本研究利用高整合性的SOPC系統結合彩色影像追蹤模組，實現一個強健性的物體追蹤及預測系統。其主要透過對二值化的視訊畫面進行分割，得到M x N的區塊與各區塊X、Y的位址定位。並將每區塊中二值化得到的數值累加，得到該區塊分數。將每個區塊不同的分數除以總分，定義得到的值為各區塊的權重值。並將每個區塊不同的權重值與區塊位址相乘並加總，可計算得追蹤物體的中心位置。
　　系統中亦規劃感興趣區域的範圍，對於追蹤物體劃分出一個矩形區域邊界。利用感興趣區域的規劃，可結合影像壓縮技術使得應用在監視系統時，減少影像儲存量，降低監視系統建構成本。移動預測功能則可結合主動式攝影機；透過預測的移動趨勢，將追蹤目標物維持在影像畫面的中心，以達到最佳追蹤及紀錄效果。

　　This research utilized the highly integrated SOPC to combine the color tracking module so as to implement a robust object tracking and motion estimation system. First, it would divide the binary image into M×N blocks matrix and define positions of X, and Y of each block. Then, this research would use accumulator to add up the binary value of every block and it would regard it as the scores for each block. After that, it would divide these scores by the total score of current frame. Then, the result could be defined as the weight value of all blocks. The sum of these weight values that were multiplied by blocks’ position is the actual location of the tracking object.
　　In this system, it also schemed out a rectangular region as the ROI of the tracking object. According to the result, it suggested that it would be better to process the ROI cooperate with novel image compression technology, JPEG200 or MPEG4 in the future. The storage capacity could be reduced for image and the surveillance system’s price could be cost down. The function of motion estimation can be used with active CCD camera. By the predicted trend of the tracking object, the object could be kept in the center of image and the best record and tracking could be achieved.

[01] M. D. Cordea, E. M. Petriu, N. D. Georganas, D. C. Petriu, Thomas E. Whalen, “Real-Time 2(1/2)-D Head Pose Recovery for Model-Based Video-Coding”, IEEE Transactions on Instrumentation and Measurement, Vol.50, No.4, pp.1007-1012, 2001.
[02] T-J. Yang, F-C. Wu, and M. Ouhyoung, “Real-Time 3D Head Motion Estimation in Facial Image Coding”, Proceedings of Multimedia Modeling Conference '98, pp. 50-51, 1998.
[03] V. Atienza, J. M. Valiente, “Face Tracking Algorithm Using Grey-Level Images”, International Conference On Signal Processing and Communications (SPC'2000), pp. 507-512, 2000.
[04] Z. Xiang, T. Yao, J. Li, and K. Yu, “Real-Time Facial Patterns Mining and Emotion Tracking”, Third International Conference on Advances in Web-Age Information Management, pp. 409 - 420, 2002.
[05] 譚永恆, “以數位影像處理技術做人臉自動追蹤系統之研究”, 國立成功大學電機工程學系, 1999.
[06] J. P. Mammen, S. Chaudhuri and T. Agrawal, “Simultaneous Tracking of Both Hands by Estimation of Erroneous Observations”, British Machine Vision Conf, 2001.
[07] J. Park, J. Yi, “Efficient Fingertip Tracking and Mouse Pointer Control for a Human Mouse”, International Conference on Computer Vision Systems 2003, pp.88-97, 2003.
[08] B. Maurin, O. Masoud, N. Papanikolopoulos, “Camera surveillance of crowded traffic scenes”, ITS America 12th Annual Meeting, pp.1- 28, 2002.
[09] T-S. Lee, E-M. Lee, H-T. Park, Y-K. Kwag, S-S. Lim, J-H. Baek, B-W. Hwang, “Implementation of Traffic Flow Measuring Algorithm Using Real-Time Dynamic Image Processing”, International Conference on Computer Vision Systems 2003 pp.78-87, 2003.
[10] 陳思源, “擷取及辨識在快車道上的摩托車”, 國立交通大學資訊工程系, 2002.
[11] 劉正一, “以電腦視覺為基礎之汽車行駛障礙物偵測及辨識”, 國立臺灣大學資訊工程學研究所, 1999.
[12] 白家榮, “十字路口行人的偵測及追蹤”, 國立臺灣師範大學資訊教育研究所, 2001.
[13] R. Cucchiara, C. Grana, A. Prati, R. Vezzani, “Computer Vision Techniques for PDA Accessibility of In-House Video Surveillance”, IWVS’03, pp. 87-97, 2003.
[14] 林昌廣, “嵌入式網路監視系統”, 國立交通大學電機與控制工程系, 2001 .
[15] 蔡忠松, “應用於家庭保全系統之低解析度紅外線影像辨識”, 國立中正大學電機工程研究所, 1999.
[16] S. Ye, W. J. Bell, “A simple video position-digitizer for studying animal movement patterns”, Journal of Neuroscience Methods volume 37,pp. 215-225,1991.
[17] S. S. Intille, J. W. Davis, and A. F. Bobick, “Real-Time Closed-World Tracking”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 697-703, 1997.
[18] R. García-Campos, J. Batlle, and R. Bischoff. “Architecture of an Object-based Tracking System Using Colour Segmentation”, 3rd International Workshop on Image and Signal Processing (IWISP'96), pp.299-302, 1996.
[19] J. Batlle, J. Martí, P. Ridao and J. Amat, “A New FPGA, DSP-Based Parallel Architecture for Real-Time Image Processing”, Real-Time Imaging archive Volume 8, pp. 345-356, 2002.
[20] S.S. Beauchemin, F. Nouboud and G. Roth, “FPGA implementation of Camus correlation Optical Flow Algorithm for real time images”, International Conference on Vision Interface, pp. 7-9, 2001.
[21] 陳裕仁, “多目標追蹤用即時動態彩色影像處理晶片之研製”, 義守大學電子工程學系, 2002.
[22] P. M. Curry, F. Morgan, L. Kilmarti, “Xilinx FPGA Implementationof a Pixel Processor for Object Detection Applications”, http://www.celoxica.com/techlib/files/CEL-W0307171JAD-29.pdf
[23] G. Gordon, T. Darrell, M. Harville, J. Woodfill, “Background estimation and removal based on range and color Proceedings”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 459-464, 1999.
[24] J. Konrad and M. Ristivojevi, “Video segmentation and occlusion detection over multiple frames”, SPIE Image and Video Communications and Process, vol. 5022, pp. 377-388, 2003.
[25] http://linux.wku.edu/~lamonml/algor/sort/quick.html
[26] S-F. Lin, S-S. Liao and J-Y. Chen, “Design of Fuzzy Predictor in the Moving Target Tracking System”, International Journal of Fuzzy Systems, Vol.3, No.1, 2001.
[27] 王智鳴, “利用Mosaic 技術擷取移動物體並使用主動式攝影機進行追蹤之研究”, 國立清華大學電機工程學系, 2000.
[28] http://www.blackice.com/colorspaceRGB.htm
[29] http://www.blackice.com/colorspaceHSI.htm
[30] Philips, SAA7113H Datasheet
[31] http://www.xilinx.com/products/logicore/alliance/perigee/ycrcb2rgb.pdf
[32] http://www.altera.com/literature/tt/tt_nios_hw_apex_20k200e.pdf
[33] http://www.altera.com/literature/ds/ds_nios_pio.pdf
[34] http://www.altera.com/literature/an/an284.pdf
[35] http://www.altera.com/literature/tt/tt_nios_ci.pdf
[36] http://www.altera.com/literature/an/an188.pdf
[37] Philips, SAA7121H Datasheet