(3.231.166.56) 您好!臺灣時間:2021/03/08 12:05
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:郭禕偉
研究生(外文):YiWei Guo
論文名稱:基於慣性測量裝置之動作辨識與評估:以太極拳動作為例
論文名稱(外文):Movement Recognition and Evaluation Based on Inertial Measurement Unit: Use Tai-Chi Chuan Movement as an Example
指導教授:洪一平洪一平引用關係
口試日期:2017-07-20
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊網路與多媒體研究所
學門:電算機學門
學類:網路學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:英文
論文頁數:42
中文關鍵詞:慣性測量裝置動作辨識太極拳學習系統深度攝影機頭戴式顯示器
外文關鍵詞:Inertial Measurement UnitMovement RecognitionTai-Chi Chuan LearningDepth CameraHead-mounted Display
相關次數:
  • 被引用被引用:0
  • 點閱點閱:119
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
近年來,隨著多媒體設備的發展,特別是頭戴式顯示器的出現,運動的學習已經不再局限於進行課堂學習,由教練進行指導,而是可以透過觀看多媒體教學影片進行學習。然而進行多媒體學習雖然很方便,但卻不能及時獲得像真實教練引導的回饋和互動性,同時也無法掌握自己練習的準確性和完整度。
基於以上問題,本研究提出了一套基於慣性測量裝置進行動作辨識和評估的系統,在本研究中主要以觀看頭戴式顯示器的動作引導,進行十六式太極拳動作練習為例。本研究利用搭載三軸慣性測量的智慧型手錶對太極拳動作進行辨識和評估,可以讓太極拳学生更加準確的了解自己練習的完整度。進而可以讓太極拳学生在沒有教練的情況下,使用本系統獨立完成太極拳動作的練習,並獲得相應練習的完整度回饋。
相較於以往研究根據用戶練習數據進行機器學習,獲得太極拳動作的模型不同,本研究採用深度攝影機技術來獲得太極拳教練手腕的示範動作,使得每個招式的模型更加精準。之後我們根據学生的練習數據進行辨識,獲得了極高的正確率。最後,我們應用機器學習的方式,根據学生數據和教練動作的差距,計算学生練習的完整度,給予学生完成情況的評估,以利太極拳練習。
In recent years, with the development of multimedia equipment, especially the appearance of head-mounted display, sports learning is no longer limited to classroom learning, with a coach to guide your movement, but can through watching multimedia teaching videos to learn. However, although the multimedia learning is very convenient, but student cannot get the feedback from the coach, also student cannot get the accuracy and completeness of their practice.
Based on the above problems, our research presents a system based on inertial measurement unit for movement recognition and evaluation. In our research, we mainly let student watching a Tai-Chi Chuan learning video with sixteen movements through the head-mounted display. Then we use a smart watch with three-axis inertia measurement unit for Tai-Chi Chuan movement recognition and evaluation. Student can get more accurate understanding of their own exercise integrity during Tai-Chi Chuan practice. And then student can use the system to complete the practice of Tai-Chi Chuan without a coach on their side, and they can get the evaluation from the completeness feedback.
Different with the previous study, Tai-Chi Chuan movement model is using practitioner practice data for machine learning. Our research uses depth camera to get the Tai-Chi coach’s movement, making each movement model more accurate. We got a very high accuracy precision using different students practice data for recognition. Finally, we use the machine learning to calculate the completion of the student practice according to the difference between student movement and coach movement. Then we give student score as evaluation in order to help them finish the Tai-Chi Chuan practice.
口試委員會審定書 I
誌謝 II
中文摘要 III
ABSTRACT IV
CONTENTS VI
LIST OF FIGURES IX
LIST OF TABLES X
Chapter 1 Introduction 1
Chapter 2 Related Work 4
2.1 IMU Applications 4
2.2 Movement Recognition 5
2.3 Tai-Chi Chuan Training System 6
Chapter 3 Movement Recognition and Evaluation 9
3.1 Insight of Tai-Chi Chuan Movement 9
3.2 Coach Movement Based on Vicon 10
3.2.1 Coach Movements Model 10
3.2.2 Coach Wrist Movements 11
3.3 Coach Movements Processing 11
3.3.1 Wrist Movement 11
3.3.2 Acceleration Component 12
3.3.3 Gravity Component 14
3.4 Student Data Acquisition 15
3.4.1 Student Hardware 15
3.4.2 Data Acquisition Processing 17
3.5 Movement Recognition 18
3.5.1 Sensor Axes Alignment 18
3.5.2 Dynamic Time Warping 19
3.5.3 DTW limitations 20
3.5.4 Constrained Dynamic Time Warping 22
3.5.5 Nearest Neighbor Movement Recognition 23
3.6 Evaluation Based on Feedback Techniques 24
3.6.1 Feedback Techniques 24
3.6.2 Support Vector Classification 26
Chapter 4 Recognition and Evaluation System 27
4.1 System Scenarios 27
4.2 System Processing 28
4.3 System Evaluation 31
4.3.1 Experiment Design 31
4.3.2 Experiment Result 34
Chapter 5 Discussion 36
Chapter 6 Conclusion and Future Work 38
REFERENCES 40
[1]Hong, Y., & Li, J. X. (2007). Biomechanics of Tai Chi: a review. Sports biomechanics, 6(3), 453-464.
