English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 113160/144130 (79%)
Visitors : 50739764      Online Users : 622
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    政大機構典藏 > 商學院 > 資訊管理學系 > 學位論文 >  Item 140.119/146884
    Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/146884


    Title: 基於球員行動的羽球贏家策略
    Badminton winner strategy synthesis based on player position motions
    Authors: 陳宜莉
    Contributors: 郁方
    陳宜莉
    Keywords: 自動化程式
    物件偵測
    序列預測
    邏輯規則
    序列分析
    Automation Programs
    Object Detection
    Sequence Prediction
    Logic Rule
    Sequence Synthesis
    Date: 2022
    Issue Date: 2023-09-01 14:52:33 (UTC+8)
    Abstract: 利用機器學習技術對球員行為進行分析已在足球和棒球等各種活動中取得成就。我們將這一成就延續到羽毛球領域,旨在系統地綜合球員的動作,從 Youtube 視頻中分析選手對不同對手的勝負策略。模型的學習過程基於可從影片的幀中識別的球員位置(相對於基於跟蹤羽毛球的方法而言),我們使用來自 Youtube 上的國際羽聯官方網站的視頻。
    分析框架包括幾個階段:首先將羽毛球比賽的幀整理成為同一種畫面,然後採用 MASK-RCNN 檢測幀中的雙方球員,以獲得他們的邊界框和坐標。
    另外我們訓練一個 DeepCTRL 模型,根據球員的坐標預測每幀中羽毛球的方向。
    我們使用連續的位置坐標來預測每幀中的羽毛球方向。為了提高精準度,我們採用了DeepCTRL 模型結合了 Bi-LSTM 模型作為方向序列預測的模型,並附加了分數規則,以指導正確分數變化下的學習過程。羽毛球的方向可用於識別擊球幀(基於方向的變化)、獲勝者(下一個發球者)和比賽歷史。然後,我們利用球員在擊球幀中的位置來檢測擊球類型,並進一步識別每個點的勝負擊球序列。為了克服觀察到的擊球序列不足的限制,我們使用 SeqGAN 合成更多的勝負擊球序列,以識別戴資穎對不同對手的策略。最後我們以戴資穎參加奧運會和世界羽聯匯豐銀行總決賽的比賽為例,總結了她對不同對手的勝負策略。
    Systematical analysis on player behaviors that leverages modern machine learning techniques
    has shown great success in various activities such as football and baseball. We continue
    the success to badminton and aim to systematically synthesize player movements to analyze
    their winning/losing strategies against different opponents from Youtube videos. The learning
    process is based on player positions that can be recognized from rather low-resolution
    frames (with respect to approaches based on tracking shuttlecocks), advancing our source
    base in scale to widely available videos, e.g., from the BWF official website on Youtube.
    The analysis framework involves several stages: We first convert frames of badminton games
    into normalized court frames, then adopt MASK-RCNN to detect both players in frames
    to obtain their bounding boxes and coordinates. We train a DeepCTRL model to predict
    directions of the shuttlecock in each frame based on players’ coordinates. Our DeepCTRL
    model combines a Bi-LSTM model as the task base for direction sequence prediction with
    additional rule loss on scores to guide the learning process under correct score changes. The
    directions of the shuttlecock can then be used to identify Shot frames (based on changes of directions),
    point winners (the next starting direction) and match history (direction segments).
    We then use the position of players in shot frames to detect shot type and further identify
    winning/losing shot sequences in each point. To overcome the limitation of insufficient observed
    shot sequences, we synthesize more winning/losing shot sequences with SeqGAN to
    recognize the Tai Tzu Ying’s strategies against different opponents. We take Tai Tzu Ying’s
    games including Olympic games and BWF HSBC Final games as an example and summarize
    our findings in her winning and losing strategies to different opponents.
    Reference: 1.J. Galeano, M. A. Gomez, F. Rivas, and J. M. Buld ́u, “Entropy of badminton strike positions,” Entropy, vol. 23, no. 7, p. 799, Jun 2021.
    2.K. Mona Teja and N. Prabakaran, “Automated visual tracking and live data analysis in badminton,” International Journal of Advanced Science and Technology, vol. 29, no. 9s,pp. 5094 – 5105, May 2020.
    3.T. H. Hsu, C. C. Wang, Y. H. Lin, C. H. Chen, N. P. Ju, T. U. Ik, W. C. Peng, Y. S.Wang, Y. C. Tseng, J. L. Huang, and Y. T. Ching, “Coachai: A project for microscopic badminton match data collection and tactical analysis,” 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS), pp. 1–4, 2019.
    4.Y. Su and Z. Liu, “Position detection for badminton tactical analysis based on multi-person pose estimation,” 2018 14th International Conference on Natural Computation,Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pp. 379–383, 2018.
    5.K. Weeratunga, K. How, A. Dharmaratne, and C. Messom, “Application of computer vision to automate notation for tactical analysis of badminton,” 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014, pp. 340–345, Mar 2015.
    6.M. Ks, “Applications of artificial intelligence in the game of football: The global per-spective,” Researchers World – Journal of Arts Science Commerce, vol. 11, pp. 18–29, Jul 2020.
    7.S. Chen, Z. Feng, Q. Lu, B. Mahasseni, T. Fiez, A. Fern, and S. Todorovic, “Play type recognition in real-world football video,” IEEE Winter Conference on Applications of Computer Vision, pp. 652–659, 2014.
    8.V. D. Silva, M. Caine, J. Skinner, S. Dogan, A. Kondoz, T. Peter, E. Axtell, M. Birnie, and B. Smith, “Player tracking data analytics as a tool for physic agement in football: A case study from Chelsea Football Club Academy,” Sports, Oct 2018.
    9.M. H. Hung and C. H. Hsieh, “Event detection of broadcast baseball videos,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 18, no. 12, pp. 1713–1726, 2008.
    10.S. Chun, C. H. Son, and H. Choo, “Inter-dependent lstm: Baseball game prediction with starting and finishing lineups,” 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), pp. 1–4, 2021.
