臺灣博碩士論文加值系統

人機介面和手持式行動裝置技術在近年一直是重要的研究課題，相關成果也常在產學界做技術轉移，快速開發並銷售到消費市場，創造巨大產值。許多原本並非是多功能裝置的製造商，例如Apple 的iPhone、Google 的gPhone 等，都是近年國內外廠商急欲切入此產業之表現，顯示此研究領域之重要性。產學界均莫不積極推動相關研究，以期開發出具創意且實用之研究成果，在這個新興的領域嶄露角頭。日商任天堂公司所推出引起熱潮的體感遊戲機-Wii，其中遊戲主機所使用的遙控器使用了加速度感測器，可以做為使用者之動作辨識，並予以適當地回應。而加速度感測器的可應用範圍相當地廣泛，例如虛擬實境與遊戲互動、數位學習及教學輔助、數位家電控制、居家看護及安全監控、無障礙設備改善及醫療復健輔助等。
本論文嘗試使用加速度感測器的概念，設計一辨識人體3D動作特徵之演算法，並將之應用於生活中多種情境，如身分密碼驗證、演講教學輔助、多媒體家電控制、危險警報等，不僅改善以往人機介面、增進使用親合度。所開發之方法並可利用嵌入式系統的可攜性與運算能力，來架構成豐富的智慧型人機互動系統。

Human-Computer Interface for handheld mobile devices has been an important issue in recent years. Many newly developed HCI technologies have being transferred between research entities and industries, and being used in real life applications with huge success and profit, e.g. iPhone from Apple and the forthcoming gPhone from Google. Such successes also draw more and more academic and industrial groups into developing more creative and useful mobile devices. For example, the very popular Nintendo gaming console Wii uses a “Wii Remote”, which has an accelerometer, for a game to identify a user’s body motions and react accordingly. With motion detection ability, an accelerometer can be used in many applications, such as Virtual Reality and game interaction, e-learning and briefing assistant, IA control, security control and health care, improvement of free access for the disabled, and etc.
This research develops an algorithm that can recognize a person’s body motion patterns by using the data collected from an accelerometer and match them with some pre-taught patterns, used as, for example, passwords for user authentication, control signs for teaching assistant tools (virtual mouse, pointers, and etc.), commands for multimedia devices, emergency alarms for health care, and etc.
The aim is to develop friendly HCI and improve the usability of mobile devices by combing embedded technologies. The developed technologies can be used as the infrastructure of future intelligent HCI and devices, which will make human life much easier.

中文摘要 I
Abstract II
誌謝 IV
目錄 V
第一章 緒論 1
1.1. 研究背景 1
1.2. 研究動機與目的 3
1.3. 研究方法 4
1.4. 研究成果與貢獻 4
1.5. 論文架構 5
第二章 相關研究 6
2.1. 加速度感測器技術 6
2.2. 動作辨識原理 12
2.3. 技術應用探討 17
第三章�憟[速度動作辨識系統 25
3.1. 系統架構 25
3.1.1. 系統運作流程 26
3.1.2. 硬/軟體環境與架構 27
3.2. 動作辨識演算法 29
3.2.1. 訊號取樣與正規化 29
3.2.2. 特徵向量分析與轉換 30
3.2.3. 雜訊過濾與強度縮減 31
3.2.4. 計算動作向量最長共同子序列 31
3.2.5. 計算動作相似度 34
3.2.6. 門檻值判斷 34
3.2.7. 子功能應用 35
3.3. 技術應用 36
3.3.1. 身分密碼驗證 37
3.3.2. 教學演講輔助 39
3.3.3. 多媒體控制 40
3.3.4. 危險警報 41
第四章 系統實作測試 43
4.1. 系統開發環境介紹 43
4.2. 系統實作介面 44
4.2.1. 即時動作向量顯示圖 44
4.2.2. 身分密碼驗證 45
4.2.3. 教學演講輔助 47
4.2.4. 多媒體控制 48
4.2.5. 危險警報 50
第五章 實驗設計與結果 52
5.1. 實驗環境設定 52
5.2. 實驗I-身分密碼驗證 52
5.2.1. 實驗結果與討論 53
5.3. 實驗II-教學演講輔助 56
5.3.1. 實驗結果與討論 56
5.4. 實驗III-多媒體控制 58
5.4.1. 實驗結果與討論 59
5.5. 實驗IV-危險警報 61
5.5.1. 實驗結果 61
5.6. 綜合討論 63
第六章 結論與未來展望 64
6.1. 結論 64
6.2. 未來發展 64
參考文獻 65
自 述 67

