在此研究中，我們提出了一個可以建構出拳擊選手出拳軌跡的系統。該系統利用慣性感測單元繪製出三種拳的軌跡，包含直拳、鉤拳及上鉤拳。為了有效消除慣性感測單元的內建誤差，我們使用了橢球擬合的原理作為校正方法。此外，我們也使用了四元數的概念來對蒐集到的感測資料進行三維空間中的旋轉。最後，實驗結果顯示在直拳、鉤拳和上鉤拳的軌跡當中，均方根誤差分別為0.041m、0.078m和0.117m。

In this work, we propose a system to construct the trajectory of punch for boxers. This system can plot trajectories of three kinds of punches including straight punch, hook, and uppercut via a single IMU sensor. A quaternion-based approach is utilized to identify rotations on collected data in three-dimensional space. Furthermore, we apply ellipsoid fitting as our calibration method to remove the built-in offsets inside the IMU sensor effectively. The experimental results show that the proposed system achieves reliable trajectories compared to the professional motion capture product, VICON Motion Systems. The root mean square error (RMSE) of trajectory in straight punch, hook, and uppercut are 0.041m, 0.078m, and 0.117m, respectively.

中文摘要 -------------------------------------------- i
Abstract ------------------------------------------- ii
誌謝辭 --------------------------------------------- iii
Contents ------------------------------------------- iv
List of Tables ------------------------------------- vi
List of Figures ------------------------------------ vii
1 Introduction ------------------------------------- 1
2 Preliminaries ------------------------------------ 4
2.1 IMU Sensor ------------------------------------- 4
2.2 Quaternion ------------------------------------- 4
3 Method ------------------------------------------- 6
3.1 Data Segmentation ------------------------------ 6
3.2 Sensor Calibration ----------------------------- 8
3.3 Verfication on Calibration --------------------- 11
3.4 Orientation Adjustment ------------------------- 12
3.5 Gravity Removal -------------------------------- 13
3.6 Overall Flow ----------------------------------- 13
4 Experimental Results ----------------------------- 15
4.1 Data Segmentation ------------------------------ 15
4.2 Trajectory ------------------------------------- 16
4.3 Effectiveness of Calibration ------------------- 17
5 Conclusions -------------------------------------- 20
Bibliography --------------------------------------- 21

1. A. Ahmadi, F. Destelle, D. Monaghan, N. E. O'Connor, C. Richter and K. Moran, “A Framework For Comprehensive Analysis of a Swing in Sports Using Low-cost Inertial Sensors,” in {\it Proc. IEEE SENSORS}, pp. 2211-2214, 2014.

2. C.-J. Chen, Y.-T. Lin, C.-C. Lin, Y.-C. Chen, Y.-J. Lee and C.-Y. Wang, “Rehabilitation System for Limbs using IMUs,” in {\it Proc. International Symposium on Quality Electronic Design}, pp. 285-291, 2020.

3. C. Chen, C. X. Lu, J. Wahlström, A. Markham and N. Trigoni, “Deep Neural Network Based Inertial Odometry Using Low-Cost Inertial Measurement Units,” {\it IEEE Transactions on Mobile Computing}, vol. 20, no. 4, pp. 1351-1364, 2021.

4. Y.-P. Chang, T.-C. Wang, Y.-J. Lee, C.-C. Lin, Y.-C. Chen and C.-Y. Wang,“A Smart Single-Sensor Device for Instantaneously Monitoring Lower Limb Exercises,”in {\it Proc. International System-on-Chip Conference}, pp. 197-202, 2019

5. Y.-L. Chen, I.-J. Yang, L.-C. Fu, J.-S. Lai, H.-W. Liang and L. Lu, “IMU-Based Estimation of Lower Limb Motion Trajectory With Graph Convolution Network,” {\it IEEE Sensors Journal}, vol. 21, no. 21, pp. 24549-24557, 2021.

6. I. Khasanshin, “Application of an Artificial Neural Network to Automate the Measurement of Kinematic Characteristics of Punches in Boxing,” {\it Applied Sciences}, vol. 11, no. 3, pp. 1223, 2021.

7. Y.-T. Lin, C.-J. Chen, P.-Y. Kuo, S.-H. Lee, C.-C. Lin, Y.-J. Lee, Y.-T. Li, Y.-C.Chen and C.-Y. Wang, “An IMU-aided Fitness System,” in {\it Proc. International System-on-Chip Conference}, pp. 224-229, 2021.

8. M. Pedley, “High Precision Calibration of a Three-axis Accelerometer,” Freescale Semiconductor, Inc., Austin, TX, USA, Application Note AN4399, 2015.

9. T.-Y. Pan, C.-H. Kuo, H.-T. Liu and M.-C. Hu, “Handwriting Trajectory Reconstruction Using Low-Cost IMU,” {\it IEEE Transactions on Emerging Topics in Computational Intelligence}, vol. 3, no. 3, pp. 261-270, 2019.

10. T.-Y. Pan, W.-L. Tsai, C.-Y. Chang, C.-W. Yeh and M.-C. Hu, “A Hierarchical Hand Gesture Recognition Framework for Sports Referee Training-Based EMG and Accelerometer Sensors,” {\it IEEE Transactions on Cybernetics}, vol. 52, no. 5, pp. 3172-3183, 2022.

11. J. Rueterbories, E.G. Spaich, B. Larsen, O.K. Andersen, “Methods For Gait Event Detection and Analysis in Ambulatory Systems,” {\it Medical engineering \& physics}, pp. 545-552, 2010.

12. Tao W, Liu T, Zheng R, Feng H, “Gait Analysis Using Wearable Sensors,” {\it Sensors}, pp. 2255-2283, 2012.

13. T.-C. Wang, Y.-P. Chang, C.-J. Chen, Y.-J. Lee, C.-C. Lin, Y.-C. Chen and C.-Y. Wang,“IMU-based Smart Knee Pad for Walking Distance and Stride Count Measurement, in {\it Proc. International Symposium on Quality Electronic Design}, pp. 173-178, 2020

14. J. Wu, L. Sun and R. Jafari, “A Wearable System for Recognizing American Sign Language in Real-Time Using IMU and Surface EMG Sensors,” {\it IEEE Journal of Biomedical and Health Informatics}, vol. 20, no. 5, pp. 1281-1290, 2016.

15. R. Xie and J. Cao, “Accelerometer-Based Hand Gesture Recognition by Neural Network and Similarity Matching,” {\it IEEE Sensors Journal}, vol. 16, no. 11, pp. 4537-4545, 2016.

16. C. Yu, T.-Y. Huang, and H.-P. Ma, “Motion Analysis of Football Kick Based on an IMU Sensor,” {\it Sensors}, vol. 22, no. 16, pp. 6244, 2022.

17. VICON Motion Systems, https://www.vicon.com/.

18. Sea Land Technology Inc, https://sealandtech.com.tw/.