簡易檢索 / 詳目顯示

研究生: 許家齊
Chia-Chi Hsu
論文名稱: 智慧化學習架構應用於精準棒球投手疲累偵測
An Intelligent Quantification and Aggregation Learning Architecture for Pitcher Fatigue Detection in Precision Sports
指導教授: 陳俊良
Jiann-Liang Chen
馬奕葳
Yi-Wei Ma
口試委員: 郭耀煌
Yau-Hwang Kuo
孫雅麗
Yea-li Sun
廖婉君
Wan-Jiun Liao
黎碧煌
Bih-Hwang Lee
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2020
畢業學年度: 108
語文別: 中文
論文頁數: 67
中文關鍵詞: 精準運動電腦視覺投手疲累影像分析機器學習
外文關鍵詞: Precision sports, Computer visions, Pitcher fatigue, Image analysis, Machine learning
相關次數: 點閱:220下載:6
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
  • 體育在近年來一直是人們生活中不可或缺的娛樂元素之一。隨著物聯網、人工智慧與電腦視覺等新興資通訊技術的崛起,體育結合資通訊技術所發展出的「精準運動」成為了新興的體育型態。本研究以棒球為研究主題,引入精準棒球的觀點,結合系統所設計的學習演算法,將圖片與時間量化為疲累值,目的在於建立智慧化學習架構應用於偵測投手疲累。
    本研究建構一Quantification and Aggregation Learning Architecture (QALA)。收集層負責用於收集影像和感測訊息,於此包括攝影設備和感測器。分析層主要用於分析投手姿勢變化與投球時間間隔變化,其中包含投手手肘角度、背部軀幹角度及計算投球間隔時間等分析方法。聚合層主要用於計算疲勞量化,包括評估角度變化和評估時間變化等方法。在學習層則是在各階段會調用系統架構中的模組進行計算與驗證,達到在Offline Stage中,能學習投手的投球姿勢變化以及投球時間變化與疲累的關係,並驗證出一系統所測試出最適合的模型進行測試。在Online Stage中能以此測試模型實際應用到比賽,達到偵測投手疲累的目的。
    本研究在效能分析用了十種Cases進行不同參數的驗證,得到以疲累界線(?)為0.7、手肘角度變化分析方法的權重(W_1)為0.7、背部軀幹角度變化分析方法的權重(W_2)為0.2、投球間隔時間分析方法的權重(W_3)為0.1以及疲累門檻值(T)為50作為驗證所得到89.1%準確率為最適效果的參數。以此設定進行Online Stage實際測試,得到測試準確率87%的表現,系統在實際應用方面將能有效提供教練進行換投決策的參考。


    Sports is an important part of human life. At present, the sports industry is showing rapid development, and many athletes emerged as an important figure in international events. In recent years, with the rise of emerging information and communication technologies such as the Internet of Things, artificial intelligence, and computer vision, the concept of "smart sports" has also been proposed. This study focuses on "appropriate time for pitcher change". The pitcher is one of critical elements that affect game result. Therefore, when pitcher does not perform well, defensive coach considers whether to change pitcher.

    This study proposes Quantification and Aggregation Learning Architecture (QALA), which includes collection layer, analysis layer, quantification layer, aggregation layer, learning layer and public layer. Collection layer is mainly used for collect image and sensor information, which includes camera and sensor device. Analysis layer is mainly used for analysis pitcher posture and pitch interval from video stream, which include extract elbow valgus angle method, extract trunk flexion angle method and extract time between pitch method. Quantification layer is mainly used for calculate quantification of fatigue, which include evaluate angle changes method and evaluate time changes method. Aggregation layer is mainly used for aggregate various fatigue quantitative data, which include aggregation function, calculate fatigue point method and assess accuracy of validation method. Learning layer is mainly used for fatigue model training, data verification and result display, which include training module, validation module and testing module. Public layer is mainly used for store relevant information, which include player information database and player predict database.

    This study used ten cases to verify different parameters setting for accurate analysis. When setting of fatigue point (?) is 0.7, weight of method 1 (W_1) is 0.7, weight of method 2 (W_2) is 0.2, weight of method 3 (W_3) is 0.1 and threshold value of fatigue (T) is 50, the validation accuracy is 89.1% which mean this parameter is the most suitable choice. Test with this parameter setting to get a test accuracy rate of 87%, which means system effectively provide a reference information for coaches to make decisions.

