簡易檢索 / 詳目顯示

回結果列表
研究生： 陳姮妤
Heng-Yu Chen
論文名稱： 基於混合式DTW之 羽球動作辨識演算法開發
Development of Badminton Stroke Recognition Based on Hybrid DTW
指導教授： 林淵翔
Yuan-Hsiang Lin
口試委員: 陳筱青
Hsiao-Ching Chen
陳維美
Wei-Mei Chen
學位類別： 碩士
Master
系所名稱： 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 中文
論文頁數： 71
中文關鍵詞： 動態時間歸整 、動作辨識 、慣性感測器 、羽球
外文關鍵詞： Dynamic Time Warping, stroke recognition, inertial measurement unit, badminton
相關次數： 點閱：372  下載：1 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  •  上一筆

    • 目前羽球運動為臺灣受歡迎的十大運動之一，許多人會利用錄影的方式記錄自己的運動過程，分析揮拍的動作球種，如自我訓練的目標設定，或羽球選手藉由動作分析進行戰術討論。然而利用錄影的方式除了會受到攝影設備的品質或視線的死角影響之外，重要的是，需要花更多的時間檢視影片，記錄各個球種。因此，本論文針對羽球運動開發出一套使用混合式動態時間歸整(Dynamic Time Warping)的演算法辨識揮拍的動作，並結合穿戴式裝置，以加速度計和陀螺儀作為感測元件，將裝置擺放至球拍握柄上收錄選手的揮拍動作。本論文辨識的羽球動作種類為正反手長球、切球、平抽球、撲球、挑球，一共10種。本論文將收錄的揮拍動作，經訊號處理後找尋擊球時產生的特徵，並透過本論文所開發之混合式DTW演算法將各個動作進行辨識。實驗結果顯示，本論文所提出的混合式DTW演算法準確度為91.04%，原始DTW演算法準確度85.63%。此證明使用本論文提出的混合式DTW演算法有較高的準確度。本研究提出的方法能對10種羽球動作進行分類與記錄，並實現於穿戴式裝置中。不僅提供一般民眾一個檢視自我訓練成果的羽球訓練器，也可協助羽球教練減少傳統檢視影片所花費的時間。

    Nowadays, badminton is one of top ten sports in Taiwan. Many people will use video to record their movement during exercising and classify badminton shots. Such as setting self-training goals or badminton players can do tactics analysis by classify badminton shots. However, people use video which will be influenced by video device quality or blind spot. The most important of all is that people need to spend more time on watching video and recording badminton shots.Therefore, a badminton stroke recognition is developed based on hybrid Dynamic Time Warping (hybrid DTW) in this study to classify ten types of badminton shots. Combining wearable sensors device like accelerometer and gyroscope, we put device on the handle of racket to collect badminton players actions. Our research can classify ten types of badminton: backhand/forehand clear, drop, drive, net shot, and lift.Badminton players action datas will be done signal preprocessing and find feature when stroke occurred. Based on the comparison of the data, our algorithm has an accuracy of 91.04% and original DTW has an accuracy of 85.63%. The result shows that our proposed algorithm is better than original.Our research can classify ten types of badminton, record badminton shots and implement on wearable device. Our research not only provide people a way to check self-learning result but also help badminton coach spend less time on watching players actions.

    摘要.........................................I Abstract....................................II 目錄.......................................III 圖目錄.......................................V 表目錄.....................................VII 第一章、 緒論................................1 1.1 研究動機與目的...........................1 1.2 文獻探討.................................2 1.3 論文架構.................................6 第二章、 研究背景............................7 2.1 慣性感測器...............................7 2.2 藍牙模組.................................7 2.3 方向估計演算法...........................7 2.4 四元數...................................8 2.5 Dynamic Time Warping....................11 2.5.1 Derivative Dynamic Time Warping.......17 2.5.2 Feature-based Dynamic Time Warping....18 2.6 Quaternion Dynamic Time Warping.........20 2.7 羽球動作種類............................22 2.7.1 長球..................................22 2.7.2 切球..................................24 2.7.3 平抽球................................25 2.7.4 挑球..................................27 2.7.5 撲球..................................28 第三章、 研究方法...........................30 3.1 系統架構................................30 3.2 裝置端硬體架構..........................31 3.2.1 感測器電路............................32 3.2.2 裝置圖................................33 3.2.3 藍牙傳輸封包格式......................34 3.3 演算法流程架構..........................34 3.3.1 資料前處理............................35 3.3.2 訓練動作資料集........................39 3.3.3 訓練階段..............................39 3.3.4 第一階混合式DTW.......................40 3.3.5 第二階QDTW............................42 3.4 實驗設計................................43 3.4.1 參考裝置..............................44 3.4.2 實驗流程..............................45 3.4.3 實驗驗證..............................45 第四章、 實驗結果與討論.....................47 4.1 羽球選手本身動作比對結果................47 4.2 羽球選手－羽球選手動作比對結果..........49 第五章、 結論與未來展望.....................54 附錄一......................................58

