請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94671完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳育任 | zh_TW |
| dc.contributor.advisor | Yuh-Renn Wu | en |
| dc.contributor.author | 林宇泰 | zh_TW |
| dc.contributor.author | Yu-Tai Lin | en |
| dc.date.accessioned | 2024-08-16T17:26:26Z | - |
| dc.date.available | 2024-08-17 | - |
| dc.date.copyright | 2024-08-16 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-07 | - |
| dc.identifier.citation | [1] Kazuhiro Umemura, Toshimasa Yanai, and Yasushi Nagata. Application of vbgmm for pitch type classification: analysis of trackman’s pitch tracking data. Japanese Journal of Statistics and Data Science, 4:41–71, 2021.
[2] Alan M Nathan. What new technologies are teaching us about the game of baseball. In Proceedings of the Euromech Physics of Sports Conference, 2012. [3] Joshua Mizels, Brandon Erickson, and Peter Chalmers. Current state of data and analytics research in baseball. Current reviews in musculoskeletal medicine, 15(4):283– 290, 2022. [4] Michael Craw and Geoff Dickson. Innovation in golf. In Golf Business and Management, pages 158–169. Routledge, 2017. [5] Mike Fast. What the heck is PITCHf/x. The Hardball Times Annual, 2010:153–158, 2010. [6] Marcos Lage, Jorge Piazentin Ono, Daniel Cervone, Justin Chiang, Carlos Dietrich, and Claudio T Silva. Statcast dashboard: Exploration of spatiotemporal baseball data. IEEE computer graphics and applications, 36(5):28–37, 2016. [7] Kelvin Yeo Soon Keat and Batuhan Okur. Object surface matching with a template for flight parameter measurement, March 17 2020. US Patent 10,593,048. [8] Cristine Agresta, Michael T Freehill, Bryson Nakamura, Samuel Guadagnino, and Stephen M Cain. Using sensors for player development: Assessing biomechanical factors related to pitch command and velocity. Sensors, 22(21):8488, 2022. [9] Baljinder Singh Bal and Gaurav Dureja. Hawk eye: A logical innovative technology use in sports for effective decision making. Sport Science Review, 21, 2012. [10] Harry Collins and Robert Evans. You cannot be serious! public understanding of technology with special reference to “Hawk-Eye＂. Public Understanding of Science, 17(3):283–308, 2008. [11] André Guéziec. Tracking pitches for broadcast television. Computer, 35(3):38–43, 2002. [12] Kenneth M Dawson-Howe and David Vernon. Simple pinhole camera calibration. International Journal of Imaging Systems and Technology, 5(1):1–6, 1994. [13] Rigoberto Juarez-Salazar, Juan Zheng, and Victor H Diaz-Ramirez. Distorted pinhole camera modeling and calibration. Applied Optics, 59(36):11310–11318, 2020. [14] Takashi Ijiri, Atsushi Nakamura, Akira Hirabayashi, Wataru Sakai, Takeshi Miyazaki, and Ryutaro Himeno. Automatic spin measurements for pitched baseballs via consumer-grade high-speed cameras. Signal, Image and Video Processing, 11:1197–1204, 2017. [15] Myron Ross, Harry Shaffer, Andrew Cohen, Richard Freudberg, and Harold Manley. Average magnitude difference function pitch extractor. IEEE Transactions on Acoustics, Speech, and Signal Processing, 22(5):353–362, 1974. [16] Ghulam Muhammad. Extended average magnitude difference function based pitch detection. The International Arab Journal of Information Technology, 8(2):197–203, 2011. [17] Zhengyou Zhang. A flexible new technique for camera calibration. IEEE Transactions on pattern analysis and machine intelligence, 22(11):1330–1334, 2000. [18] Gary Bradski and Adrian Kaehler. Learning OpenCV: Computer vision with the OpenCV library. O’Reilly Media, Inc., 2008. [19] Hartigan Ja. A k-means clustering algorithm. JR Stat. Soc. Ser. C-Appl. Stat., 28:100– 108, 1979. [20] Hansheng Chen, Pichao Wang, Fan Wang, Wei Tian, Lu Xiong, and Hao Li. Epropnp: Generalized end-to-end probabilistic perspective-n-points for monocular object pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2781–2790, 2022. [21] Paresh R Kamble, Avinash G Keskar, and Kishor M Bhurchandi. Ball tracking in sports: a survey. Artificial Intelligence Review, 52:1655–1705, 2019. [22] Philip L Bogler. Radar principles with applications to tracking systems. New York, 1990. [23] Olivier Emile and Janine Emile. Rotational