在傳統的監控系統中，皆是使用廣角鏡頭的場景攝影機進行全天候之監控影像存取，而這樣會使所抓取到目標物之影像較為模糊，而造成難以辨識目標物之身份，且全天候影像存取亦會使得硬碟資源浪費，因此在本系統中則加入PTZ攝影機來協助場景攝影機進行追蹤，並將所抓取到之目標物，進行Zoom in功能的影像放大，以擷取到較清晰之目標物影像，另外，在論文中提出以環境音訊來判斷目前之音訊是否為一異常音訊，進而判斷是否為一事件發生，才進行事件影像存取，以減少硬碟資源浪費。在本系統中使用德州儀器TMS320DM642 DSP之開發模組來發展Server端的監控系統，且此系統具有獨立運作之特性，而Client端則是以PC進行使用者介面的開發，而Server端之影像與事件狀態亦可透過網路傳輸至Client端，當Server端有異常音發生時，則Client端則會進行事件影像存取與警訊顯示，並在日後可進行調閱與瀏覽，如此建構出一套即時多目標物追蹤與異常音偵測之監控系統。

In traditional surveillance systems, which use a wide-angle lens with field camera and store image all day. It can’t grab target’s face clearly for identification and storing image all day, because of it will waste of hard-disk’s resources. In the system, using high-resolution PTZ camera to be in conjunction with field camera and can track targets. And abnormal sound detection, whether abnormal event happen or not and store event-image, it will save many hard-disk resources. This research will combine TI TMS320DM642 Evaluation Module to development surveillance system in Server-side, the system has stand-alone characteristic and developing the graphical user interface based on PC in Client-side, Server-side will transmit the alarm information and image to the Client-side automatically. When the abnormal events happen in Server-side and it will transmit the alarm information and store the event-image in time, if necessary it will able to browse the event-image. Thereby, the system develops a real-time multi-object tracking and abnormal sound detection system with online warning function.

[1] 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, pp. 780-785, 1997.
[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] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
[4] 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.
[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] S. J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld and H. Wechsler, “Tracking Groups of People,” Computer Vision and Image Understanding, Vol. 80, pp. 42-56, 2000.
[7] M. J. Swain and D. H. Ballard, “Colour Indexing,” International Journal of Computer Vision, Vol. 7, pp. 11-32, 1999.
[8] S. Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms,” Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 232-237, June 1998.

[9] X. Zhou, R. Collins, T. Kanade and P. Metes, “A Master-Slave System to Acuire Biometric Imagery of Human at Distance,” ACM International Workshop on Video Surveillance, pp. 113-120, Nov. 2003.
[10] 馬仲強， “以DSP實現雙攝影機多目標物協同追蹤與遠端影像間控系統，” 國立台灣科技大學電機程系， pp. 9-90， 民國九十八年五月。
[11] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.
[12] 程上福， “以DSP實現人眼視覺之橢圓目標物量測系統，” 國立台灣科技大學電機程系， pp. 23-49， 民國九十七年七月。
[13] Texas Instruments Inc., Optimizing Complier User’s Guide, April 2001.
[14] L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals, Prentice Hall, pp. 30-70, 1978.
[15] 孫益君， “以PDA為平台之語音辨識應用系統開法，” 中原大學資訊工程學系， pp. 3-8， 民國九十三年七月。
[16] W. B. Pennebaker and J. L. Mitchell, JPEG : Still Image Data Compression Standard, Van Nostrand Renihold, New York, 1993.
[17] Texas Instruments Inc., JPEG Network on the DM642 EVM, July 2004.
[18] Texas Instruments Inc., TMS320C6000 TCP/IP Network Developer’s Kit User’s Guide, June 2003.
[19] Texas Instruments Inc., TMS320C6000 Assembly Language Tools User’s Guide, Oct 2006.
[20] Texas Instruments Inc., Creating a Second-Level Bootloader for FLASH Bootloading on TMS320C6000 Platform With Code Composer Studio, May 2006.
[21] Texas Instruments Inc., TMS320C6000 DSP External Memory Interface (EMIF) Reference Guide, April 2008.
[22] Texas Instruments Inc., Reference Framework for eXpressDSP Software : RF5, An Extensive, High-Density System, April 2003.
[23] Texas Instruments Inc., Reference Framework for eXpressDSP Software : API Reference, April 2003.
[24] Texas Instruments Inc., TMS320C6000 Network Developer’s Kit (NDK) Software Programmer’s Reference Guide, Aug 2007.
[25] Texas Instruments Inc., TMS320C6000 DSP/BIOS 5.32 Application Programming Interface(API) Reference Guide, Sep 2007.
[26] Texas Instruments Inc., TMS32 DSP/BIOS User’s Guide, Nov 2004.
[27] Texas Instruments Inc., TLV320AIC23 Data Manual, July 2001.
[28] S. Einav and Y. Roffeh, “Analysis of Sounds From Occluded Arteries by Using a Linear Array of Microphones,” Proceedings-IEEE Convention of Electrical & Electronics Engineers in Israel, pp. 4.2.1/1-5, 1995.
[29] 黃啟揚， “以雙核心平台實現即時影音追蹤與語音純化系統，” 國立交通大學電機與控制工程系所， pp. 10-15， 民國九十七年七月。
[30] T. Shindoi, T. Hirai, K. Takashima and T. Usami, “Plant equipment diagnosis by sound processing,” IECON Proceedings (Industrial Electronics Conference) 2, pp. 1020-1026, 1999.
[31] 盧怡仁，蔡偉和著，單晶片於數位信號處理器的應用，初版，文魁資訊，2007。