y. Na, “Fast Multi-face Detection in Color Images Using Fuzzy Logic,” Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, Hong Kong, pp. 777 – 780, 2005. [Baf08] F. E. Baf, T. Bouwmans, and B. Vachon, “Foreground Detection using the Choquet Integral,” Proceedings of the Ninth International Workshop on Image Analysis for Multimedia Interactive Services, Klagenfurt, Austria, pp. 187 – 190, 2008. [Che08] K. W. Chen, C. C. Lai, Y. P. Hung, and C. S. Chen, “An Adaptive Learning Method for Target Tracking across Multiple Cameras,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, pp. 1 – 8, 2008. [Cuc05] R. Cucchiara, C. Grana, A. Prati, and R. Vezzani, “Computer Vision System for In-house Video Surveillance,” Proceedings of the IEE Conference on Vision, Image, and Signal Processing, pp. 242 – 249, 2005.

[Dra08] I. Draganjac, Z. Kovacic, D. Ujlaki, and J. Mikulic, “Dual Camera Surveillance System for Control and Alarm Generation in Security Applications,” Proceedings of the IEEE International Symposium on Industrial Electronics, pp. 1070 – 1075, 2008. [Esh08] R. Eshel and Y. Moses, “Homography Based Multiple Camera Detection and Tracking of People in a Dense Crowd,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, pp. 1 – 8, 2008. [Eve07] I. Everts, N. Sebe, and G. Jones, “Cooperative Object Tracking with Multiple PTZ Cameras,” Proceedings of the 14th International Conference on Image Analysis and Processing, Modena, Italy, pp. 323 – 330, 2007. [Foc02] D. Focken and R. Stiefelhagen, “Towards Vision-based 3D People Tracking in a Smart Room,” Proceedings of the Fourth IEEE International Conference on Multimodal Interfaces, Pittsburgh, pp. 400 – 405, 2002. [Fun04] T. Funahasahi, M. Tominaga, T. Fujiwara, and H. Koshimizu, “Hierarchical Face Tracking by Using PTZ Camera,” Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, pp. 427 – 432, 2004. [Hu06] W. Hu, M. Hu; X. Zhou, T. Tan, J. Lou, and S. Maybank; “Principal Axis-based Correspondence Between Multiple Cameras for People Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 28, pp. 663 – 671, 2006. [Lu08] Y. Lu and S. Payandeh, “Cooperative Hybrid Multi-camera Tracking for People Surveillance,” Proceedings of the IEEE Conference on CCECE/CCGEI, Niagara Falls, Canada, pp. 1365 – 1368, 2008.

[Var08] P. D. Z Varcheie, M. Sills-Lavoie, and G. A. Bilodeau, “An Efficient Region-Based Background Subtraction Technique,” Proceedings of the Canadian Conference on Computer and Robot Vision, Windsor, Ontario, Canada, pp. 71 – 78, 2008. [Yan08] L. Yan and S. Payandeh, “Cooperative Hybrid Multi-camera Tracking for People Surveillance,” Proceedings of Canadian Conference on Electrical and Computer Engineering, Ontario, Canada, pp. 001365 – 001368, 2008. [Yan07] P. Yang, W. Wu, M. Moniri, and C. C. Chibelushi, “RFID Tag Infrastructures for Camera Tracking in Virtual Studio Environment,” Proceedings of the 4th European Conference on Visual Media Production, London, pp. 1 – 8, 2007. [王05-1] 王政雄，“使用環場及PTZ攝影機結合之系統”，國立台灣師範大學資訊工程研究所碩士論文，民國94年。 [王05-2] 王志高，吳先晃，結合全景與PTZ相機之視訊監控系統，Proceedings of the 2005 Workshop on Consumer Electronics and Signal Processing (WCEsp 2005), Taiwan, Nov. 17-18.