本論文係探討以FPGA設計實現小型人形機器人之模糊控制與視覺處理系統。所有的運算皆以FPGA為控制與處理中心。影像畫面由CMOS感測器擷取，過濾顏色資訊並以多層中值法降低雜訊干擾。視覺處理系統的主要功能為物體辨識與字元辨識。物體辨識主要以隨機測圓法辨識目標球體，配合模糊控制追蹤實現策略。字元辨識以影像區塊切割處理將所需字元位置定位，用字素比例法對字元作取樣編碼，最後經由改良式樣板比對法完成字元之辨識，再將辨識出的結果藉由語音模組播放。控制策略包括PK、保齡球、單字辨識和數字比大小。透過驅動兩顆小型伺服馬達控制CMOS感測器，使機器人追蹤特定目標物，並藉由影像分析場地上的狀況來決定機器人的動作。本論文會針對影像方面做詳細的說明，包含物體與字元辨識的演算法，控制策略以模糊控制器追蹤目標物的方法以及各項競賽項目。最後透過實驗與競賽結果，可充分展現本小型人形機器人的辨識能力及其優越的效能與強健性。

This thesis mainly covers the development of a FPGA-based fuzzy controller and image processing system for a small-sized humanoid robot. All the computations are operated on an FPGA board. The image is captured by the CMOS image sensor, and the color detection will filter out the color information. The MLM (Multi-Level Median) method is utilized to reduce the noise. The main algorithm of the image processing system is recognition of the object and characters. The object recognition identifies the target ball via the RCD (Randomized Circle Detection) method and performs the strategy with fuzzy-based tracking. Character recognition then locates the characters by region segmentation and encodes them with the pixel ratio method. And then the improved template matching method is used on the recognition, and the results are spoken by the TTS (Text-To-Speech) module. There are four control strategies presented in this thesis, which are the PK event, the bowling event, the vocabulary recognition, and the numbers comparison. Our robot can track specific objects via the CMOS sensor controlled by two small servomotors. The motions of the robot are decided by analyzing the condition of the environment from the captured image. This thesis focuses on the vision system, including the algorithm of the object, and character recognition. Furthermore, it describes the method of the object tracking by the fuzzy controller and events in the competition in detail. Finally, the results of the experiment show the capability of the vision system and the efficiency and validity in the 2007 IEEE International Student Experimental Hands-on Project Competition.

[1]I. W. Park, J. Y. Kim, S. W. Park and J. H. Oh, “Development of humanoid robot platform KHR-2 (KAIST Humanoid Robot-2),” in Proc. IEEE/RAS Int. Conf. on Humanoid Robots, vol. 1, pp. 292-310, Nov. 2004.
[2]K. Kaneko, F. Kanehiro, S. Kajita, H. Hirukawa, T. Kawasaki, M. Hirata, K. Akachi and T. Isozumi, “Humanoid robot HRP-2,” in Proc. IEEE Int. Conf. on Robotics and Automation, vol. 2, pp. 1083-1090, Apr. 2004.
[3]H. H. Lund, “Modern artificial intelligence for human-robot interaction,” in Proc. IEEE, vol. 92, Issue 11, pp. 1821-1838, Nov. 2004.
[4]J. A. Adams and H. K. Keskinpala, “Analysis of perceived workload when using a PDA for mobile robot teleoperation,” in Proc. IEEE Int. Conf. on Robotics and Automation, vol. 4, pp. 4128-4133, Apr. 2004.
[5]J. Ido, Y. Matsumoto, T. Ogasawara and R. Nisimura, “Humanoid with interaction ability using vision and speech information,” in Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 1316-1321, Oct. 2006.
[6]FIRA, http://www.fira.net
[7]J. Y. Kim, I. W. Park, J. Lee and J. H. Oh, “Experiments of vision guided walking of humanoid robot, KHR-2,” in Proc. IEEE-RAS Int. Conf. on Humanoid Robots, pp. 135-140, Dec. 2005.
[8]S. Palnitkar, Verilog HDL A Guide to Digital Design and Synthesis, PRENTICE-HALL, Inc. 1996.
[9]R. Wichman and Y. Neuvo, “Multilevel median filters for image processing,” in Proc. IEEE Int. Symposium Circuits and Systems, vol. 1, pp. 412-415, Jun. 1991.
[10]A. Taguchi and Y. Murata, “Improving the performance of multilevel median filters for image processing,” in Proc. 35th Midwest Symposium Circuits and Systems, vol. 1, pp. 369-372, Aug. 1992.
[11]J. Luo and D. Crandall, “Color object detection using spatial-color joint probability functions,” IEEE Transactions on Image Processing, vol. 15, Issue 6, pp. 1443-1453, Jun. 2006.
[12]S. Suthaharan, “Image and edge detail detection algorithm for object-based coding,” Pattern Recognition Letters, vol. 21, Issues 6-7, pp. 549-557, Jun. 2000.
