Accuracy Evaluation of 2D MediaPipe-Based Pose Estimation for Archery Posture Detection Using N-MPJPE

Muhammad Andhika Bayu Prasetya; Harits Ar Rosyid; M. Zainal Arifin

doi:10.15408/jti.v19i1.49778

Authors

Muhammad Andhika Bayu Prasetya Department of Electrical Engineering and Informatics, State University of Malang
Harits Ar Rosyid Departement of Electrical Engineering and Informatics, Faculty of Engineering, State University of Malang
M. Zainal Arifin Departement of Electrical Engineering and Informatics, Faculty of Engineering, State University of Malang

DOI:

https://doi.org/10.15408/jti.v19i1.49778

Keywords:

Archery, Mediapipe, N-MPJPE, 2D Human Pose Estimation, Computer Vision

Abstract

Archery requires high consistency and precise body posture, where small deviations can affect stability and accuracy. Recently, 2D human pose estimation has become an effective approach for analyzing sports techniques through automatic joint detection. This study proposes a 2D pose estimation system based on the MediaPipe framework to detect eight fundamental phases of archery technique and evaluate accuracy using the Normalized Mean Per Joint Position Error (N-MPJPE) metric. The dataset consists of annotated images representing the eight phases, which serve as ground-truth references. Accuracy is measured by calculating the normalized Euclidean distance between predicted joint positions and ground-truth coordinates across all phases. Experimental results show an average N-MPJPE of 0.71, indicating low joint-position deviation after scale normalization. Compared with prior studies reporting N-MPJPE values between 0.6 and 1.2, the proposed system demonstrates competitive accuracy for real-time 2D pose estimation. These results indicate that the system can reliably capture posture variations across archery phases and provide quantitative feedback on body alignment, making it a practical tool to support athletes and coaches in improving training quality and shooting performance.

References

[1] C. Mulyanti et al., “Differences in Archery Skill Results for Vocational School Students and Beginners Based on Shooting Distance,” Retos, vol. 55, pp. 957–962, Aug. 2024, doi: 10.47197/retos.v55.106081.

[2] D. Destriani et al., “Results of Beginner Archery Skills Among Adolescents Based on Gender Review and Shot Distance,” Retos, vol. 56, pp. 887–894, Aug. 2024, doi: 10.47197/retos.v56.106629.

[3] K. Ludwig, S. Scherer, M. Einfalt, and R. Lienhart, “Self-Supervised Learning for Human Pose Estimation in Sports,” in 2021 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2021, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/ICMEW53276.2021.9456000.

[4] S. Lee, J. Y. Moon, J. Kim, and E. C. Lee, “AI-Based Analysis of Archery Shooting Time from Anchoring to Release Using Pose Estimation and Computer Vision,” Appl. Sci., vol. 14, no. 24, Dec. 2024, doi: 10.3390/app142411838.

[5] H. Chen, R. Feng, S. Wu, H. Xu, F. Zhou, and Z. Liu, “2D Human pose estimation: a survey,” Multimed. Syst., vol. 29, no. 5, pp. 3115–3138, 2023, doi: 10.1007/s00530-022-01019-0.

[6] J.-L. Chung, L.-Y. Ong, and M.-C. Leow, “Comparative analysis of skeleton-based human pose estimation,” Futur. Internet, vol. 14, no. 12, p. 380, Dec. 2022.

[7] N. Andriyanov and S. Mikhailova, “Improving Gesture Recognition Efficiency with MediaPipe and YOLO-Pose,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. XLVIII-2/W9-2025, pp. 13–18, 2025, doi: 10.5194/isprs-archives-XLVIII-2-W9-2025-13-2025.

[8] D. F. Al Muzaki, Tino Feri Efendi, and M. Muqorobin, “Penerapan Jaringan Hotspot Berbasis Mikrotik Menggunakan Metode PPDIO (Prepare, Plan, Design, Implement, Operate, Optimize),” Bull. Comput. Sci. Res., vol. 5, no. 4 SE-, pp. 490–502, Jun. 2025, doi: 10.47065/bulletincsr.v5i4.592.

[9] M. N. Ahmadi, D. Risqiwati, and B. F. Muthohirin, “Optimalisasi Jaringan MikroTik Dengan Menggunakan Load Balancing PCC dengan Pendekatan PPDIOO,” J. Algoritm., vol. 22, no. 2 SE-Artikel, pp. 632–643, Nov. 2025, doi: 10.33364/algoritma/v.22-2.2878.

[10] D. Saputra, M. T. Kurniawan, and M. Fathinuddin, “Analysis of Quality of Service in Software Defined Networks Using the Opendaylight Controller with Prepare, Plan, Design, Implement, Operate, Optimize Method,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 10, no. 4, pp. 3396–3405, 2025.