    摘要 I Abstract II 致謝 IV Contents V List of Figures VII List of Tables IX Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Contributions 3 1.3 Organization of This Thesis 4 Chapter 2 Related Works 5 2.1 Sports Fatigue 5 2.2 OpenPose 6 2.3 Fatigue Definition and Detection Methods 7 2.4 Assumptions 8 Chapter 3 Proposes Quantification and Aggregation Learning Architecture 9 3.1 Analysis Methods 12 3.1.1 Elbow Valgus Angle Analysis Method 13 3.1.2 Trunk Flexion Angle Analysis Method 13 3.1.3 Time Between Pitch Analysis Method 14 3.2 Quantification Methods 15 3.3 Aggregation Methods 17 3.4 Determination Methods 17 3.5 Learning Methods 17 3.6 Working Stages 19 Chapter 4 Performance Analysis 21 4.1 Experimental Setting 21 4.2 Offline Testing 21 4.2.1 Case Study 21 4.2.2 Case Comparison 45 4.2.3 Summary 48 4.3 Online Testing 49 Chapter 5 Conclusions and Future Works 50 5.1 Conclusions 50 5.2 Future Works 51 References 52

    [1] Y. Qiu, K. Hu and X. Luo, "Application of Computer Virtual Reality Technology in Modern Sports," Proceedings of the Third International Conference on Intelligent System Design and Engineering Applications, pp. 362-364, 2013.
    [2] J. Pers and S. Kovacic, "Computer Vision System for Tracking Players in Sports Games," Proceedings of the First International Workshop on Image and Signal Processing and Analysis, pp. 177-182, 2000.
    [3] C. Zhang, F. Yang, G. Li, Q. Zhai, Y. Jiang and D. Xuan, "MV-Sports: A Motion and Vision Sensor Integration-Based Sports Analysis System," Proceedings of IEEE Conference on Computer Communications, pp. 1070-1078, 2018.
    [4] N. Blanchard, K. Skinner, A. Kemp, W. Scheirer and P. Flynn, ""Keep Me In, Coach!": A Computer Vision Perspective on Assessing ACL Injury Risk in Female Athletes," Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1366-1374, 2019.
    [5] M. Buric, M. I.Kos and M. Pobar, "Player Tracking in Sports Videos," Proceedings of the IEEE International Conference on Cloud Computing Technology and Science, pp. 334-340, 2019.
    [6] A.W. Kiefer, C. Dicesare, S. Bonnette, K. Kitchen, B. Gadd, S. Thomas, K.D.B. Foss, G.D. Myer, M.A. Riley and P. Silva, "Sport-specific Virtual Reality to Identify Profiles of Anterior Cruciate Ligament Injury Risk during Unanticipated Cutting," Proceedings of the International Conference on Virtual Rehabilitation, pp. 1-8, 2017.
    [7] W. Zhang, "Analysis of Sports Training Injury Measurement with Grey Markov Model (GMM)," Proceedings of the 10th International Conference on Measuring Technology and Mechatronics Automation, pp. 194-197, 2018.
    [8] H. Shih, "A Survey of Content-Aware Video Analysis for Sports, "IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 5, pp. 1212-1231, 2018.
    [9] T. Hira, M. Ban, S. Enoki and S. Uchida, "A Baseball Game Analysis by an Extraction of Characteristic Play Sequence," Proceedings of the 16th International Conference on Control, Automation and Systems, pp. 994-997, 2016.
    [10] K. Konda and Y. Yamamoto, "Analysis of the Impact of Temperature on Nippon Professional Baseball," Proceedings of the 17th International Conference on ICT and Knowledge Engineering, pp. 1-6, 2019.
    [11] W. Matt, "Fatigue in Sport and Exercise," The Journal of the Canadian Chiropractic Association, vol. 60, no. 1, pp. 288, 2016.
    [12] A.D. Monte, M. Faina, G. Mirri, "VIII Antonio Arrigo Award. Fatigue and Sport," Proceedings of Institute of Sports Science, pp. 7-10, 2002.
    [13] Definition of Fatigue in Sport http://psychology.iresearchnet.com/sports-psychology/health-promotion/definition-of-fatigue-in-sport/ (last visited on 2020/07/04)
    [14] K.O. Sullivan, P.B.O. Sullivan, T.J. Gabbett, "Pain and Fatigue in Sport: Are They so Different? " British Journal of Sports Medicine, vol.52, pp. 555-556, 2018.
    [15] Fatigue and Performance https://nssmc.com.au/conditions-we-treat/fatigue-and-performance/ (last visited on 2020/07/04)
    [16] 6 Surprising Risks of Fatigue for Pitchers (and How to Beat It) https://www.stack.com/a/pitcher-fatigue (last visited on 2020/06/09)
    [17] How Fatigue Affects a Pitcher’s Fastball https://tht.fangraphs.com/how-fatigue-affects-a-pitchers-fastball/ (last visited on 2020/06/15)
    [18] Baseball Pitcher Fatigue: Learning to Recognize the Critical Signs https://www.pottsmerc.com/baseball-pitcher-fatigue-learning-to-recognize-the-critical-signs/article_507d26aa-5a2b-11e9-972a-ef43251c974b.html (last visited on 2020/06/20)
    [19] T. Suchomel and C. Bailey, "Monitoring and Managing Fatigue in Baseball Players," Strength and Conditioning Journal, vol. 36, no. 6, pp. 39-48, 2014.
