棒球在台灣為相當盛行的主流運動，尤其是近年來，台灣培育出許多的棒球好手，像是王建民、陳偉殷等，都已在美國大聯盟上發光發熱，並將台灣帶上國際。而本論文為了增進棒球的發展，我們希望發展一套系統，用來幫助國內的投手的訓練，在國科會的計畫中[1]，我們研究棒球的軌跡，但現在，我們希望更進一步了解，棒球在空中飛行時的旋轉，因為，對於在飛行中的棒球，如何旋轉是非常重要的議題，當投手投出棒球時，會因為不同的旋轉方式，使縫線跟風產生交互作用，大大的影響棒球的軌跡，像是快速直球(Fastball)、滑球(Slider)、曲球(Curveball)等不同的球路，就是藉由不同的旋轉方式來達成，而且在國科會的棒球軌跡重建的計畫中，棒球在被補手接住的過程中，是最重要的時刻，但常常因為距離太遠、軌跡變化太大、雜訊太多，導致誤判的情形，所以也希望藉由研究棒球旋轉這個議題，增進棒球軌跡預測的能力。
除了量測棒球飛行中的軌跡外，本論文也嘗試對之前軌跡重建系統做了一些實驗方法上的改變，使可能導致誤差的原因減少到最小，像是增加同步訊號源、用無線SD卡取代傳輸線、相機拍攝影片先存至SD卡，拍完時再傳至電腦做分析等、修改影像處理方法，並採用高速攝影機，提升追踨棒球的準確率。
本論文實驗結果顯示，靜態棒球球體旋轉測試中，其點座標在旋轉後，pixels實際位置跟預期位置，其誤差率大約在10%左右，其原因主要是因為相機拍攝有一定仰角，使得在旋轉時進而影響到其座標軸，但透過多個記號點算出最佳解(旋轉矩陣)，並依照所公式算出來的角度，與實際誤差將降至5%左右，再延伸實驗至飛行中的棒球，經過多次多組實驗，實際測試的出旋轉角度跟滾動方向推算出的旋轉角度，也完全的符合。

Baseball is one of the most popular sports in Taiwan. In recent years, there are already many baseball players establish their position as major baseball league starters, such as Chien-Ming Wang, Wei-Yin Chen etc. They have been showing their talent on the U.S. Major League Baseball and helped bringing Taiwan to the international level. In order to promote the development of baseball, we hope to develop a system to help the pitcher improve playing skills. We build system to track the trajectory of the baseball with the sponsor of the National Science Council. In this paper, as well as the determination of baseball trajectory, we hope to further understand baseball’s rotation while flying through the air. It is a very important issue to discuss the rotation of the baseball during its flight, for the baseball will be affected by different rotational angle when the pitcher throws it out, such as fastball, slider ball, curveball etc. We hope our system can further improve the study of pitcher’s effectiveness.
On the other hand, the most important decisive call for baseball game is its strike zone. The result will sometimes be affected by the umpire. We hope to increase the accuracy by studying such as baseball trajectory and rotation. In order to reduce the error caused by non-synchronous cameras, we use techniques synchronization source cameras, using wireless SD card to substitute a physical communication line, applying the image processing methods and using high-speed cameras to improve the accuracy of baseball tracking.
To verify our method to automatic capture of static baseball sphere rotation, the coordinate points identified by measuring are compared with the points that are computer calculated, thus to check for any difference. This experiment error is approximately 10%. The main reason is because the camera has a certain elevation error and thereby affects its axis. We calculate the optimal solution (rotation matrix) by applying more than one point to further reduce actual error to about 5%.

[1] 詹凱鈞，「低成本棒球偵測三維軌跡重建系統」，碩士論文，國立台灣科技大學，台北(2011)。
[2] S. Furuno, K. Kobayashi, T. Okubo and Y. Kurihara, “A Study on Spin-rate Measurement Using a Uniquely Marked Moving Ball,” (2009)
[3] L. Susman, “Calibration of a six-port reflectometer using projective geometry concepts, ”Journal of Electronics Letters, Vol.20, pp. 9 (1984)
[4] 呂傑棋，「3D視覺校正軟體之研製」，碩士論文，中華大學，新竹 (1997)。
[5] 馬維章，「以多部攝影機實現棒球偵測與追蹤系統」，碩士論文，國立台灣科技大學，台北 (2008) 。
[6] 龔雨軒，「互動式投影遊戲之視覺平台發展」，碩士論文，國立台灣科技大學，台北 (2008) 。
[7] G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O, Reilly, pp. 348-363 (2008)
[8] G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O, Reilly, pp. 370-374 (2008)
[9] R. D. Sampson, A. E. Peterson and E. P. Lozowski, “Photogrammetric calibration of a consumer grade flat-bed scanner,” IEEE Canadian Conference on Electrical and Computer Engineering, Vol.2, pp. 622-626 (1999)
[10] R. I. Hartley, “An algorithm for self calibration from several views,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 908-912 (1994)
[11] W. Guanghui, Q. M. Wu and W. Zhang, “Camera Self-Calibration and Three Dimensional Reconstruction under Quasi-Perspective Projection,” IEEE Canadian Conference on Computer and Robot Vision, pp. 129-136 (2008)
[12] Q. T. Luong and O. Faugeras, “Self-calibration of a moving camera from point correspondences and fundamental matrices,” Journal of Computer Vision, Vol.4, pp. 880-883 (1997)
[13] 繆紹綱，數位影像處理，培生出版社，台北，第392-395 頁、726-730 頁 (2009)。
[14] 鐘國亮，影像處理與電腦視覺，東華書局，台北 (2004)。
[15] W. Niblack, An Introduction to Digital Image Processing, Prentice-Hall, New Jersey (1986)
[16] M. Sonka, V. Hlavac and R. Boyle, Image Processing, Analysis, and Machine Vision, PWS Publishing, pp. 68-102 (1999)
[17] J. R. Parker, Algorithms for Image Processing and Computer Vision, NY, John Wiley & Sons (1997)
[18] R. Yan, X. Song and S. Yan, “Moving object detection based on an improved gaussian mixture background model,” Journal of Computing, Communication, Control, and Management, Vol.1, pp. 12-15 (2009)
[19] S. Ju, X. Chen and G. Xu, “An Improved Mixture Gaussian Models to Detect Moving Object Under Real-Time Complex Background,” International Conference on Cyberworlds, pp. 730-734 (2008)
[20] 劉冠廷，「基於運動歷史影像實現行人追蹤與計數系統」，碩士論文，國立台灣科技大學，台北 (2010)。
[21] P. Shrestha, M. Barbieri, H. Weda and D. Sekulovski, “Synchronization of Multiple Camera Videos Using Audio-Visual Features,” IEEE Transactions on Multimedia, Vol.12, pp. 79-92 (2010)
[22] D. N. Brito, “Synchronizing Video Cameras with Non-Overlapping Fields of View,” Journal of Computer Graphics and Image Processing, pp. 37-44 (2008)
[23] Jean-Yves Bouguet (2010), Camera Calibration Toolbox for Matlab
Available：http://www.vision.caltech.edu/bouguetj/calib_doc/htmls/example.html
[24] E. Angel, Interactive Computer Graphics: A Top-Down Approach Using OpenGL, Addison Wesley (2008)
[1] R. C. Gonzalez, Digital Image Processing, New Jersey, Prentice Hall (2002)
[25] H. Shum and T. Komura, “Tracking the translational and rotational movement of the ball using high-speed camera movies,” (2005)