臺灣博碩士論文加值系統

現今大部份數位影像處理系統，大多以個人電腦為基礎架構，透過數位攝影機擷取影像資料，接著再運算我們希望達到的功能。所以電腦內的中央處理器除了要抓取影像資料外還要執行視窗作業系統，這些程序往往會造成電腦內的中央處理器龐大負擔，因而導致整個系統效率降低，且個人電腦體積龐大，高耗功率，不適於獨立作業的需求。所以本論文利用德州儀器生產的數位訊號處理器TMS320DM642 EVM結合CCS(Code Composer Studio)軟體系統為我們的開發平台。首先利用EDMA(Enhanced Direct Memory Access)控制器開啟DMA通道，將影像資料直接存入我們預設好的緩衝區內等待處理，在即時影像偵測追蹤處理方面，利用背景相減法得到移動物體區塊，並建立各別移動物體的彩色直方圖模型，在移動物體沒有交會情況下使用關聯性區塊比對法追蹤，當移動物體產生交會時改用彩色直方圖模型比對來完成我們的追蹤系統，而處理完畢的影像，也透過EDMA控制器將畫面輸出在監控螢幕上。系統完成後，我們可以對監控畫面上的移動物體做即時偵測與追蹤。

Now most of digital image process systems are based on personal computer, we catch image materials and operate them in order to reach our target. Therefore a computer’s CPU not only captures image materials but also executes Windows Operating System; These procedures often cause the huge loading of the CPU and lower efficiency of the system; however the PC is bulky and high comsuming power, so it’s not suitable for Stand-alone systems. We combine the TI TMS320DM642 EVM with CCS software system to be the research developing platform. At first we use EDMA controller to create DMA gateway, and directly store image materials in capture buffer to wait for process. In real-time motion tracking, we get moving objects block by Background Image Subtraction Algorithm, and we build every moving object Color Histogram Model. When moving objects don’t cross, we use Correlation Based Block Matching Method; on the other hand, when they cross, we use Color Histogram Model Matching to complete our tracking system. Finally we export processed images on the screen by EDMA controller. After we complete the system, we can detect and track the moving object in real time.

中文摘要 ………………………………………………………………I
英文摘要 ………………………………………………………………II
誌 謝 ………………………………………………………………III
目 錄 ………………………………………………………………IV
圖表索引 ………………………………………………………………VII

第一章 緒論…………………………………………………………1
1.1 研究目的與動機 ……………………………………………………1
1.2 研究方法……………………………………………………………3
1.3 論文架構……………………………………………………………4

第二章 即時多目標移動物體偵測與追蹤系統架構………………5
2.1 影像輸入輸出程序…………………………………………………6
2.2 移動物體偵測系統…………………………………………………7
2.3 移動物體模型建立…………………………………………………8
2.4 移動物體追蹤系統…………………………………………………10
2.5 相關硬體使用與規格………………………………………………12

第三章 移動物體偵測程序 ……………………………………… 14
3.1 影像品質的改善 ……………………………………………………14
3.1.1 平滑法 ……………………………………………………14
3.1.2 中值法 ……………………………………………………16
3.2 背景影像相減法 ……………………………………………………18
3.3 影像前處理 ……………………………………………………19
3.3.1 低通濾波器…………………………………………………20
3.3.2 陰影去除 ……………………………………………………21
3.3.3 修補移動物體區塊 ……………………………………… 23
3.4 連接元件標記法 ……………………………………………………24
3.5 移動物體模型建立…………………………………………………26
3.6移動物體偵測程序流程…………………………………………… 29

第四章 即時移動物體追蹤程序……………………………………31
4.1 物件關係表…………………………………………………………31
4.2 區塊比對法…………………………………………………………40
4.3 彩色直方圖模型比對………………………………………………47
4.4 移動物體追蹤流程…………………………………………………50