[11] A. A. A. Fernandes, M. Koehler, N. Konstantinou, P. Pankin, N. W. Paton, and R. Sakellariou, “Data Preparation: A Technological Perspective and Review,” SN Comput. Sci., vol. 4, no. 4, Jul. 2023, doi: 10.1007/s42979-023-01828-8.

[12] J. Stenum, K. M. Cherry-Allen, C. O. Pyles, R. D. Reetzke, M. F. Vignos, and R. T. Roemmich, “Applications of pose estimation in human health and performance across the lifespan,” Nov. 01, 2021, MDPI. doi: 10.3390/s21217315.

[13] P.-O. Côté, A. Nikanjam, N. Ahmed, D. Humeniuk, and F. Khomh, “Data cleaning and machine learning: a systematic literature review,” Autom. Softw. Eng., vol. 31, no. 2, p. 54, 2024, doi: 10.1007/s10515-024-00453-w.

[14] M. Arzt et al., “LABKIT: Labeling and Segmentation Toolkit for Big Image Data,” Front. Comput. Sci., vol. Volume 4-2022, 2022, doi: 10.3389/fcomp.2022.777728.

[15] J. Liu, G. Huang, J. Hyyppä, J. Li, X. Gong, and X. Jiang, “A survey on location and motion tracking technologies, methodologies and applications in precision sports,” Expert Syst. Appl., vol. 229, p. 120492, 2023, doi: https://doi.org/10.1016/j.eswa.2023.120492.

[16] J.-W. Kim, J.-Y. Choi, E.-J. Ha, and J.-H. Choi, “Human Pose Estimation Using MediaPipe Pose and Optimization Method Based on a Humanoid Model,” Appl. Sci., vol. 13, no. 4, 2023, doi: 10.3390/app13042700.

[17] G. Dibenedetto, S. Sotiropoulos, M. Polignano, G. Cavallo, and P. Lops, “Comparing Human Pose Estimation through deep learning approaches: An overview,” Comput. Vis. Image Underst., vol. 252, p. 104297, 2025, doi: https://doi.org/10.1016/j.cviu.2025.104297.

[18] Achmad Ivan Taruna Jaya, P. Puspitaningayu, A. P. Adiwangsa, and N. Funabiki, “Two-dimensional Human Pose Estimation using Key Points’ Angular Detection for Basic Strength Training,” J. Intell. Syst. Telecommun., vol. 1, no. 1, pp. 105–119, Dec. 2024, doi: 10.26740/jistel.v1n1.p105-119.

[19] Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M. G., Lee, J., Chang, W.-T., Hua, W., Georg, M., & Grundmann, M. (2019). MediaPipe: A Framework for Building Perception Pipelines. http://arxiv.org/abs/1906.08172

[20] Mitrović, K., & Milošević, D. (2023). Pose Estimation and Joint Angle Detection Using Mediapipe Machine Learning Solution. In N. Filipovic (Ed.), Applied Artificial Intelligence: Medicine, Biology, Chemistry, Financial, Games, Engineering (pp. 109–120). Springer International Publishing.

[21] Phang, J. T. S., Lim, K. H., Lease, B. A., & Chiam, D. H. (2022). Deep Learning Pose Estimation for Kinematics Measurement in Archery. 2022 International Conference on Green Energy, Computing and Sustainable Technology (GECOST), 298–302. https://doi.org/10.1109/GECOST55694.2022.10010619

[22] Putra, A. A. A. W., Suranata, I. W. A., & Kusumawati, A. A. I. P. (2024). Pengembangan Prototype Aplikasi MedCov Indonesia dengan Metode Human Centered Design dan Usability Testing. Jurnal Algoritma, 21(2), 91–100. https://doi.org/10.33364/algoritma/v.21-2.1970

[23] Rhodin, H., Constantin, V., Katircioglu, I., Salzmann, M., & Fua, P. (2019, June). Neural Scene Decomposition for Multi-Person Motion Capture. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24] SIMOES, W., REIS, L., ARAUJO, C., & MAIA JR., J. (2024). Accuracy Assessment of 2D Pose Estimation with MediaPipe for Physiotherapy Exercises. Procedia Computer Science, 251, 446–453. https://doi.org/https://doi.org/10.1016/j.procs.2024.11.132

[25] Sukarno, P., & Medina, F. R. (2025). Enhancing IoT Security: Optimizing PUF Responses through Pre-Processing Techniques. JURNAL INFOTEL, 17(2), 210–228. https://doi.org/10.20895/infotel.v17i2.1236

[26] Totlani, K., Dhavala, S. S., Vijayarao, S. S. K., Challagundla, Y., Roy, B., & Zhuo, E. R. (2024). Real-Time Human Pose Estimation Using Media-Pipe an Artificial Intelligence Applications in Health and Fitness. 2024 4th International Conference on Artificial Intelligence and Signal Processing (AISP), 1–6. https://doi.org/10.1109/AISP61711.2024.10870725