[13]S. T. Acton and D. P. Mukherjee “Area operators for edge detection,” Pattern Recognition Letters, vol. 21, Issue 8, pp. 771-777, Jul. 2000.
[14]Y. H. Yua and C. C. Chang, “A new edge detection approach based on image context analysis,” Image and Vision Computing, vol. 24, Issue 10, pp. 1090-1102, Oct. 2006.
[15]X. Wang, “Laplacian operator-based edge detectors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, Issue 5, pp. 886-890, May 2007.
[16]P. E. Trahanias and A. N. Venetsanopoulos, “Vector order statistics operators as color edge detectors,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 26, Issue 1, pp. 135-143, Feb. 1996.
[17]M. K. Quweider, J. D. Scargle and B. Jackson, “Grey level reduction for segmentation, threshholding and binarisation of images based on optimal partitioning on an interval,” Image Processing, IET, vol. 1, Issue 2, pp. 103-111, Jun. 2007.
[18]Y. T. Su, T.-H. S. Li, C. L. Hsu, M. F. Lu, C. Y. Hu and S. H. Liu, “Omni-directional vision-based control strategy for humanoid soccer robot,” in Proc. IEEE Int. Conf. on Industrial Electronics Society, pp. 2950-2955, Nov. 2007.
[19]M. F. Lu, Design and implementation of SOPC based image and control system for small size humanoid robot, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, Jun. 2007.
[20]S. C. Pei and J. H. Horng, “Circular arc detection based on Hough transform,” Pattern Recognition Letters, vol. 16, Issue 6, pp. 615-625, Jun. 1995.
[21]Y. Qiao and S. H. Ong, “Connectivity-based multiple-circle fitting,” Pattern Recognition, vol. 37, Issue 4, pp. 755-765, Apr. 2004.
[22]T. C. Chen and K. L. Chung, “An efficient randomized algorithm for detecting circles,” Computer Vision and Image Understanding, Academic Press, pp. 172-191, 2001.
[23]B. Lamiroy, L. Fritz and O. Gaucher, “Robust circle detection,” in Proc. Int. Conf. on Document Analysis and Recognition, vol. 1, pp. 526-530, 2007.
[24]C. Su and R. M. Haralick, “Recursive erosion, dilation, opening, and closing transforms,” IEEE Transactions on Image Processing, vol. 4, Issue 3, pp. 335-345, Mar. 1995.
[25]J. Y. Gil and R. Kimmel, “Efficient dilation, erosion, opening, and closing algorithms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, Issue 12, pp. 1606-1617, Dec. 2002.
[26]B. Bödvarssona, S. Klima, M. Mørkebjerga, S. Mortensena, C.H. Yoona, J. Chena, J.R. Maclarena, P.K. Lutherb, J.M. Squirec, P.J. Bonesa and R.P. Millane, “A morphological image processing method for locating myosin filaments in muscle electron micrographs,” Image and Vision Computing, vol. 26, Issue 8, pp. 1073-1080, Aug. 2008.
[27]T. Gevers, “Robust Segmentation and Tracking of Colored Objects in Video,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, Issue 6, pp. 776-781, Jun. 2004.
[28]R. G. Casey and E. Lecolinet, “A survey of methods and strategies in character segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, Issue 7, pp. 690-706, Jul. 1996.
[29]K. Hirota and Y. Kyo, “A target tracking robot based on fuzzy control,” in Proc. IEEE International Workshop on Robot and Human Communication, pp. 335-340, Sep. 1992.
[30]A. Jain, “Object tracking using fuzzy logic for Khepera-II robot, “ Illinois Journal of Undergraduate Research at the University of Illinois at Urbana-Champaign, vol. 1, 2006.
[31]I. Harmati and K. Skrzypczyk, “Robot team coordination for target tracking using fuzzy logic controller in game theoretic framework,” Robotics and Autonomous Systems, in Press, Corrected Proof, Feb. 2008.
[32]X. Fan, N. Zhang and S. Teng, “Trajectory planning and tracking of ball and plate system using hierarchical fuzzy control scheme,” Fuzzy Sets and Systems, vol. 144, Issue 2, pp. 297-312, Jun. 2004.
[33]S. H. Hahn, J. H. Lee and J. H. Kim, “A study on utilizing OCR technology in building text database,” in Proc. Int. Workshop on Database and Expert Systems Applications, pp. 582-586, Sep. 1999.
[34]A. Busch, W. W. Boles and S. Sridharan, “Texture for script identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, Issue 11, pp. 1720-1732, Nov. 2005.
[35]LM386N-3 IC, http://cache.national.com/ds/LM/LM386.pdf
[36]C. R. David and C. Jordi, “Camera-based digit recognition system,” in Proc. IEEE Int. Conf. Electronics, Circuits and Systems, pp. 756-759, Dec. 2006.