    [1] 世新大學, "中華民國105年運動現況調查 調查報告書," 2016.
    [2] 衛生福利部國民健康署, "健康九九網站," [Online]. Available: http://health99.hpa.gov.tw/Default.aspx. [Accessed Sep. 07 2017].
    [3] "Zepp," [Online]. Available: http://www.zepp.com/zh-cn/.
    [4] "Babolat," [Online]. Available: http://www.babolat.us/.
    [5] "Tennis Smart Sensor," [Online]. Available: http://www.sony.com/electronics/smart-devices/sse-tn1w.
    [6] C. Z. Shan, E. S. L. Ming, H. A. Rahman and Y. C. Fai , "Investigation of Upper Limb Movement during Badminton Smash," in Control Conference (ASCC), Malaysia, 2015.
    [7] M. Salim, H. Lim, M. Salim and M. Baharuddin, "Motion Analysis of Arm Movement during," in IEEE EMBS Conference on Biomedical Engineering & Sciences, Malaysia, 2010.
    [8] H. Zhou and H. Hu, "Reducing Drifts in the Inertial Measurements of Wrist and Elbow Positions," IEEE Transactions on Instrumentation and Measurement ,vol. 59, no 3, pp. 575-585, March 2010.
    [9] H. Zhou and H. Hu, "Inertial sensors for motion detection of human upper limbs," Sensor Review,vol 27,no 2, pp. 151-158, 2007.
    [10] S. Ramasinghe, K. G. M. Chathuramali and R. Rodrigo, "Recognition of Badminton Strokes Using Dense," in Information and Automation for Sustainability, Sri Lanka, 2014.
    [11] A. Avci, S. Bosch, M. Marin-Perianu, R. Marin-Perianu and P. Havinga, "Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey," in 23th International Conference on Architecture of Computing Systems, Hannover, Germany, 2010.
    [12] A. Lees, “Science and the major racket sports: a review,” Journal of Sports Sciences, October 2003.
    [13] M. Ermes, J. Parkka, J. Mantyjarvi and Ilk, "Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions," IEEE Transactions on Information Technology in Biomedicine,vol. 12 ,no 1, pp. 20 - 26, 07 January 2008.
    [14] M. I. Rusydi, M. Sasaki, M. H. Sucipto, Zaini and N. Windasari, "Local Euler Angle Pattern Recognition for Smash and Backhand in Badminton Based on Arm Position," in 6th International Conference on Applied Human Factors and Ergonomics (AHFE 2015) and the Affiliated Conferences, 2015.
    [15] A. Jacob, W. N. W. Zakaria and M. R. B. M. Tomari, "Implementation of IMU Sensor for Elbow Movement Measurement of Badminton Players," in Robotics and Manufacturing Automation, Malaysia, 2016.
    [16] A. I. Anik, M. Hassan, H. Mahmud and K. Hasan, "Activity Recognition of a Badminton Game Through Accelerometer and Gyroscope," in 19th International Conference on Computer and Information Technology, Dhaka, Bangladesh, 2016.
    [17] Z. Wang, M. Guo and C. Zhao, "Badminton Stroke Recognition Based on Body Sensor Networks," IEEE Transactions on Human-Machine Systems, vol. 46, no. 5, pp. 769-775, October 2016.
    [18] S. O. Madgwick, "Estimation of IMU and MARG orientation using a gradient descent algorithm," IEEE International Conference on Rehabilitation Robotics, pp. 1-7, June 2011.
    [19] S. O. Madgwick, "An efficient orientation filter for inertial and inertial/magnetic sensor arrays," Madgwick, Sebastian O.H., UK, 2010.
    [20] D. R. Wilkins, "On Quaternions by William Rowan Hamilton," Royal Irish Academy, vol. 3, pp. 1-16, 1999.
    [21] A. Brito, "Gimbal Lock," [Online]. Available: https://www.allanbrito.com/2007/04/18/gimbal-lock/.
    [22] C. Fick, J. Coetzer and J. Swanepoel, "Efficient curve-sensitive features for offline signature verification," in PRASA-RobMech International Conference, South Africa, 2016.
    [23] H. Sakoe and S. Chiba, "Dynamic Programming Algorithm Optimization for Spoken Word Recognition," IEEE transactions on acoustics,speech, and signal processing, vol 26, no. 1, pp. 43 - 49, February 1978.
    [24] E. J. Keogh and M. J. Pazzani, "Derivative Dynamic Time Warping," in Proceedings of the First SIAM International , Chicago, USA, 2001.
    [25] Y. Xie and B. Wiltgen, "Adaptive Feature Based Dynamic Time Warping," JCSNS International Journal of Computer Science and Network Security, vol. 10, No.1, pp. 264 - 273, January 2010.
    [26] B. Jablonski, "Quaternion Dynamic Time Warping," IEEE Transactions on Signal Processing, vol. 60, no. 3, pp. 1174 - 1183, March 2012.
    [27] 周旺俊 and 廖國茂, "羽球9大技術," 30 11 2012. [Online]. Available: http://www.victorsport.com.tw/. [Accessed 23 May 2017].
    [28] "羽球入門," [Online]. Available: http://www2.ntin.edu.tw/divsion/staffair/sta3/各科講義/羽球入門.html. [Accessed 23 May 2017].
    [29] Nordic Semiconducto, nRF51422 Multi-protocol ANT System-on-Chip, nRF51422 datasheet, July, 2017.

    QR CODE