臺灣博碩士論文加值系統

本論文研製之目的在於提出一種利用具有可控制攝影機的監控系統來擷取人的臉部特寫。在現今已知的監控系統中，大部份都是拍攝固定區域，而且只單純追蹤影像中人物的軌跡或者是抓取影像中的人臉；但是當人物距離攝影機較遠的時候，就無法獲得更仔細的資訊。本實驗利用離散小波轉換來去除雜訊及增進計算效能，並以背景相減及邏輯AND運算的方式來取得移動區域，接著使用膚色偵測來過濾出人體區域。藉由人體區域可以計算出移動向量，然後再根據移動向量的方向來預測人物下一步會到達的位置，並且依據移動向量的大小來設定攝影機的旋轉速度，以達到控制攝影機來拍攝臉部特寫的目的。

A procedure is proposed to use a controllable video camera to obtain the close-up of the human face. The surveillance systems developed in the last years focused on a fixed area. Most of the systems tracked the trajectories of the people and the others only captured the small-scale picture of the human body because the people were far away from the video camera. The discrete wavelet transform is used to reduce the effect of the noises of the video camera and improve the computational efficiency. Then the moving regions are detected by the background subtraction and the logic AND operation. Hence the human body regions are derived from the moving regions by detecting the skin color, and those are used to calculate the motion vectors. Then the direction of the motion vector is used to control the direction of the panning and the tilting directions of the video camera and its norm is adopted to set the speed parameters of the panning and the tilting of the video camera.

書名頁 ……………………………………………………………… i
論文口試委員審定書 ……………………………………………… ii
授權書 ……………………………………………………………… iii
中文摘要 …………………………………………………………… iv
英文摘要 …………………………………………………………… v
誌謝 ………………………………………………………………… vi
目錄 ………………………………………………………………… vii
表目錄 ……………………………………………………………… viii
圖目錄 ……………………………………………………………… ix
一、 緒論 ……………………………………………………… 1
1.1 研究動機 ………………………………………………… 1
1.2 研究目的 ………………………………………………… 2
1.3 文獻回顧 ………………………………………………… 3
二、 系統運作情境 …………………………………………… 8
2.1 前處理 …………………………………………………… 11
2.1.1 色彩空間的選擇 ………………………………………… 12
2.1.2 去除雜訊 ………………………………………………… 22
2.2 人體區域之偵測 ………………………………………… 23
2.2.1 偵測移動區域 …………………………………………… 24
2.2.2 偵測膚色區域 …………………………………………… 28
2.3 攝影機的控制 …………………………………………… 31
2.3.1 置中人體區域 …………………………………………… 31
2.3.2 追蹤及拍攝特寫 ………………………………………… 35
2.3.3 拍攝後的確認 …………………………………………… 36
2.3.4 攝影機的歸位 …………………………………………… 37
三、 實驗結果 ………………………………………………… 39
四、 結論與展望 ……………………………………………… 42
參考文獻 …………………………………………………………… 43

[1] A. Cavallaro and T. Ebrahimi, “Video object extraction based on adaptive background and statistical change detection,” in Proc. SPIE Electronic Imaging. Visual Communications and Image Processing, San Jose (California, USA), 21-26 January 2001, pp. 465-475.
[2] S. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler, “Tracking groups of people,” Comput. Vis. Image Understanding, vol. 80, no. 1, pp. 42–56, 2000.
[3] N. Amamoto and A. Fujii, “Detecting obstructions and tracking moving objects by image processing technique”, Electronics and Comm. in Japan, Part 3, vol. 82, no. 11, pp. 28-37, 1999.
[4] P. Peer, F. Solina, “An Automatic Human Face Detection Method,” in Proc. 4th Computer Vision Winter Workshop, Rastenfeld, Austria, 1999, pp. 122-130.
[5] J. Kovač, P. Peter, F. Solina, “Human skin colour clustering for face detection,” Int. Conf. Computer as a Tool, Ljubljana, Slovenia, 22-24 Sept. 2003, pp. 144-148.
[6] H. Yoon, D. Kim, S. Chi, Y. Cho, “A robust human head detection method for human tracking,” IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Oct. 2006, pp. 4556-4563.
[7] J.S.C. Yuk, K.-K.Y. Wong, R.H.Y. Chung, F.Y.L. Chin, K.P. Chow, “Real-time multiple head shape detection and tracking system with decentralized trackers,” in Proc. Sixth Int. Conf. Intelligent Systems Design and Applications, Oct. 2006, pp. 384-389.
[8] D. Comaniciu, V. Ramesh, P. Meer, “Real-time tracking of non-rigid objects using mean shift,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition. 2000, pp. 142-149.
[9] A. Cavallaro, O. Steiger, T. Ebrahimi, “Tracking video objects in cluttered background,” IEEE Trans. Circuit s and Systems for Video Technology, vol. 15, no. 4, pp. 575-584, 2005
[10] T. Yang, S. Z. Li, Quan Pan, Jing Li, “Real-time multiple objects tracking with occlusion handling in dynamic scenes,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 20-25 June 2005, pp. 970-975.
[11] J. Zhou, J. Hoang, “Real time robust human detection and tracking system,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 20-26 June 2005, pp. 149-149.
[12] S. Ribarić, G. Adrinek, S. Šegvić, “Real-time active visual tracking system,” in Proc. 12th IEEE MELECON, Dubrovnik, Croatia, 12-15 May 2004, pp.231 – 234.
[13] Y. Wei, W. Badawy, “A novel zoom invariant video object tracking algorithm (ZIVOTA),” IEEE CCECE Conf. Electrical and Computer Engineering, 2003., 4-7 May 2003, pp. 1191 – 1194.
[14] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: real-time tracking of the human body,” IEEE Trans. Pattern Anal. Machine Intell., vol. 19, pp. 780–785, July 1997.
[15] I. Haritaoglu, D. Harwood, and L. S. Davis, “W4: Real-time surveillance of people and their activities,” IEEE Trans. Pattern Anal. Machine Intell., vol. 22, pp. 809–830, Aug. 2000.
[16] F. H. Cheng, Y. L. Chen, “Real time multiple objects tracking and identification based on discrete wavelet transform”, Pattern Recognition, vol. 39, no. 6, pp. 1126-1139, 2006.
[17] P. Azzari, L. Di Stefano, and A. Bevilacqua, “An effective real-time mosaicing algorithm apt to detect motion through background subtraction using a PTZ camera,” IEEE Conf. Advanced Video and Signal Based Surveillance, 15-16 Sept. 2005, pp. 511-516.