doppler effect: a review. Annalen Der Physik, 535(11):2300250, 2023. [24] Jordan Calandre, Renaud Péteri, Laurent Mascarilla, and Benoit Tremblais. Table tennis ball kinematic parameters estimation from non-intrusive single-view videos. In 2021 International Conference on Content-Based Multimedia Indexing (CBMI), pages 1–6. IEEE, 2021. [25] Masaki Takahashi, Mahito Fujii, and Nobuyuki Yagi. Automatic pitch type recognition from baseball broadcast videos. In 2008 Tenth IEEE International Symposium on Multimedia, pages 15–22. IEEE, 2008. [26] Pádraig Cunningham, Matthieu Cord, and Sarah Jane Delany. Supervised learning. In Machine learning techniques for multimedia: case studies on organization and retrieval, pages 21–49. Springer, 2008. [27] Trevor Hastie, Robert Tibshirani, Jerome Friedman, Trevor Hastie, Robert Tibshirani, and Jerome Friedman. Unsupervised learning. The elements of statistical learning: Data mining, inference, and prediction, pages 485–585, 2009. [28] David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019. [29] Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, and Anil Anthony Bharath. Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine, 34(6):26–38, 2017. [30] Shan Suthaharan and Shan Suthaharan. Decision tree learning. Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning, pages 237–269, 2016. [31] Gérard Biau. Analysis of a random forests model. The Journal of Machine Learning Research, 13(1):1063–1095, 2012. [32] Farkhod Khushvaktov. Introduction to random forest classification by example, 2023. [33] Baoxun Xu, Yunming Ye, and Lei Nie. An improved random forest classifier for image classification. In 2012 IEEE International Conference on Information and Automation, pages 795–800. IEEE, 2012. [34] Ahmad Taher Azar and Shereen M El-Metwally. Decision tree classifiers for automated medical diagnosis. Neural Computing and Applications, 23:2387–2403, 2013. [35] Manoj Thakur and Deepak Kumar. A hybrid financial trading support system using multi-category classifiers and random forest. Applied Soft Computing, 67:337–349, 2018. [36] Abdullah ORHAN and Necdet SAĞLAM. Financial forecast in business and an application proposal: The case of random forest technique. Journal of Accounting & Finance/Muhasebe ve Finansman Dergisi, (99), 2023. [37] Asma Ahmed Abokhzam, NK Gupta, and Dipak Kumar Bose. Efficient diabetes mellitus prediction with grid based random forest classifier in association with natural language processing. International Journal of Speech Technology, 24(3):601– 614, 2021. [38] Vojislav Kecman. Support vector machines–an introduction. In Support vector machines: theory and applications, pages 1–47. Springer, 2005. [39] P Kumar and B Vijayakumar. Brain tumour mr image segmentation and classification using by PCA and RBF kernel based support vector machine. Middle-East Journal of Scientific Research, 23(9):2106–2116, 2015. [40] Manmohan Singh, Rajendra Pamula, et al. Email spam classification by support vector machine. In 2018 International Conference on Computing, Power and Communication Technologies (GUCON), pages 878–882. IEEE, 2018. [41] Anil Kumar Mandle, Pranita Jain, and Shailendra Kumar Shrivastava. Protein structure prediction using support vector machine. International Journal on Soft Computing, 3(1):67, 2012. [42] Ying Liu. Active learning with support vector machine applied to gene expression data for cancer classification. Journal of chemical information and computer sciences, 44(6):1936–1941, 2004. [43] Jan-Henning Trustorff, Paul Markus Konrad, and Jens Leker. Credit risk prediction using support vector machines. Review of Quantitative Finance and Accounting, 36:565–581, 2011. [44] Matija Burić, Miran Pobar, and Marina Ivašić-Kos. Adapting YOLO network for ball and player detection. In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods, volume 1, pages 845–851, 2019. [45] Kay Thwe Min Han and Bunyarit Uyyanonvara. A survey of blob detection algorithms for biomedical images. In 2016 7th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES), pages 57–60. IEEE, 2016. [46] Salman Qasim, Kaleem Nawaz Khan, Miao Yu, and Muhammad Salman