[1].王宗一、鍾哲民、張書龍、羅聖心, "使用加速度感測器辨認3D動作之身分驗證機制", 2008 Symposium on Digital Life Technologies: Human- Centric Smart Living Technology, Tainan, 2008.
[2].Nintendo公司推出的動作辨識為主的遊戲主機-Wii (2006), http://wii.com/
[3].Google推出gPhone以及Android的相關計畫,http://www.openhandsetalliance.com
[4].Samsung推出的動作辨識操控的手機SCH-S31(2005), http://www.samsung.com/us/
[5].Sony Ericsson推出內建加速度感測器的手機F305 (2008), http://www.sonyericsson.com/cws/products/mobilephones/overview/f305?cc=hk&lc=zh
[6].Apple的觸控手機iPhone (2007),http://www.apple.com/iphone/
[7].ADXL330: Small, Low Power, 3-Axis ±3g iMEMS® Accelerometer, http://www.analog.com/en/mems-and-sensors/imems-accelerometers/adxl330/products/product.html
[8].Johnny Chung Lee (2007), Carnegie Mellon University 發表Wii 的相關應用,http://www.cs.cmu.edu/~johnny/projects/wii/
[9].賴盈霖,“結合GPS/重力感測器/陀螺儀　DR功能進駐導航裝置”, 新電子科技雜誌 2008 年 1 月號 262 期, http://www.mem.com.tw/coverstory_content.asp?sn=0801290009
[10].羅清岳, “車用電子－車用感測器發揮汽車駕駛安全極緻” (2006), DigiTimes.com,http://tech.digitimes.com.tw/print.aspx?zNotesDocId=9E061363FC99D481482571950033F2D2
[11].V.I. Pavlovic, R. Sharma, and T.S. Huang (1997), “Visual interpretation of hand gestures for human-computer interaction: a review,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.19, No.7.
[12].D.S. Hirschberg (1975), A Linear Space Algorithm for Computing Maximal Common Subsequence, Communication of ACM, Vol.18, pp.341-343
[13].Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77 (2), 257--286.
[14].Junker, H., Amft, O., Lukowicz, P., Tröster, G.: Gesture Spotting with Body-Worn Inertial Sensors to Detect User Activities. In: Pattern Recognition: The Journal of the Pattern Recognition Society. Vol 41:6, 2008, Elsevier
[15].Yen-Ping Chen, Jhun-Ying Yang, Shun-Nan Liou, Gwo-Yun Lee, and Jeen-Shing Wang, “Online Classifier Construction Algorithm for Human Motion Detection Using an Accelerometer,” accepted by Applied Mathematics and Computation, 2008.
[16].M. Rehm, N. Bee, and E. André: Wave Like an Egyption - Accelerometer Based Gesture Recognition for Culture Specific Interactions. In: Proceedings of HCI 2008, Culture, Creativity, Interaction, 2008.
[17].Schlömer, T., Poppinga, B., Henze, N., and Boll, S. 2008. Gesture recognition with a Wii controller. In Proceedings of the 2nd international Conference on Tangible and Embedded interaction (Bonn, Germany, February 18 - 20, 2008). TEI '08. ACM, New York, NY, 11-14.
[18]."Determination of simple thresholds for accelerometry-based parameters for fall detection", Kangas. M., Konttila. A., Winblad. I., Jamsa. T., Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE 22-26 Aug. 2007 Page(s):1367 - 1370
[19].Schou, T. and Gardner, H. J. 2007. A Wii remote, a game engine, five sensor bars and a virtual reality theatre. In Proceedings of the 2007 Conference of the Computer-Human interaction Special interest Group (Chisig) of Australia on Computer-Human interaction: Design: Activities, Artifacts and Environments (Adelaide, Australia, November 28 - 30, 2007). OZCHI '07, vol. 251. ACM, New York, NY, 231-234.
[20].Sreedharan, S., Zurita, E. S., and Plimmer, B. 2007. 3D input for 3D worlds. In Proceedings of the 2007 Conference of the Computer-Human interaction Special interest Group (Chisig) of Australia on Computer-Human interaction: Design: Activities, Artifacts and Environments (Adelaide, Australia, November 28 - 30, 2007). OZCHI '07, vol. 251. ACM, New York, NY, 227-230.
[21].Mohammad Shirali-Shahreza (2006). “Login to Internet Websites by Next Generation Game Console＂, In Proc. of 2006 2nd IEEE/IFIP Intl Conf. on Internet, Page:1 – 4.
[22].Kela, J., Korpipää, P., Mäntyjärvi, J., Kallio, S., Savino, G., Jozzo, L., and Marca, D. 2006. Accelerometer-based gesture control for a design environment. Personal Ubiquitous Comput. 10, 5 (Jul. 2006), 285-299.
[23].Ward, J. A., Lukowicz, P., and Tröster, G. 2005. Gesture spotting using wrist worn microphone and 3-axis accelerometer. In Proceedings of the 2005 Joint Conference on Smart Objects and Ambient intelligence: innovative Context-Aware Services: Usages and Technologies (Grenoble, France, October 12 - 14, 2005). sOc-EUSAI '05, vol. 121. ACM, New York, NY, 99-104.
[24].Wilson D.H., and Wilson A. "Gesture Recognition Using the XWand," Tech. Report CMU-RI-TR-04-57, Robotics Institute, Carnegie Mellon University, April 2004.
[25].Qt: Cross-Platform Rich Client Development Framework, http://trolltech.com/products/qt