臺灣博碩士論文加值系統

通常在學校補習班的教室，常會使用攝影機在旁做側錄，以供複製拷貝、發行販售、紀錄保存及重複瀏覽播放等，以供學員及未參與者二次學習的機會，側錄的動作通常以人工的方式去操作攝影機，因此本論文以開發以DSP實現遠端同部教學傳播系統為目的，希望能全自動錄影追蹤取代人力資源。由於數位訊號處理器(DSP：Digital Signal Processor)具有執行速度較快，整體效能佳、特殊硬體及指令設計可達成真正的即時運作的優點，因此本系統實現在德州儀器(Texas Instrument)之TMS320DM642 EVM模組上，並搭配具有旋轉以及變焦功能之PTZ(Pan/Tilt/Zoom)攝影機來實現，透過旋轉PTZ攝影機追蹤講師位於畫面，再根據講師手寫姿態的手部端點，適時的用PTZ攝影機去做Zoom in追蹤或Zoom out以供學員能看清講師的上課焦點位置，最後再透過乙太網路將影像傳送至遠端電腦去做遠端監控，如此便能達到遠端同部教學傳播系統。

In the school, and cram school, we usually use the camera to record the class contents in order to let the students who were absent can learn the class contents or save it. The record work usually record by the someone. The purpose of this thesis is to implement the remote synchronization communication teaching system to replace the record work. The Digital Signal Processor (DSP) has many benefits such as high performance, small size and special hardware instruction for this reason. We use the TI’s TMS320DM642 DSP module as our research developing platform, and the camera which has the pan, tilt and zoom functions named PTZ camera. We can use the pan function to track the teacher stay in the frame and the zoom function to enlarge the frame to track the hand endpoint. Finally, we through Ethernet transmit the image to the remote computer to do remote monitoring. Hereby develop a real-time remote synchronization teaching communication system.

摘 要I
AbstractII
致 謝III
目 錄IV
圖索引VI
表索引X

第一章 緒論1
1.1 研究動機與目的1
1.2 研究方法2
1.3 論文架構3

第二章 系統架構4
2.1 目標物偵測程序6
2.2 姿態分析程序7
2.3物件基準背景更新程序8
2.4手部追蹤程序9
2.5影像網路傳輸程序10
2.6 硬體配置與規格11

第三章 目標物偵測與背景更新15
3.1 前景區塊萃取與陰影偵測15
3.1.1 前景目標物萃取導論5
3.1.2 前景區塊背景相減法16
3.1.3 YCbCr陰影偵測法19
3.1.4形態學雜訊濾除及區塊填補21
3.2 移動目標物框取23
3.2.1 物件連通標記法23
3.2.2 目標物框選25
3.3 影像大小初始調整26
3.3.1 目標物大小寬度位置26
3.3.2 影像大小初始調整28
3.4 物件基準背景更新方法30
3.4.1 常用背景更新方法30
3.4.2 物件基準背景更新33
3.4.3背景更新位移預測法38

第四章 目標物姿態分析40
4.1 特徵點偵測40
4.1.1 邊緣偵測與外圍輪廓萃取 40
4.1.2 質心點建立43
4.1.3 特徵點建立45
4.2 建立上半身骨架47
4.2.1 頭部特徵點選取48
4.2.2 手部特徵點選取48
4.3 姿態比對52
4.3.1 碼本分類與建立52
4.3.2 寫字姿態判定 55

第五章 目標物追蹤控制58
5.1 PTZ攝影機旋轉角度與像素關係58
5.2 目標物追蹤模式62
5.3 手部追蹤模式65
5.3.1 手部放大定位 65
5.3.2 手部追蹤步驟 67
5.3.3 追蹤終止條件 70

第六章 系統實現與效能測試73
6.1 系統軟體架構73
6.2 網路傳輸75
6.2.1 建立網路連線 75
6.2.2 遠端使用者介面77
6.2.3 網路傳輸流程圖78
6.3 系統實現79
6.4 系統效能測試86

第七章 結論88
7.1 研究成果88
7.2 未來研究方向91

參考文獻92

[1] C. R. Wren, A. Azarbayejani, T. Darrell and A. Pentland. “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, pp. 780-785, 1997.
[2] I. Haritaoglu, D. Harwood and L. S. Davis, “W4: Real-Time Surveillance of People and Their Activities,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 809-830, 2000.
[3] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
[4] Y. H. Liang, S. Guo, Z. Y. Wang, X. W. Xu and X. Y. Cao, “A Robust and Fast Motion Segmentation Method for Video Sequences,” Proceedings of the IEEE International Conference on Automation and Logistics, ICAL 2007, pp. 2952-2957, 2007.
[5] A. Prati, I. Mikic, M. M. Trivedi and R. Cucchiara, “Detecting Moving Shadows: Algorithms and Evaluation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 7, pp. 918-923, 2003.
[6] L. D. Stefano and A. Bulgarelli, “A Simple and Efficient Connected Components Labeling Algorithm,” Proceedings of 10th International Conference on Image Analysis, pp. 322-327, 1999.
[7] K. Takahashi and M. Naemura, “Remarks on Real-Time Human Posture Estimation from Silhouette Image Using Neural Network,” Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, pp. 370-375, 2004.
[8] H. S. Chen, H. T. Chen, Y. W. Chen and S. Y. Lee, “Human Action Recognition Using Star Skeleton,” Proceedings of the ACM International Multimedia Conference and Exhibition, pp. 171-178, 2006.
[9] Texas Instruments Inc., TMS320DM642 Evaluation Module with TVP Video Decoders Technical Reference, Dec. 2004.
[10] S. Y. Chien, S. Y. Ma and L. G. Chen, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 7, pp. 577-586, 2002.
[11] 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.
[12] Grzegorz Szwoch, Piotr Dalka, “Identification of Regions of Interest in Video for a Traffic Monitoring System”, Proceedings of the 2008 1st International Conference on Information Technology, pp. 19-21, May 2008.
[13] A. J. Lipton, H. Fujiyoshi and R. S. Patil, “Moving Target Classification and Tracking from Real-Time Video,” Proc. IEEE Workshop Applications of Computer Vision, pp. 8-14, 1998.
[14] J. Stauder, R. Mech and J. Ostermann, “Detection of Moving Cast Shadows for Object Segmentation,” IEEE Transactions on Multimedia, Vol. 1, No. 1, pp. 65-76, 1999.
[15] C. Kim and J. N. Hwang, “Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications,”IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 2, pp. 122-129, 2002.
[16] J. Barron, D. Fleet and S. Beauchemin, “Performance of Optical Flow Techniques,” International Journal of Computer Vision, Vol. 12, No. 1, pp. 42-77, 1994.
[17] J. W. Hsieh, W. F. Hu, C. J. Chang and Y. S. Chen, “Shadow Elimination for Effective Moving Object Detection by Gaussian Shadow Modeling,” Image Vision and Computing Journal, Vol. 21, pp. 505-516, 2003.
[18] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.
[19] A. Bevilacqua, L. D. Stefano and P. Azzari, “An Effective Real-Time Mosaicing Algorithm Apt to Detect Motion Through Background Substraction Using a PTZ Camera, “IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 511-516, Sept. 2005.
[20] S. Jabri, Z. Duric, H. Wechsler and A. Rosenfeld, “Detection and Location of People in Video Images Using Adaptive Fusion of Color and Edge Information,“ Proceedings of 15th International Conference on Pattern Recognition (ICPR), Vol. 4, pp. 627-630, Sept. 2000.
[21] P. J. Burt and E. H. Adelson, “The Laplacian Pyramid as a Compact Image Code,” IEEE Transactions Communications, Vol. COM-31, No. 4, pp. 532-540, 1983.
[22] S. R. Gunn, “On the Discrete Representation of the Laplacian of a Guassian,” Pattern Recognition, Vol. 32, No. 8, pp. 1463-2472, 1999.
[23] R. J. Qian and T. S. Huang, “Optical Edge Detection in Two-Dimensional Image,” IEEE Transactions Image Processing, Vol. 5, No. 7, pp. 1215-1220, 1996.
[24] A. Rosenfield and M. Thurston, “Edge and Curve Detection for Visual Scene Analysis,” IEEE Transactions Computation, Vol. C-20, pp. 562-569, 1971.
[25] J. Canny, “Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8, No. 6, pp. 679-698, 1986.
[26] Chen B S and Lei Y Q, “Indoor and Outdoor People Detection and Shadow Suppression by Exploiting HSV Color Information,” Proceedings of the Fourth International Conference on Computer and Information Technology (CIT’04), pp. 137-142, 2004
[27] R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt and L. Wixson, “A system for surveillance and monitoring,” The Robotics Institute, Carnegie Mellon University, Pittsburgh PA, Tech. Rep. CMU-RI-TR-00-12, 2000.
[28] Shuan Liu, Jun-Yu Dong, Sheng-Ke Wang and Guo-Jiang Chen, “Road Junction Background Reconstruction Based on Median Estimation and Support Vector Machines,” Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, pp. 4200-4205, 2006.
[29] Yong Fan, “A real-time algorithm of dynamic background extraction in image sequence,” Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, pp. 4997-5000, 2005.
[30] G. Borgefors, “Distance Transformations in Digital Images,” Computer Vision, Graphics, & Image Processing, Vol. 34, No. 3, pp. 344-371, 1986.
[31] Texas Instruments Inc., TMS320C6000 TCP/IP Network Developer’s Kit User’s Guide, June 2003.