目前大部分的立體視覺伺服系統，其應用範圍多半以工業自動化為主，較少以娛樂或休閒為導向作開發，且主要開發核心皆以個人電腦為基本架構，造成系統成本過高且體積龐大，而數位訊號處理器（Digital Signal Processor, DSP）功能的提升，強化運算效能與增加儲存容量，因此可用來取代以個人電腦為主的立體視覺伺服系統。
本研究利用德州儀器公司所生產之數位訊號處理器DM648，作為系統之開發平台，整合取像攝影機與六軸機械臂，建構一套三維空間的立體視覺伺服控制系統。
研究中分為影像處理與運動控制二個系統，由影像處理系統計算出球的中心座標，將結果通知運動控制系統，規劃六軸機械臂以擬人的姿態進行追蹤紅球；經由實際測試，確實能正確計算出球之位置，進而能準確地進行追蹤並預備抓球。

Most of the stereo vision systems in are currently designed for the industrial automation application. Few of them are created for recreational or leisure purposes, and besides, the core of their development is based on personal computer, resulting in the enormous system cost and huge volume. However, several functional upgrades of digital signal processor (DSP), including computing enhancement and increase of storage capacity, have enabled DSP to replace the personal computer-based Visual Servo Systems.
The research utilized the DSP provided by Texas Instrument as the platform for system development, integrating visual capture cameras and Six-link robotic arms. build a three-dimensional visual servo control system.
The research is divided into visual processing and motion control sub-systems. Visual processing sub-system will calculate the location coordinates of the ball, and then notify the motion control system the result, to formulate the robot arm in anthropomorphic ways to catch the ball. From actual field tests of this research, the system proves that it can accurately predict the catching area of the ball and then perform exact catching movements.

[1] Palacin, J., Sanuy, A., Clua, X., Chapinal, G., Bota, S., Moreno, M.,
and Herms, A., “Autonomous mobile mini-robot with embedded
CMOS vision system,”Proc. of 2002 28th IEEE Annual Conf. on
Industrial Electronics Society, Seville, Spain, vol. 3, pp. 2439-2444
(5-8 Nov. 2002).
[2] Corley, D., and Jovanov, E., “A low power intelligent
video-processingsensor,” Proc. of 2002 the Thirty-Fourth
Southeastern Symposium on System Theory, pp. 176-178 (2002).
[3] Andrian, H., and Song, K. T., “Embedded CMOS imaging system for
real-time robotic vision,” Proc. of 2005. (IROS 2005). 2005
IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Alberta,
Canada, pp. 1096-1101 (2-6 Aug.2005).
[4] Li, D., Jiang, Y., and Chen, G., “A Low Cost Embedded Color Vision
System Based on SX52,” Proc. of 2006 IEEE International Conf. on
Information Acquisition, Weihai, China, pp. 883-887 (20-23 Aug.
2006).
[5] Yanling Zhao, Peng Wang, Huanrui Hao, Xianli Liu “The Embedded
Control System of Vision Inspecting Instrument for Steel Ball Surface
Defect,” Proc. of 2008. CCDC 2008. Chinese Control and Decision
Conference, Yantai,Shandong, pp. 3469-3474 (2-4 July 2008).
[6] Zhang, Y., “Design of robot monocular vision based on DSP and
CMOS image sensor,” Proc. of ICALIP 2008 International Conf. on
Audio, Language and Image Processing, Shanghai, China, pp.
614-618 (7-9 July 2008).
[7] Jun Yu, Peihuang Lou, Xing Wu, “A Dual-Core Real-Time Embedded
System for Vision-Based Automated Guided Vehicle,” Proc. of 2009
CASE. 2009 IITA International Conf. on Control, Automation and
Systems Engineering, Zhangjiajie, pp.207-211 (11-12 July 2009).
[8] Huang, S. J., Wu, S. S., “Vision-Based Robotic Motion Control for
Non-autonomous Environment,” Journal of Intelligent and Robotic
Systems:Theory and Application, Vol. 54, No. 5, pp. 733-754 (2009).
[9] “TMS320DM647/DM648 DSP Subsystem User's Guide”,Texas
Instrument(2007).
[10] “DM648 EVM C2 - Technical reference guide”, Texas
Instrument(2007).
[11] “TMS320DM647/TMS320DM648 Digital Media Processors” Texas
Instrument(2007).
[12] “Texas Instruments，TMS320C64x／C64x+DSP CPU and
Instruction Set Reference Guide”, Texas Instrument(2006).
[13] " TI, Code Composer Studio Development Tool v3.3 Getting Started
Guide, Literature Number SPRUE509H, October 2006"( 2003).
[14] “鐘國亮，影像處理與電腦視覺，台灣東華書局股份有限公司，台北，第一章（2006）。
[15] 晉茂林，機器人學，五南圖書出版股份有限公司，台北，第36-188頁 (1999)。
[16] “E. R. Davies, Machine Vision: Theory, Algorithms, Practicalities, 3rd Edition, Elsevier Science and Technology, pp. 445-454, 609-619, January 2005.
[17]D. A. Forsyth and J. Ponce, Computer Vision: A Modern Approach,
Prentice Hall, pp. 215-250, January 2003.
[18]L. D. Stefano, M. Marchionni and S. Mattoccia, “A Fast Area-Based
Stereo Matching Algorithm,” Image and Vision Computing, Vol. 22, No.
12, pp. 983-1005, 2004.
[19] D. Marr and T. Poggio, “Cooperative Computation of Stereo Disparity,”Science, Vol. 194, pp. 283-287, 1976.
[20] D. Schreiber, B. Alefs and M. Clabian, “Single Camera Lane Detection and Tracking,” IEEE Conference on Intelligent Transportation Systems, pp. 13-16, 2005.
[21] 陳毓淞，車輛前景移動物體影像的即時偵測系統之實現，國立臺灣科技大學電機工程研究所，2006.
[22] A. N. Ansari and M. Abdel-Mottaleb, “Automatic Facial Feature Extraction and 3D Face Modeling Using Two Orthogonal Views with Application to 3D Face Recognition,” Pattern Recognition, Vol. 38, No. 12, pp. 2549-2563, 2005.
[23] A. P. Tirumalai, B. G. Schunck and R. C. Jain, “Dynamic Stereo with
Self-Calibration,” IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol. 14, pp. 1184-1189, 1992.
[24] W. Y. Yau and H. Wang, “Fast Relative Depth Computation for an
Active Stereo Vision System,”Real-Time Imaging, Vol. 5, pp.
189-202,1999.
[25] Y. Ma, S. Soatto, J. Kosecka and S. Sastry, An Invitation to 3-D Vision:From Images to Geometric Models, Springer-Verlag, New York, pp.117-124, 391-394, November 2003.
[26] S. T. Barnard and W. B. Thompson, “Disparity Analysis of Images,”
IEEE Transactions on Pattern Analysis and Machine Intelligence,
Vol.2,pp. 330-340, 1980.
[27] Z. Zhang, “A Flexible New Technique for Camera Calibration, ” Technical Report MSR-TR-98-71, Microsoft Research, December 2, 1998.
[30] Texas Instruments Inc., TL16C752B 3.3-V Dual UART with 64-byte
FIFO, August 2000.
[31] 王韻婷，以DSP實現及時雙眼視覺之目標物量測系統，國立臺灣科技大學電機工程研究所，2007.