跳繩是個常見的休閒活動，同時也是一項競技運動，是一種簡單、高強度，且無論老小都能進行的有氧活動，不論是減脂塑身或是健身鍛鍊的族群都很適合進行跳繩運動。2021年台灣Covid-19疫情爆發，多數實體課程都改為線上教學，而體育課於線上教學時老師難以即時教導每位學生做出正確的動作，若學生做出錯誤的動作卻無察覺，長期於不適當的關節角度進行運動所累積的習慣，嚴重的後果恐引發運動傷害。OpenPose影像辨識模型可透過影像取得人體關節點位置、建立人體骨架，具高便利性與即時性，此模型已廣泛應用於在運動姿勢輔助上，分析人體運動過程中的關節點位置，提醒使用者調整運動姿勢。
本研究建立一套OpenPose跳繩姿勢即時偵測之系統，僅需透過手機拍攝人體矢狀面跳繩的過程，藉由OpenPose影像辨識模型建立人體骨架。並計算人體關節角度，針對指定下肢關節(如髖關節、膝關節與踝關節)的關節角度，即時分析使用者在跳繩運動時指定下肢關節角度是否有建議範圍內，若關節角度不在建議範圍內則發出警訊請使用者調整姿勢，進而降低錯誤姿勢帶來的運動傷害。並且為了避免系統誤導使用者，使用Vicon光學式動作捕捉系統驗證關節角度計算之正確性。經由統計結果顯示，本研究以OpenPose計算膝關節與踝關節角度的結果與Vicon比較，分別於著地期與空中期具顯著差異，而髖關節角度計算結果不論在任何階段皆無顯著差異，且平均而言兩種方法計算關節角度的相關係數不論在髖、膝、踝皆高於0.85以上。表示本研究發展之系統，對於使用者跳繩角度的辨識具一定程度的正確性，可應用於實際場景，若往後可根據不同運動參數提供不同的建議角度範圍，將能給予使用者更多有效的資訊。而其他運動亦可依照此系統之方法，界定該運動的建議特定關節角度範圍，以提供使用者安全且便利的運動偵測系統。

Rope skipping is a common recreational activity and a competitive sport. It is a simple, high-intensity aerobic exercise that can perform suitable for individuals who are to lose weight, tone their bodies, or engage in fitness training. In 2021, during the outbreak of the Covid-19 pandemic in Taiwan, most physical classes shifted to online teaching. During online physical education classes, teachers found it difficult to provide real-time guidance on correct movements for each student. Suppose students unknowingly perform incorrect movements and continue to exercise with improper joint angles for an extended period, In that case it can lead to sever consequences and increase the risk of sports injuries. The OpenPose image recognition model can capture the positions of human body joints and create a skeletal structure based on images. It offers high convenience and real-time capabilities, and has been widely used in assisting sports posture analysis by analyzing joint positions during human body movements, thus alerting users to adjust their exercise postures.
This research aims to develop a real-time detection system for rope skipping postures using OpenPose. By capturing the process of sagittal plane rope skipping using a smartphone camera and utilizing the OpenPose image recognition model to create a skeletal structure, the system calculates the joint angles of the human body. Specifically focusing on the specified lower limb joints such as the hip, knee, and ankle joints, the system analyzes in real-time whether the joint angles during periods of rope skipping fall within the recommended range. Suppose the joint angles are not within the recommended range. In that case, the system issues a warning to prompt the user to adjust their posture, thereby reducing the risk of injuries caused by incorrect postures. Additionally, to ensure the accuracy of joint angle calculations, the system is validated using the Vicon optical motion capture system to avoid misleading the user. According to the statistical results, the angle calculations of the knee and ankle joints using OpenPose in both the landing and flight phases showed significant differences. However, there were no significant differences between the OpenPose and Vicon methods in calculating hip joint angles at any phase. On average, the correlation coefficients between the two methods for joint angle calculations were all above 0.85 for the hip, knee, and ankle joints. This indicates that the system developed in this study demonstrates a certain level of accuracy in recognizing user rope skipping angles and can be applied in real-world scenarios. If in the future, different recommended angle ranges can be provided based on various sports parameters, it would give the users more practical information. Similarly, this system's methodology can be applied to other sports to define specific recommended joint angle ranges, offering users a safe and convenient motion detection system.

中文部分
1. Chiu, H. (2020).論文閱讀筆記—人體姿態辨識 AlphaPose, RMPE: Regional Multi-Person Pose Estimation. Medium.
2. Crossrope.如何跳繩：跳繩訓練之完整初學者指南
3. Vicon系統Plug In Gait Full-Body Model
4. 謝明達、陳五洲、邱文信(2008)。「跳繩」動作關鍵因素之探討。中華體育季刊，22(1)，97-105。
5. 陳甫銓(2022)。垂直跳(Vertical Jump)的動作分析與彼拉提斯應用。陳甫銓的物理治療筆記。

