人體姿勢技術是一項熱門的研究議題，過去利用影像辨識技術來辨識人體姿勢的辨識系統已經發展成熟，但在學術領域或專業應用上使用這種方式的辨識系統需要龐大的運算量以及昂貴的週邊設備，使得這種系統無法普及於一般大眾所能使用到的範疇。因此，在這篇論文中，我們設計了一套只有使用三軸加速度計搭配無線感測網路的系統，透過裝設在使用者四肢的三軸加速度計，判斷人體四肢動作，再利用無線感測網路去操作一台人型機器人，使得人型機器人可以作出與使用者相似的動作。整個系統主要分成三個部分，分別為人體穿戴式感測器部分、主控台部分以及機器人部分。在人體穿戴式感測器部分，使用者四肢以及欲判斷動作的部分皆裝上無線感測器及三軸加速度計模組，並將感測到的重力加速度資料傳送給無線感測器，無線感測器再利用802.15.4的MAC層傳輸協定傳送給主控台的無線感測器接收端。在主控台部分，有兩個無線感測器分別負責802.15.4協定的接收以及發送，另有一台電腦接收來自無線感測器接收端的資料，並透過以球座標系(spherical coordinate system)為基底的動作辨識方法，決定機器人該做的動作。在機器人部分，有一顆無線感測器負責接收由主控台發送的動作訊息，並將訊息傳送給機器人，使得機器人作出對應使用者的動作。

Because of the rich potential of the gesture recognition technology, the research about gesture recognition is always a popular issue. Traditionally, the gesture recognition system was implemented by the method of image recognition, which is a classic and mature technique, but the image recognition system not only spends a lot of computing time but also needs expensive devices. So we design and implement a system to recognize the human gesture and use a humanoid robot to demonstrate this system. This system consists of wireless sensor networks, triaxial acceleration sensors, and a humanoid robot. The whole system can be divided into three subsystems: 1) Wearable Sensors, 2) Host, and 3) Humanoid Robot. In the Wearable Sensors, the sensor nodes with triaxial acceleration sensor are installed in the human limbs and transmit acceleration data to Host. In the Host, a PC or laptop receives triaxial data and then recognizes the human gesture. After that, Host transmits a command message to the Humanoid Robot. In the Humanoid Robot, the robot receives command message from Host, and does the same gestures as user does.

[1] Z.-G. Xu and H.-L. Zhu, "Vision-based Detection of Dynamic Gesture," in Proceedings of IEEE International Conference on Test and Measurement (ICTM 2009), pp. 223-226, Hong Kong, China, December 2009.
[2] Microsoft Corp., Kinect, http://www.xboxkinection.com/
[3] L. Rabiner and B. Juang, "An Introduction to Hidden Markov Models," IEEE ASSP Magazine, Vol. 3, No. 1, pp. 4-16, January 1986.
[4] I. F. Akyildiz, W. Su, Y. Sankarasubramaniam, and E. Cayirci, "A Survey on Sensor Networks," IEEE Communications Magazine, Vol. 40, No. 8, pp. 102-114, August 2002.
[5] C.-C. Chang, "Design and Implementation of Wireless Sensor Platforms and Operating System," Ph. D Dissertation, Computer Sciences and Information Engineering, National Central University, 2010.
[6] A. F. Bobick and J. W. Davis, "The Recognition of Human Movement Using Temporal Templates," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 3, pp. 257-267, March 2001.
[7] S.-W. Lee, "Automatic Gesture Recognition for Intelligent Human-robot Interaction," in Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR 2006), pp. 645-650, Southampton, UK, April 2006.
[8] J. L. Raheja, R. Shyam, U. Kumar, and P. B. Prasad, "Real-time Robotic Hand Control Using Hand Gestures," in Proceedings of the second International Conference on Machine Learning and Computing (ICMLC 2010), pp. 12-16, Bangalore, India, February 2010.
[9] Nintendo Co., Ltd, Wii, http://wii.nintendo.com
[10] P.-Y. Chiang, M.-C. Kuo, J. Lee, and C.-C. J. Kuo, "WiiStick: Enhancing Motion Recognition Capability for Wii Systems," in Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS 2009), pp. 1445-1448, Taipei, Taiwan, May 2009.
[11] J. K. Perng, B. Fisher, S. Hollar, and K. S. J. Pister, "Acceleration Sensing Glove (ASG)," in Proceedings of the third International Symposium on Wearable Computers (ISWC 1999), pp. 178-180, San Francisco, California, USA, October 1999.
[12] Y.-C. Tseng, C.-H. Wu, F.-J. Wu, C.-F. Huang, C.-T. King, C.-Y. Lin, J.-P. Sheu, C.-Y. Chen, C.-Y. Lo, C.-W. Yang, and C.-W. Deng, "A Wireless Human Motion Capturing System for Home Rehabilitation," in Proceedings of the 10th International Conference on Mobile Data Management: Systems, Services and Middleware (MDM 2009), pp. 359-360, Taipei, Taiwan, May 2009.
[13] H. Tanaka, R. Kimura, and S. Ioroi, "Equipment Operation by Motion Recognition with Wearable Wireless Acceleration Sensor," in Proceedings of the third International Conference on Next Generation Mobile Applications, Services and Technologies (NGMAST 2009), pp. 114-118, Cardiff, Wales, UK, September 2009.
[14] M. Fujimoto, N. Fujita, Y. Takegawa, T. Terada, and M. Tsukamoto, "A Motion Recognition Method for a Wearable Dancing Musical Instrument," in Proceedings of the 13th International Symposium on Wearable Computers (ISWC 2009), pp. 11-18, Linz, Austria, September 2009.
[15] J. Rao, T. Gao, Z. Gong, and Z. Jiang, "Low Cost Hand Gesture Learning and Recognition System Based on Hidden Markov Model," in Proceedings of the second International Symposium on Information Science and Engineering (ISISE 2009) pp. 433-438, Shanghai, China, December 2009.
[16] H. Junker, O. Amft, P. Lukowicz, and G. Troster, "Gesture Spotting with Body-Worn Inertial Sensors to Detect User Activities," Pattern Recognition, Vol. 41, No. 6, pp. 2010-2024, December 2008.
[17] A. Zinnen and B. Schiele, "A New Approach to Enable Gesture Recognition in Continuous Data Streams," in Proceedings of the 12th International Symposium on Wearable Computers (ISWC 2008), pp. 33-40, Pittsburgh, Pennsylvania, September 2008.
[18] Mathematics Wikia, "Spherical Coordinate System," http://math.wikia.com/wiki/Spherical_coordinate_system