Khan. Performance evaluation of background subtraction techniques for video frames. In 2021 International Conference on Artificial Intelligence (ICAI), pages 102–107. IEEE, 2021. [47] Nursuriati Jamil, Tengku Mohd Tengku Sembok, and Zainab Abu Bakar. Noise removal and enhancement of binary images using morphological operations. In 2008 International Symposium on Information Technology, volume 4, pages 1–6. IEEE, 2008. [48] Richard Hartley and Andrew Zisserman. Multiple view geometry in computer vision. Cambridge university press, 2003. [49] Alan M Nathan. The effect of spin on the flight of a baseball. American Journal of Physics, 76(2):119–124, 2008. [50] Gregory S Sawicki, Mont Hubbard, and William J Stronge. How to hit home runs: Optimum baseball bat swing parameters for maximum range trajectories. American Journal of Physics, 71(11):1152–1162, 2003. [51] Sebastian Ruder. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747, 2016. [52] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. [53] Eustace M Dogo, OJ Afolabi, NI Nwulu, Bhekisipho Twala, and CO Aigbavboa. A comparative analysis of gradient descent-based optimization algorithms on convolutional neural networks. In 2018 international conference on computational techniques, electronics and mechanical systems (CTEMS), pages 92–99. IEEE, 2018. [54] Bela Julesz. Stereoscopic vision. Vision Research, 26(9):1601–1612, 1986. [55] Tao Yang, Yanning Zhang, Meng Li, Dapei Shao, and Xingong Zhang. A multi- camera network system for markerless 3d human body voxel reconstruction. In 2009 Fifth International Conference on Image and Graphics, pages 706–711. IEEE, 2009. [56] Adeshina Sirajdin Olagoke, Haidi Ibrahim, and Soo Siang Teoh. Literature survey on multi-camera system and its application. IEEE Access, 8:172892–172922, 2020. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94671 | - |
| dc.description.abstract | 隨著運動科學產業的發展，數據化呈現運動表現變得越來越重要。這不僅能讓運動員更了解自己的訓練成果，也為教練或球探提供了更多評價的依據。本研究成功開發出一套系統，能計算出投手的多項投球數據。只需使用一台高速攝影機拍攝投球畫面，即可自動化獲得投手的球速、轉速、轉軸、旋轉效率、有效轉速、出手位置、球路軌跡、位移量、進壘點及球種等資訊。這套系統既方便又多功能，相較於多攝影機的鷹眼系統，成本更低。本論文參考國內外多項研究，轉速計算部分參考SpinTracker開源程式碼，並針對實際球場及投球狀況進行優化。相機校正部分使用棋盤格來計算內部參數，並且利用立方體來求得外部參數。單相機深度估計的部分使用成像半徑，經透鏡成像公式計算，並考慮畸變及失焦等影響。球路軌跡的部分導入了空氣力學公式來模擬，最後透過隨機森林演算法訓練的模型進行球種辨識。這項研究和設備已在職業級球場進行測試，並對不同層級的投手進行測試。無論是在日常訓練還是職業棒球例行賽中，這套系統都能運作並具有一定的準確度。我們將計算出的數據與市面上活躍的商業軟體Rapsodo進行比較，發現幾乎所有投球數據的相關係數都達到0.85以上，包括轉速和轉軸等數據。而旋轉效率、球速及垂直位移量的相關係數甚至可達到0.94以上，出手點的側向距離、出手點高度及水平位移量的相關係數更是高達0.99。 | zh_TW |
| dc.description.abstract | With the development of the sports science industry, the digital presentation of athletic performance has become increasingly important. This not only allows athletes to better understand their training results but also provides coaches and scouts with more information for evaluation. This study successfully developed a system capable of calculating multiple pitching metrics for pitchers. Using just one high-speed camera to capture pitching footage, it can automatically obtain information such as pitching velocity, spin rate, spin axis, spin efficiency, effective spin rate, release point, pitch trajectory, displacement, strike point, and pitch type. This system is convenient and multifunctional, offering a lower-cost alternative to the multi-camera Hawk-Eye system. The spin rate calculation is based on the open-source SpinTracker code, optimized for real-world field and pitching conditions. For camera calibration, a checkerboard was used to calculate internal parameters and a cube was used to determine external parameters. Single-camera depth estimation was performed using the imaging radius calculated through lens imaging formulas, considering distortion and defocus effects. Pitch trajectory was simulated using aerodynamic formulas, and pitch type recognition was achieved through a model trained with a random forest algorithm. This system and equipment have been tested in professional-grade baseball stadiums and with pitchers of different levels. Whether for regular training or professional baseball games, this system can operate with a certain degree of accuracy. We compared our calculated data with the commercially active software Rapsodo and found that almost all pitching data had correlation coefficients above 0.85, including metrics such as spin rate and spin axis. Additionally, spin efficiency, pitching velocity, and vertical displacement had correlation coefficients of 0.94 or higher, while the lateral release point distance, release point height, and horizontal displacement calculations reached as high as 0.99. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-16T17:26:26Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-16T17:26:26Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 ii Abstract iii Contents v List of Figures ix List of Tables xiv Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Scientific baseball analysis system 2 1.2.1 Trackman 2 1.2.2 Rapsodo 3 1.2.3 Hawk-Eye 5 1.2.4 KZone system 6 1.3 Camera model 6 1.4 Thesis overview 9 Chapter 2 Literature review 11 2.1 Baseball spin and axis calculator 11 2.1.1 Average magnitude difference function 11 2.1.2 Cubic supersampling 13 2.1.3 Spin axis estimation 15 2.2 Camera calibration 16 2.2.1 The checkerboard corner detector 16 2.2.2 Perspective n points 18 2.3 Ball tracking system 20 2.3.1 Radar tracking 20 2.3.2 Optical system tracking 20 2.4 Pitch type recognition system 21 2.4.1 Supervised learning 22 2.4.2 Random Forest Classifier 23 2.4.3 Support Vector Machine 24 2.5 Summary 25 Chapter 3 Equipment and Methodology 26 3.1 Experimental equipment 26 3.2 System flowchart 28 3.3 Ball detection 29 3.3.1 Moving object detection 30 3.3.2 Video preprocessing 31 3.3.3 Ball candidate filtering 33 3.3.4 Signal post-processing 35 3.4 Single-camera calibration in baseball stadium 37 3.4.1 Intrinsic parameter 37 3.4.2 Extrinsic parameter 38 3.5 Application of spin and axis calculation 40 3.5.1 The impact of different frame counts on the spin calculation 40 3.5.2 Spin efficiency and effective spin calculation 42 3.6 Simulation of 3D ball trajectory 43 3.6.1 Single camera image depth estimation 44 3.6.2 3D reconstruction with single camera 46 3.6.3 Polynomial curve fitting 47 3.6.4 Time series forecasting 49 3.6.5 3D trajectory simulation with mechanical model 50 3.6.6 Gradient descent 53 3.6.7 Initial speed and direction estimation 56 3.7 Identification of ball type 59 3.8 Summary 61 Chapter 4 Results and Discussion 63 4.1 Camera calibration error analysis 63 4.2 Analysis of accuracy in spin rate and spin axis calculations 66 4.3 Ball trajectory and displacement calculation analysis 68 4.3.1 Single-camera reconstruction 68 4.3.2 Time series forecasting with mechanical model 71 4.3.3 Comparison of multi-camera reconstruction 73 4.3.4 Strike zone calculation results and analysis 76 4.3.5 Displacement calculation results and analysis 80 4.4 Statistics of professional baseball player pitching data 81 4.5 Error analysis in pitch type recognition 85 4.6 Summary 88 Chapter 5 Conclusion 90 References 92 Appendix A — Multi camera calibration result 100 | - |
| dc.language.iso | en | - |
| dc.subject | 轉速 | zh_TW |
| dc.subject | 轉軸 | zh_TW |
| dc.subject | 球路軌跡 | zh_TW |
| dc.subject | 位移量 | zh_TW |
| dc.subject | 球種辨識 | zh_TW |
| dc.subject | displacement | en |
| dc.subject | spin rate | en |
| dc.subject | spin axis | en |
| dc.subject | pitch type identification | en |
| dc.subject | ball trajectory | en |
| dc.title | 單相機電腦視覺方法在棒球轉速、轉軸、球路軌跡和球種辨識計算之應用 | zh_TW |
| dc.title | Application of Single Camera Computer Vision Method on Baseball Spin Rate, Spin Axis, Ball Trajectory, and Pitch Type Identification Calculations | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 黃致豪;徐瑋勵;郭柏齡 | zh_TW |
| dc.contributor.oralexamcommittee | Jyh-How Huang;Wei-Li Hsu;Po-Ling Kuo | en |
| dc.subject.keyword | 轉速,轉軸,球路軌跡,位移量,球種辨識, | zh_TW |
| dc.subject.keyword | spin rate,spin axis,ball trajectory,displacement,pitch type identification, | en |
| dc.relation.page | 101 | - |
| dc.identifier.doi | 10.6342/NTU202403326 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-08-10 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 光電工程學研究所 | - |
| 顯示於系所單位： | 光電工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 2.78 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。