[2]Chua, P. T., , R., Daly, B., Hu, N., Schaaf, R., Ventura, D., ... & Pausch, R. (2003, March). Training for physical tasks in virtual environments: Tai Chi. In Virtual Reality, 2003. Proceedings. IEEE (pp. 87-94). IEEE.
[3]Bächlin, M., Förster, K., & Tröster, G. (2009, September). SwimMaster: a wearable assistant for swimmer. In Proceedings of the 11th international conference on Ubiquitous computing (pp. 215-224). ACM.
[4]Ladha, C., Hammerla, N. Y., Olivier, P., & Plötz, T. (2013, September). ClimbAX: skill assessment for climbing enthusiasts. In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing (pp. 235-244). ACM.
[5]Yang, D., Tang, J., Huang, Y., Xu, C., Li, J., Hu, L., ... & Liu, H. (2017, March). TennisMaster: an IMU-based online serve performance evaluation system. In Proceedings of the 8th Augmented Human International Conference (p. 17). ACM.
[6]Smart Tennis Sensor for Tennis Rackets: http://www.smarttennissensor.sony.net/
[7]Akl, A., & Valaee, S. (2010, March). Accelerometer-based gesture recognition via dynamic-time warping, affinity propagation, & compressive sensing. In Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on (pp. 2270-2273). IEEE.
[8]Galluzzi, V., Herman, T., & Polgreen, P. (2015, April). Hand hygiene duration and technique recognition using wrist-worn sensors. In Proceedings of the 14th International Conference on Information Processing in Sensor Networks (pp. 106-117). ACM.
[9]Zhang, X., Chen, X., Li, Y., Lantz, V., Wang, K., & Yang, J. (2011). A framework for hand gesture recognition based on accelerometer and EMG sensors. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 41(6), 1064-1076.
[10]Liu, J., Zhong, L., Wickramasuriya, J., & Vasudevan, V. (2009). uWave: Accelerometer-based personalized gesture recognition and its applications. Pervasive and Mobile Computing, 5(6), 657-675.
[11]Wilson, C. J., & Datta, S. K. (2001). Tai Chi for the prevention of fractures in a nursing home population: An economic analysis. JCOM-WAYNE PA-, 8(3), 19-28.
[12]Chua, P. T., Crivella, R., Daly, B., Hu, N., Schaaf, R., Ventura, D., ... & Pausch, R. (2003, March). Training for physical tasks in virtual environments: Tai Chi. In Virtual Reality, 2003. Proceedings. IEEE (pp. 87-94). IEEE.
[13]Jin, Y., Hu, X., & Wu, G. (2012). A tai chi training system based on fast skeleton matching algorithm. In Computer Vision–ECCV 2012. Workshops and Demonstrations (pp. 667-670). Springer Berlin/Heidelberg.
[14]Lee, J. D., Hsieh, C. H., & Lin, T. Y. (2014, January). A Kinect-based Tai Chi exercises evaluation system for physical rehabilitation. In Consumer Electronics (ICCE), 2014 IEEE International Conference on (pp. 177-178). IEEE.
[15]Lu, K. Y. (2016) Developing a Depth-Camera-Based Training System with Weight-Transfer Feedback for Practicing Tai-Chi Chuan. Graduate Institute of Computer Science and Information Engineering, National Taiwan University, 1-38.
[16]Sonymobile.com. “Sony White paper on SWR50 Smartwatch 3”: http://www-support-downloads.sonymobile.com/swr50/whitepaper_EN_swr50_smartwatch3_2.pdf
[17]Keogh, E. (2002, August). Exact indexing of dynamic time warping. In Proceedings of the 28th international conference on Very Large Data Bases (pp. 406-417). VLDB Endowment.
[18]Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A practical guide to support vector classification.
[19]Lawrence R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE, 77 (2), p. 257–286, February 1989.
[20]Online TCC learning website : http://www.beginnerstaichi.com/
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