[27] Vendrame, E., Belluscio, V., Truppa, L., Rum, L., Lazich, A., Bergamini, E., & Mannini, A. (2024). Performance assessment in archery: a systematic review. In Sports Biomechanics (Vol. 23, Issue 12, pp. 2444–2466). Routledge. https://doi.org/10.1080/14763141.2022.2049357

[28] Wang, J., Qiu, K., Peng, H., Fu, J., & Zhu, J. (2019). AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance. Proceedings of the 27th ACM International Conference on Multimedia, 374–382. https://doi.org/10.1145/3343031.3350910

[29] Zheng, C., Wu, W., Chen, C., Yang, T., Zhu, S., Shen, J., Kehtarnavaz, N., & Shah, M. (2023). Deep Learning-based Human Pose Estimation: A Survey. ACM Comput. Surv., 56(1). https://doi.org/10.1145/3603618

[30] Debnath, S., & Debnath, S. (2018). Performance Evaluation by Image Processing Techniques in Archery – A Case Study.

[31] Arif, A., Ghadi, Y. Y., Alarfaj, M., Jalal, A., Kamal, S., & Kim, D. S. (2022). Human Pose Estimation and Object Interaction for Sports Behaviour. Computers, Materials and Continua, 72(1), 1–18. https://doi.org/10.32604/cmc.2022.023553

[32] Arkin, I., & Budak, M. (2021). Trunk stabilization, body balance, body perception, and quality of life in professional physically disabled and able-bodied archers. Sport Sciences for Health, 17(4), 881–889. https://doi.org/10.1007/s11332-021-00744-9

[33] Badiola-Bengoa, A., & Mendez-Zorrilla, A. (2021). A systematic review of the application of camera-based human pose estimation in the field of sport and physical exercise. In Sensors (Vol. 21, Issue 18). MDPI. https://doi.org/10.3390/s21185996

[34] Lin, Z., Chen, H., Rao, F., & Li, D. (2022). Application of AI Motion Capture Technology in Archery Teaching. HBDSS 2022; 2nd International Conference on Health Big Data and Smart Sports, 1–5.

[35] Ferraris, C., Amprimo, G., Cerfoglio, S., Vismara, L., & Cimolin, V. (2025). A Deep Dive Into MediaPipe Pose for Postural Assessment: A Comparative Investigation. IEEE Access, 13, 211055–211074. https://doi.org/10.1109/ACCESS.2025.3643126

[36] Garg, S., Saxena, A., & Gupta, R. (2023). Yoga pose classification: a CNN and MediaPipe inspired deep learning approach for real-world application. Journal of Ambient Intelligence and Humanized Computing, 14(12), 16551–16562. https://doi.org/10.1007/s12652-022-03910-0

[37] Ji, X., Al Tamimi, Z., Gao, X., & Piovesan, D. (2025). The Impact of Draw Weight on Archers’ Posture and Injury Risk Through Motion Capture Analysis. Applied Sciences (Switzerland), 15(2). https://doi.org/10.3390/app15020879

[38] Knap, P., Hardy, P., Tamajo, A., Lim, H., & Kim, H. (2024). Improving Real-Time Omnidirectional 3D Multi-Person Human Pose Estimation with People Matching and Unsupervised 2D-3D Lifting. 2024 International Conference on Electronics, Information, and Communication (ICEIC), 1–4. https://doi.org/10.1109/ICEIC61013.2024.10457094

[39] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. In F. Pereira, C. J. Burges, L. Bottou, & K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems (Vol. 25). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

[40] Lease, B. A., Lim, K. H., Phang, J. T. S., & Zuo, H. (2024). Deep Learning Posture Estimation for Archery Consistency Measurement. 2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), 1770–1773. https://doi.org/10.1109/ICICML63543.2024.10957898

[41] Difini, G. M., Martins, M. G., & Barbosa, J. L. V. (2021). Human Pose Estimation for Training Assistance: a Systematic Literature Review. Proceedings of the Brazilian Symposium on Multimedia and the Web, 189–196. https://doi.org/10.1145/3470482.3479633

[42] Elrashdi, A. S., Alferjani, S. K., Omar, R. R., & Hasan, F. M. (2024). The efficiency of using PPDIOO Methodology to Design Graduation Projects for Network Department Students. 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP), 1, 438–442. https://doi.org/10.1109/ATSIP62566.2024.10638951

[43] Fang, H.-S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., Li, Y.-L., & Lu, C. (2023). AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6), 7157–7173. https://doi.org/10.1109/TPAMI.2022.3222784