    [20] B. Erickson, T. Sgori, P. Chalmers, P. Vignona, M. Lesniak, C. Joseph, N. Verma and A. Romeo, "The Impact of Fatigue on Baseball Pitching Mechanics in Adolescent Male Pitchers," Arthroscopy: The Journal of Arthroscopic and Related Surgery, vol. 32, no. 5, pp. 762–771, 2016.
    [21] Z. Cao, T. Simon, S.E. Wei, Y. Sheikh, "Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields, " Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1302-1310, 2017
    [22] S. Qiao, Y. Wang and J. Li, "Real-time Human Gesture Grading Based on OpenPose," Proceedings of the International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, pp. 1-6, 2017.
    [23] R. Bajireanu, J. A. Pereira, R. J. Veiga, J. D. Sardo, P. J. Cardoso, R. Lam and J. M. Rodrigues, "Mobile Human Shape Superimposition: An Initial Approach using OpenPose," International Journal of Computers, vol.3, pp. 1-8, 2019.
    [24] A. Qammaz, D. Michel and A. Argyros, "A Hybrid Method for 3D Pose Estimation of Personalized Human Body Models," Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 456-465, 2018.
    [25] Z. Huang, Y. Liu, Y. Fang and B. K. Horn, "Video-based Fall Detection for Seniors with Human Pose Estimation," Proceedings of the 4th International Conference on Universal Village, pp. 1-4, 2018.
    [26] M. Nakai, Y. Tsunoda, H. Hayashi and H. Murakoshi, "Prediction of Basketball Free Throw Shooting by OpenPose," Proceedings of the JSAI International Symposium on Artificial Intelligence, pp. 435-446, 2018.
    [27] S. Chen and R.R. Yang, "Pose Trainer: Correcting Exercise Posture Using Pose Estimation," arXiv, 2020.
    [28] S. Kreiss, L. Bertoni and A. Alahi, "Pifpaf: Composite Fields for Human Pose Estimation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11977-11986, 2019.
    [29] S. Schwarcz and T. Pollard, "3D Human Pose Estimation from Deep Multi-view 2D Pose," Proceedings of the International Conference on Pattern Recognition, pp. 2326-2331, 2018.
    [30] N. Kolotouros, G. Pavlakos, M. J. Black, and K. Daniilidis, "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop," Proceedings of the IEEE International Conference on Computer Vision, pp. 2252-2261, 2019.
    [31] K. Chen, P. Gabriel, A. Alasfour, C. Gong, W. K. Doyle, O. Devinsky, D. Friedman, P. Dugan, L. Melloni, T. Thesen, D. Gonda, S. Sattar, S. Wang, and V. Gilja, "Patient-specific Pose Estimation in Clinical Environments," IEEE Journal of Translational Engineering in Health and Medicine, vol. 6, pp. 1-11, 2018.
    [32] A.I. Fajar and L.R. Chuang, "Baseball and Biomechanics: Injury Prevention for Baseball Pitcher," Journal Keolahragaan, vol.7, pp 57-64, 2019.
    [33] D.W. Keeley, G.D. Oliver, M.R. Torry and J. Wicke, "Validity of Pitch Velocity and Strike Percentage to Assess Fatigue in Young Baseball Pitchers," International Journal of Performance Analysis in Sport, vol.14, pp. 355-366, 2014.
    [34] W. Carroll and B. Hansen, "The New Science of Bioball: Sensors and Software Protect Baseball Pitchers from Injury," IEEE Spectrum, vol. 56, no. 10, pp. 34-53, 2019.
    [35] M. Stig, G. Gilbert, N. James, "Shoulder Weakness in Professional Baseball Pitchers," Medicine and Science in Sports and Exercise, vol. 30, no. 9, pp. 544-551, 1994.
    [36] R. Birfer, M.W. Sonne and M.W. Holmes, "Manifestations of Muscle Fatigue in Baseball Pitchers: A Systematic Review," PeerJ, vol. 7, pp. 1-23, 2019.
    [37] J. Yang, J. Stepan, L. Dvoracek, R. Wright, R. Brophy and M. Smith "Fast-Pitch Softball Pitchers Experience a Significant Increase in Pain and Fatigue During a Single High School Season," HSS Journal: the Musculoskeletal Journal of Hospital for Special Surgery, vol. 12, no. 2, pp. 111–118, 2016.
    [38] Baseball Pitching: Signs and Symptoms of Pitcher Fatigue to Reduce Arm Injury https://www.train2playsports.com/baseball-pitching-signs-symptoms-pitcher-fatigue-reduce-arm-injury/ (last visited on 2020/7/1)
    [39] L. Vincent, G. Caleb, D. Smith, M. Jason, B. Peter, M. Vasilios, M. Eric, "Predictors of Elbow Torque Among Professional Baseball Pitchers," Journal of Shoulder and Elbow Surgery, vol. 29, no. 2, pp. 316-320, 2019.
    [40] N. Nithin, Z. Alan and P.G. George, "Unusual Cause of Elbow Pain in a Baseball Pitcher," BMJ Case Reports, 2018.
    [41] O. Kelechi, M. Jason, L. Vincent, M. Fabein, Stephens, Jeffrey, M. Vasilious and M. Eric, "Effect of Fatigue on Medial Elbow Torque in Baseball Pitchers: A Simulated Game Analysis," The American Journal of Sports Medicine, 2018.

    QR CODE