PERANCANGAN SISTEM DETEKSI GERAKAN DASAR PENCAK SILAT MERPATI PUTIH MENGGUNAKAN YOLOV8
DOI:
https://doi.org/10.33480/inti.v21i1.8773Keywords:
Pencak Silat Merpati Putih, YOLOv8-pose, Computer Vision, Cosine Similarity, Pose DetectionAbstract
Pencak Silat Merpati Putih is an Indonesian cultural heritage martial art that demands high precision in the mastery of its movement techniques. This research specifically focuses on verifying the correctness of a movement's final pose, rather than evaluating the complete sequence, speed, or transition of the movement. The training and evaluation processes, particularly during the Promotion Exams (UKT), still face challenges regarding the subjectivity of examiner assessments and limitations in providing real-time quantitative feedback. This research aims to design a basic movement detection system for Pencak Silat Merpati Putih capable of assessing technical correctness automatically and objectively. The system was developed using Deep Learning methods with the pretrained YOLOv8 Pose algorithm for skeleton extraction and Cosine Similarity to verify the similarity of user movements against the trainer’s reference movements. The analysis process involves coordinate normalization using the body center and torso length to address variations in user distance and posture. Based on system testing, a similarity threshold of 0.95 (95%) was established heuristically. The system successfully detected movements with an average similarity score of 98.1% for correct movements and 91.0% for incorrect movements (based on 31 interactions recorded in the system log), operating in real-time at an average speed of 28–35 FPS. This research produced a prototype of an independent training tool effective in maintaining the standardization of Merpati Putih basic techniques and digitally documenting athletes’ training history.
Downloads
References
Ahmad Asshidiqy, R., Setiawan, A., & Sasongko, D. (2022). Penerapan metode PoseNet untuk deteksi ketepatan pose yoga. Journal of Computer System and Informatics, 4(1), 31–38. https://doi.org/10.47065/josyc.v4i1.2444
Alzahrani, N., Bchir, O., & Ben Ismail, M. M. (2025). YOLO-Act: Unified spatiotemporal detection of human actions across multi-frame sequences. Sensors, 25(10), 1–24. https://doi.org/10.3390/s25103013
Bachri, O. S., & Muhami, R. (2023). Komparasi metode SAW dan MFEP pada penyeleksian kenaikan tingkat pencak silat PSHT. Jurnal Ilmiah Intech: Information Technology Journal of UMUS, 5(2), 162–169. https://doi.org/10.46772/intech.v5i2.1410
Bahriyanto, A., Raharjo, B. B., Rahayu, S., & Irawan, F. A. (2023). Literature study: Development of Pencak Silat measurement and evaluation test instruments. Proceedings of International Conference on Science, Education, and Technology, 9(1), 43–47.
Cai, S., Xu, H., Cai, W., et al. (2025). A human pose estimation network based on YOLOv8 framework with efficient multi-scale receptive field and expanded feature pyramid network. Scientific Reports, 15, 15284. https://doi.org/10.1038/s41598-025-00259-0
Chen, D., & Zhang, S. (2025). Deep learning-based involution feature extraction for human posture recognition in martial arts. Informatica, 49(12), 77–90. https://doi.org/10.31449/inf.v49i12.7041
Dyansyah, K. R. K., Purwantoro, S. D., & Ilmi, M. (2025). Penggunaan computer vision untuk estimasi pose squat sebagai solusi alternatif latihan kebugaran di gym. Seminar Nasional Teknologi Sains, 4, 199–207.
Gu, K., & Su, B. (2024). A study of human pose estimation in low-light environments using YOLOv8 model. Applied Computer Engineering, 32(1), 136–142. https://doi.org/10.54254/2755-2721/32/20230200
Hardiansyah, B., & Hermawati, F. A. (2025). Human pose estimation and tracking via keypoints detection. International Conference on Innovation and Community Engagement, 146–154.