外文部分
1. Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., & Sheikh, Y. (2021). OpenPose: realtime muti-person 2D pose estimation using Part Affinity Fields. IEEE transactions on pattern analysis and machine intelligence, 43(1), 172-186.
2. Chang, R., Chang. M., Wang. L., & Gu. C. (2010). The Influence of Knee Joint Angle Change on Vertically Squat Jumps Performance. Chinese Journal of Sports Biomechanics, 20(1), 57-63.
3. Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences. (second ed.) Phycology Press, New York.
4. Fani, H., Mirlohi, A., Hosseini, H., & Horaud, R. (2014). Swim Stroke Analytic: Front Crawl Pulling Pose Classification. 2018 25th IEEE International Conference on Image Preocessing(ICIP).
5. Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J. (2021, April). Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression. Paper presented at the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
6. Go, D. S., Hyung, H. J., Lee, D. W., & Yoon, H. U. (2018). Andorid Robot Motion Generation Based on Video-Recorded Human Demonstrations. 2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
7. Guo. S., Chiu. W. (2013). On the Sport Training of Different Frequencies of Rope Jumping. Wushu Science. 10(12)，105-108.
8. Jin, S., Ma, X., Han, Z., Wu, Y., Yang, W., Liu, W., Qian, C., Ouyang, W. (2017). Towards Mutlti-Person Pose Tracking: Bottom-up and Top-down Methods.
9. Lin, Y., Jiao, X., Zhao, L. (2023). Detection of 3D Human Posture Based on Improved Mediapipe. Journal of Computer and Communications. 11(2).
10. Lohmander, L., Engkund, P., Dahl, L., & Roos, E. (2007). The Long-term Consequence of Anterior Cruciate Ligament and Meniscus Injuries: Osteoarthritis. The American Journal of Sports Medicine. 35(10).
11. Lohmander, L., Ostenberg, A., Englund, M., & Roos, H. (2004). High prevalence of knee osteoarthritis, pain, and functional limitations in female soccer players twelve years after anterior cruciate ligament injury. Arthritis, & Rheumatism. 50(10), 3145-3152.
12. Lohmander, L., & Roos, H. (1994). Knee ligament injury, surgery and osteoarthrosis: Truth or consequences? Acta Orthopaedica Scandinavica. 65 (6), 605-609.
13. Mehdizadeh, S., Arshi, A. R., & Davids, k. (2014). Effect of speed on local dynamics stability of locomotion under different task constraints in running. European journal of sport science, 14(8), 791-798.
14. Hsieh. M., Chiu. W. (2009). The Study of Coordination among Lower Limb Joints for Different Jumping Frequencies of Rope Jumping. Physical Education Journal. 42(3). 17-28.
15. Mullerpatan, R., Shetty, T., Singh, Y., Agarwal, B. (2021). Lower extremity joint loading during Bounce rope skip in comparison to run and walk. Journal of Bodywork, & Movement Therapies. 26, 1-6.
16. Niiyama, R., Nagakubo, A., Kuniyoshi., Y. (2007). Mowgli: A Bipedal Jumping and Landing Robotwith an Artificial Musculoskeletal System. Paper Present at the 2007 IEEE International Conference on Robotics and Automation.
17. Ota, M., Tateuchi, H., Hashiguchi, T., Kato, T., Ogino, Y., Yamagata, M., & Ichihashi, N. (2020). Verification of reliability and validity of motion analysis systems during bilateral squat using human pose tracking algorithm. Gait Posture. 80, 62-67.
18. Ota, M., Tateuchi, H., Hashiguchi, T., Ichihashi, N. (2021). Verification of validity of gait analysis systems during treadmill walking and running using human pose tracking algorithm. Gait & Posture. 85, 290-297
19. Paletta, G. A. (2003). Special consideration anterior cruciate ligament reconstruction in the skeletally immature. Orthopedic Clinics of North America, 34(1), 65-77.
20. Paszkowska, M., S., Powroznik, P., & Lukasik, E., (2020). Learning Three Dimensional Tennis Shots Using Graph Convolutional Networks. Sensors. 20(6094).
21. Qiao, S., Wang, Y., Li, J. (2017). Real-Time Human Gesture Grading Based on OpenPose. Paper presented at the 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
22. Rahul, M. (2018). Review on motion capture technology. Global Journal of Computer Science and Technology.
23. Ribeiro, T. H., & Viera, M. L. H. (2016). Motion Capture Technology- Benefits and Challenges. Int. J. Innov. Res. Teschnol. Sci. Int. J. Innov. Res. Technol. Sci, 48(1), 2321- 1156.
24. Salonen, S. (2021). Motion capture in 3D animation. Faculty of Information Technology and Communication Sciences
25. Schlagenhauf, F., Sreeram, S.; Singhose, W. (2018). Comparison of Kinect and Vicon Motion Capture of Upper-Body Joint Angle Tracking. Paper presented at the 2018 IEEE 14th International Conference on Control and Automation (ICCA).
26. Tian, Y. (2021). Biomechanical Properties of Multi-Swing and Single-Swing Rope Skipping Actions. Molecular, & Cellular Biomechanics, 18(1), 41-49.
27. Trecroci, A., Cavaggioni, L., Caccia, R., Alberti, G. (2015). Jump Rope Training: Balance and Motor Coordination in Preadolescent Soccer Players. Journal of Sports Science and Medicine. 14, 792-798.
28. Veena Kirthika. S, Lakshmanan. R, Padmanabhan, K, Selvaraj Sudhakar, Senthil Selvam., P. (2019). The Effect of Skipping rope Exercise on Physical and Cardiovascular fitness among Collegiate Males. Research J. Pharm. and Tech, 12(10) , 0974-360X.
29. Viswakumar, A., Rajagopalan, V., Ray, T., & Parimi, C. (2019). Human gait analysis using Openpose. Paper Present at the 2019 Fifth International Conference on Image Information Processing (ICIIP).
30. Von Porat, A., Roos, E., & Roos, H.(2003). High prevalence of osteoarthritis 14 years after an anterior cruciate ligament tear in male soccer players: a study of radiographic and patient relevant outcomes. Annals of the Rheumatic Diseases. 63(3), 269-273.
31. Wang, H., & Lee, Y. (2019). Occupational evaluation with Rapid Entire Body Assessment(REBA) via imaging processing in field. Human Factors Society Conference.
32. Zhao. Q., Wang. Y., Niu. Y., Liu. S. (2023). Jumping Rope Improves the Physical Fitness of Preadolescents Aged 10-12 Years: A Meta-Analysis. Journal of sports science & medicine. 22(2). 367-380.