第五章 TI DM642 DSP與CCS發展環境簡介……………………… 53
5.1 DM642硬體架構 ……………………………………………………54
5.2 DM642的中央處理器……………………………………………… 55
5.3 DM642的記憶體 ……………………………………………………56
5.4 直接記憶體存取EDMA控制器………………………………………58
5.5 影像連接埠(Video port) ……………………………………… 59
5.5.1 影像擷取模式………………………………………………59
5.5.2 影像輸出模式………………………………………………60
5.6 燒錄程式於快閃記憶體……………………………………………61
5.7 CCS軟體發展系統………………………………………………… 66
5.8 基本輸入輸出系統(DSP/BIOS)……………………………………69

第六章 多目標追蹤系統的實現 ……………………………………… 71
6.1 DSP/BIOS設定………………………………………………………71
6.2 系統實現……………………………………………………………78
6.3 編譯程式選項(Build Options)重要設定……………………… 82
6.4 系統效能測試………………………………………………………86

第七章 結論……………………………………………………………92
7.1 研究成果………………………………………………………… 92
7.2 發展方向………………………………………………………… 95

參考文獻 ………………………………………………………………97
作者簡介 ………………………………………………………………100
授 權 書 ………………………………………………………………101

[1] A.K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall, New York, pp. 62-77, 1989.
[2] 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.
[3] 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.
[4] 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.
[5] M.J. Swain and D.H. Ballard, “Colour Indexing,” International Journal of Computer Vision, Vol. 7, pp. 11-32, 1999.
[6] 鍾國亮編著，影像處理與電腦視覺，第二版，東華書局，台北，2004。
[7] K.E. Batch, “Sorting Networks and Their Applications,” Proc. AFIPS 1968 Spring Joint Comput. Conf., Atlantic City, NJ, pp. 307-314, 1968.
[8] 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.
[9] 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.
[10] M. Petrou and P. Bosdogianni, “Image Enhancement,” in Image Processing: the fundamentals New York: John Wiley & Sons, pp. 125-154, 2001.
[11] M. Mason and Z. Duric, “Using Histograms to Detect and Track Objects in Color Video,” Proceedings of 30th Applied Imagery Pattern Recognition Workshop(IPRW), Washington, DC, pp. 154-159, October 2001.
[12] 張家榮，“使用高等集合法對多目標移動物追蹤之研究”，元智大學電機工程研究所，2001
[13] K.R. Rao and J.J. Hwang, Techniques and standards for image,video and audio coding, Prentice Hall, 1996.
[14] M.J. Chen, L.G. Chen and T.D. Chiueh, “One-Dimensional Full Search Motion Estimation Algorithm for Video Coding,” IEEE Trans. Circuits and Systems for Video Technology, vol. 4, pp. 504-509, 1994.
[15] H.M. Jong, L.G. Chen and T.D. Chiueh, “Accuracy Improvement and Cost Reduction of 3-step Search Block-matching Algorithm for Video Coding,” IEEE Trans. Circuits and Systems for Video Technology, vol. 4, pp. 88-90, 1994.
[16] Y.K. Lai, “A Memory Efficient Motion Estimation for Three Step Search Block Matching Algorithm,” IEEE Transactions on Consumer Electronics, Vol.47, No.3, pp. 644-651, August 2001.
[17] L.M. Po and W.C. Ma, “A Novel Four-step Search Algorithm for Fast
Block Motion Estimation,” IEEE Trans. Circuits and Systems for Video Technology, vol. 6, pp. 313-317, 1996.
[18] Texas Instruments Inc., “TMS320DM642 Technical Overview”
[19] Texas Instruments Inc., “TMS320C64x DSP Two-Level Internal Memory Reference Guide”
[20] Texas Instruments Inc., “TMS320C6000 DSP Enhanced Direct Memory Access Controller Reference Guide”
[21] Texas Instruments Inc.,“TMS320C64x DSP Video Port/VCXO Interpolated Control Port Reference Guide”
[22] Texas Instruments Inc.,“Creating a Second-Level Bootloader for FLASH Bootloading on C6000”
[23] Texas Instruments Inc.,“TMS320C6000 Optimizing C Compiler Tutorial”
[24] Texas Instruments Inc.,“TMS320C6000 DSP/BIOS User’s Guide”