Hardovi, B. H., et al. (2025). Technological innovation in pencak silat training as a component of Indonesian cultural heritage: A systematic literature review. Physical Education Theory and Methodology, 25(2), 434–443. https://doi.org/10.17309/tmfv.2025.2.26
Hawe, H. H., Imanudin, I., & Umaran, U. (2025). Analysis of the quality of basic Pencak Silat techniques in Pencak Silat athletes of the Pamur Banyuwangi School, Srono Branch. ACTIVE: Journal of Physical Education, Sport, Health and Recreation, 14(2), 582–588. https://doi.org/10.15294/active.v14i2.26802
Murat, A. A., & Kiran, M. S. (2025). A comprehensive review on YOLO versions for object detection. Engineering Science and Technology, an International Journal, 70, Article 102161. https://doi.org/10.1016/j.jestch.2025.102161
Pramana Widagda, S., Prasetyanto, H., Suharto, T., & Yuwono, suselo H. (2022). Atraksi Pencaksilat Merpati Putih Sebagai Daya Tarik Wisata Dalam Upaya Melestarikan Warisan Budaya Indonesia. Media Wisata, 20(1), 136–147. https://doi.org/10.36276/mws.v20i1.316
Rahmawati, V. N., Yuniarto, E. M., & Nugroho, S. M. S. (2023). Pencak silat movement classification using CNN based on body pose. Journal of Advanced Research in Electrical Engineering (JAREE), 7(2), 99–105. https://doi.org/10.12962/jaree.v7i2.369
Ratnadewi, R., Prijono, A., Hangkawidjaja, A. D., Rustiyanti, S., & Al Badri, D. (2026). Angle-based pose analysis for digital documentation and learning support of Ibing Penca stances in Pencak Silat. Journal of Applied Science, Engineering, Technology, and Education, 8(1), 102–118. https://doi.org/10.35877/454RI.asci4539
Sarinastiti, W., Setyowati, A. D., & Basuki, A. (2022). Analisis dataset video gerakan dasar taekwondo dengan motion capture. Jurnal Sistem Informasi dan Bisnis Cerdas, 15(2), 45–53.
Sun, Y., Deng, R., & Wei, D. (2025). ST-LineNet: A spatiotemporal network for real-time 3D pose estimation in martial arts training. Alexandria Engineering Journal, 117, 136–147. https://doi.org/10.1016/j.aej.2024.12.097
Wu, Y., Chen, Z., Zhang, H., Yang, Y., & Yi, W. (2025). Enhanced pose estimation for badminton players via improved YOLOv8-Pose with efficient local attention. Sensors, 25(14), 1–21. https://doi.org/10.3390/s25144446
Xu, X., et al. (2025). Enhanced human pose estimation using YOLOv8 with integrated SimDLKA attention mechanism and DCIOU loss function. PLoS ONE, 20(5), 1–16. https://doi.org/10.1371/journal.pone.0318578
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rahmat Ramadhan, Dr. Kurniabudi, Willy Riyadi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Penulis yang menerbitkan jurnal ini menyetujui ketentuan berikut:
1. Penulis memegang hak cipta dan memberikan hak jurnal mengenai publikasi pertama dengan karya yang dilisensikan secara bersamaan di bawah Creative Commons Attribution 4.0 International License. yang memungkinkan orang lain untuk berbagi karya dengan pengakuan atas karya penulis dan publikasi awal pada jurnal.
2. Penulis dapat memasukkan pengaturan kontrak tambahan yang terpisah untuk distribusi non-eksklusif dari versi jurnal yang diterbitkan (misalnya, mengirimkannya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan atas publikasi awalnya pada Jurnal.
3. Penulis diizinkan dan didorong untuk memposting karya mereka secara online (misalnya, dalam penyimpanan institusional atau di situs web mereka) sebelum dan selama proses pengiriman, karena hal itu dapat menghasilkan pertukaran yang produktif, serta kutipan dari karya yang diterbitkan sebelumnya.