    11.K. Hirasawa, K. Maeda, T. Ogawa, and M. Haseyama, “Important scene prediction of baseball videos using twitter and video analysis based on lstm,” 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE), pp. 636–637, 2020.
    12.G. Sudhir, J. C. M. Lee, and A. K. Jain, “Automatic classification of tennis video for high-level content-based retrieval,” Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database, pp. 81–90, 1998.
    13.W. T. Chu and S. Situmeang, “Badminton video analysis based on spatiotemporal and stroke features,” Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, p. 448–451, 2017.
    14.M. St ̈ockl, T. Seidl, D. Marley, and P. Power, “Making offensive play predictable - using a graph convolutional network to understand defensive performance in soccer,”42 Analytics, Apr 2021.
    15.K. He, G. Gkioxari, P. Doll ́ar, and R. Girshick, “Mask r-cnn,” 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988, 2017.
    16.S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object de-tection with region proposal networks,” Advances in Neural Information Processing Systems, vol. 28, 2015.
    17.J. Donahue, L. A. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, and T. Darrell, “Long-term recurrent convolutional networks for visual recognition and description,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625–2634, Jun 2015.
    18.W. W. T. Fok, L. C. W. Chan, and C. Chen, “Artificial intelligence for sport actions and performance analysis using recurrent neural network (rnn) with long short-term memory (lstm),” Proceedings of the 2018 4th International Conference on Robotics and Artificial Intelligence, p. 40–44, 2018.
    19.W. Y. Wang, T. F. Chan, H. K. Yang, C. C. Wang, Y. C. Fan, and W. C. Peng, “Exploring the long short-term dependencies to infer shot influence in badminton matches,”2021 IEEE International Conference on Data Mining (ICDM), pp. 1397–1402, 2021.
    20.M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Trans-actions on Signal Processing, vol. 45, no. 11, pp. 2673–2681,1997.
    21.Z. Huang, W. Xu, and K. Yu, “Bidirectional LSTM-CRF models for sequence tagging,”CoRR, 2015.
    22.R. Zhao, R. Yan, J. Wang, and K. Mao, “Learning to monitor machine health with convolutional bi-directional lstm networks,” Sensors, vol. 17, no. 2, p. 273, Jan 2017.
    23.] S. Seo, S. ̈O. Arik, J. Yoon, X. Zhang, K. Sohn, and T. Pfister, “Controlling neural networks with rule representations,” Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 11 196–11 207, 2021.
    24.L. Yu, W. Zhang, J. Wang, and Y. Yu, “Seqgan: Sequence generative adversarial nets with policy gradient,” Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA, pp. 2852–2858, 2017.
    25.C. Li, Y. Su, J. Qi, and M. Xiao, “Using gan to generate sport news from live game stats,” Cognitive Computing – ICCC 2019, pp. 102–116, 2019.
    26.R. Girdhar, G. Gkioxari, L. Torresani, M. Paluri, and D. Tran, “Detect-and-track: Efficient pose estimation in videos,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 350–359, Jun 2018.
    27."O. Lorente, I. Riera, and A. Rana, “Scene understanding for autonomous driving,”CoRR, 2021.
    28.N. E. Sun, Y. C. Lin, S. P. Chuang, T. H. Hsu, D. R. Yu, H. Y. Chung, and T. U. ̇Ik,“Tracknetv2: Efficient shuttlecock tracking network,” 2020 International Conference on Pervasive Artificial Intelligence (ICPAI), pp. 86–91, 2020.
    29.S. L. Teng and R. Paramesran, “Detection of service activity in a badminton game,”TENCON 2011 - 2011 IEEE Region 10 Conference, pp. 312–315, 2011.
    30.A. Bulat and G. Tzimiropoulos, “Human pose estimation via convolutional part heatmap regression,” Computer Vision – ECCV 2016, pp. 717–732, 2016.
    31.T. Fernando, S. Denman, S. Sridharan, and C. Fookes, “Memory augmented deep gen-erative models for forecasting the next shot location in tennis,” IEEE Transactions on Knowledge amp; Data Engineering, vol. 32, no. 09, pp. 1785–1797,Sep 2020.
    32.W. Y. Wang, H. H. Shuai, K. S. Chang, and W. C. Peng, “Shuttlenet: Position-aware fusion of rally progress and player styles for stroke forecasting in badminton,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 4, pp. 4219–4227, Jun. 2022.
    33.W. Y. Wang, T. F. Chan, W. C. Peng, H. K. Yang, C. C. Wang, and Y. C. Fan,“How is the stroke? inferring shot influence in badminton matches via long short-term dependencies,” ACM Trans. Intell. Syst. Technol., vol. 14, no. 1, nov 2022.
    34.N. P. Ju, D. R. Yu, T. U. ̇Ik, and W. C. Peng, “Trajectory-based badminton shots detection,” in 2020 International Conference on Pervasive Artificial Intelligence (ICPAI), 2020, pp. 64–71.
    35.K. S. Chang, W. Y. Wang, and W. C. Peng, “Where will players move next? dynamic graphs and hierarchical fusion for movement forecasting in badminton." 2023.
    Description: 碩士
    國立政治大學
    資訊管理學系
    109356049
    Source URI: http://thesis.lib.nccu.edu.tw/record/#G0109356049
    Data Type: thesis
    Appears in Collections:[資訊管理學系] 學位論文

    Files in This Item:

    File Description SizeFormat
    604901.pdf5859KbAdobe PDF20View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback