隨著科技日益的進步，大型積體電路技術的快速發展，使得數位訊號處理器DSP的功能比以往更加強大，處理速度更快體積更小越來越容易開發，都是DSP的優點，而且DSP-based的系統在大量且複雜的運算處理上有著高準確度及高效能的表現，在即時性上也能滿足大部分系統的需求。本論文將結合DSP與動態影像處理方法，搭配網路傳輸來對移動物體作即時偵測，並且建立一獨立式的即時影像自動偵測的網路連線運作系統。在系統的處理流程中將攝影機所擷取到的影像資料送入DM642 EVM模組中，以DSP處理背景消除與平滑法濾波，使移動物體從背景影像中分離出來，接著利用連接元件標記法將各個移動物體分別標記，對侵入的移動物體做多目標的偵測。本系統將結合網路傳輸的架構以DSP當作Server端，以PC-Based的視窗介面作為Client端，Server端可以依照Client端所發出的要求，傳遞DSP的即時影像訊息，此外若Server端偵測到有異常的移動物體侵入，也會自動的將影像畫面警示資訊即時傳遞給Client端，建構出即時影像偵測的警示系統。

The constant advancement in technology and the rapid development of VLSI have resulted in the expanded functionality, increased processing speed, continued miniaturization, and ease of development of Digital Signal Processors. Not only are DSP-based systems highly accurate as well as efficient in the processing of high volume and complex algorithms but can also meet most systems’ requirement for real-time performance. The thesis is to achieve instantaneous detection of objects by connecting DSP enhanced with integrated image processing to a network through the setup of a standalone network operating system to automatically detect objects. During system processing, the images captured by the camera are sent to DM642 EVM module for background subtraction and then a run through a smoothing filter so that moving objects can be extracted from the static background. Next, the extracted moving objects are marked separately using a connected component labeling algorithm to detect intruding objects. The proposed system with integrated network treats the DSP as the Server-side and a Windows-based personal computer as the Client-side. Based on requests from the Client-side, the Server-side can transmit DSP’s real-time images. In addition, if the Server-side detects any unusual moving objects, it will automatically transmit the image, as well as a real-time warning message, to the Client-side, thereby creating a real-time image detection warning system.

[1] S. Khan and M. Shah, “Tracking People in Presence of Occlusion,” Proceedings of the Asian Conference on Computer Vision, Taipei, Taiwan, pp. 1132-1137, January 2000.
[2] I. Haritaoglu, D. Harwood, and L.S. Davis, “Hydra: Multiple People Detection and Tracking Using Silhouettes,” Proceedings of the Second IEEE Workshop on Visual Surveillance, pp. 6-13, June 26, 1999
[3] I. Haritaoglu, D. Harwood, and L. Davis, “W4: Who, When, Where, What: A Realtime System for Detecting and Tracking People,” IEEE International Conference on Automatic Face and Gesture Recognition, pp. 222–227, April 1998.
[4] C.R. Wren, A. Azarbayejani, T. Darrell, and A. Pentland. “Pfinder: Realtime Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, 780–785, 1997.
[5] 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.
[6] A.K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall, New York, pp. 62-77, 1989.
[7] J. Kato, T. Watanabe, and H. Hase, “Highway Surveillance System Using an HMM-based Segmentation Method,” IEICE Transactions on Information and Systems, Vol. 85-D, No.11, pp. 1767-1775, 2002.
[8] 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.
[9] J.P. Serra, Image Analysis and Mathematical Morphology, Academic
Press, pp. 115-130, 1982.
[10] Texas Instruments Inc., “TMS320DM642 Data Sheet”.

[11] Texas Instruments Inc., ”TMS320 C6000 CPU and Instruction Set
Reference Guide”.
[12] Texas Instruments Inc., “TMS320DM642 Technical Overview”.

[13] K.P. Horn and B.G. Schunck, “Determining Optical Flow,” Artificial Intelligence, Vol.17, pp. 185-203, 1981.
[14] C.S. Fuh and P. Maragos, “Region-Based Optical Flow Estimation,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, pp. 130-133, 1989.
[15] M.S. Lee, “Detecting People in Cluttered Indoor Scenes,” Processings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. COM-31, No. 4, pp. 532-540, 1983.
[16] D. Hearn and M.P. Baker, Computer Graphics, 2nd Edition, Prentice Hall, New York, pp. 49-81, 1994.
[17] M. Seul, L. O’Gorman, and M.J. Sammon, “Practical Algorithms for Image Analysis,” Cambridge University, New York, pp. 51-55, 2000.
[18] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, PWS Pub. , New York, pp. 35-48, 1999.
[19] D.H. Ballard and C.M. Brown, Computer Vision, Prentice-Hall, New York, pp. 65-78, 1982.
[20] S. Abu-Bakerand and R.J. Green, “Detection of Edges Based on Hexagonal Pixel Formats,” IEEE Int’l Conf. on Signal Processing, Vol. 2, pp. 1114-1117, Oct. 1996.
[21] J.F. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. on Pattern Analysis Machine Intelligence, Vol. PAMI-6, pp. 679-698, Nov. 1986.
[22] N. Kanopoulos, N. Vasanthavada, and R.L. Baker, “Design of an Image Edge Detection Filter Using the Sobel Operator,” IEEE Journal of Solid-State Circuits, Vol. 23, No. 2, pp. 358-367, April 1988.
[23] N. Kazakova, M. Margala, and N.G. Durdle, “Sobel Edge Detection Processor for a Real-Time Volume Rendering System,” Proceedings of the 2004 International Symposium on Circuits and Systems(ISCAS '04.), Vol. 2, pp. 913-916, May 2004.
[24] D. Hearn and M.P. Baker, Computer Graphics, 2nd Edition, Prentice Hall, New York, pp. 49-81, 1994.
[25] A.K. Jain, “Fundamentals of Digital Image Processing,” Prentice-Hall, New York, pp. 62-77, 1989.
[26] 陳同孝，張真誠，黃國峰，數位影像處理技術，台北，松崗，2001。
[27] W. Richard Stevens, TCP/IP Illustrated, Volume2, AddisonWesley,1995.
[28] 李孟書、黃鶴超譯，Windows Sockets 網路程式設計經典，台北，基
峰，1997。
[29] Texas Instruments Inc., “TMS320C6000 TCP/IP Network Developer’s Kit (NDK) User’s Guide”.
[30] Texas Instruments Inc., “TMS320C6000 Optimizing C Compiler Tutorial”.
[31] Texas Instruments Inc., “Code Composer Studio v3.0 Getting Started
Guide”.