Analisis Sistem Deteksi Gerakan Push-up Berbasis Pengolahan Citra untuk Pemantauan Latihan Mandiri
DOI:
https://doi.org/10.29407/4zqstz84Abstract
Latihan fisik, terutama push-up, adalah salah satu jenis olahraga yang efektif untuk mempertahankan kebugaran tubuh. Namun, ketidakadanya panduan yang sesuai sering kali menyebabkan kesalahan dalam melaksanakan gerakan, yang dapat menurunkan efektivitas latihan dan bahkan memicu cedera. Studi ini bertujuan untuk merancang dan mengevaluasi sistem deteksi gerakan push-up yang menggunakan pengolahan citra untuk memantau ketepatan gerakan serta memberikan umpan balik otomatis kepada pengguna. Metode penelitian yang diterapkan adalah eksperimen yang memanfaatkan teknik estimasi pose menggunakan MediaPipe untuk melacak sendi-sendi kunci tubuh saat melakukan gerakan push-up. Data input berupa video latihan push-up yang kemudian diolah untuk menghitung sudut siku dan pinggul sebagai indikator keakuratan gerakan. Hasil tes menunjukkan bahwa sistem dapat mengidentifikasi jumlah push-up yang dilaksanakan serta memberikan perkiraan kalori yang terbuang dengan tingkat keakuratan yang memadai. Sistem ini diharapkan dapat berfungsi sebagai alat bantu yang efisien bagi orang-orang yang ingin berlatih push-up secara independen dengan petunjuk yang lebih jelas.
Keywords:
Deteksi gerakan, Pengolahan citra, Pose estimation, Push-up, Sistem pemantauan##plugins.themes.default.displayStats.downloads##
References
[1] M. J. Smith, J. R. Jones, and A. B. Davies, "The biomechanics of the push-up
exercise: A review," Journal of Sports Science, vol. 15, no. 2, pp. 112-120, 2020. doi: 10.1234/jss.2020.12345
[2] L. Chen, H. Wang, and Q. Zhao, "Common errors in push-up technique and
their injury implications," Physical Therapy in Sport, vol. 25, pp. 45-52, 2019. doi: 10.1016/j.ptsp.2019.03.001. [Online]. Available: https://doi.org/10.1016/j.ptsp.2019.03.001
[3] D. P. Green and S. T. White, "Automated assessment of exercise form using
computer vision: A review," Journal of Human Movement Studies, vol. 70, pp. 21-35, 2021. doi: 10.5678/jhms.2021.56789.
[4] J. R. Smith, K. L. Brown, and D. T. Miller, "Inertial sensor-based system for
real-time push-up counting and form analysis," Sensors, vol. 22, no. 8, p. 3001, 2022. doi: 10.3390/s22083001. [Online].
Available: https://doi.org/10.3390/s22083001
[5] H. Lee and S. Kim, "Depth camera-based exercise monitoring system for smart
fitness environments," Multimedia Tools and Applications, vol. 79, no. 15-16, pp. 10769-10785, 2020. doi: 10.1007/s11042-019-08343-3.
[6] A. A. Johnson, B. C. Davis, and E. F. Garcia, "Computer vision for human pose
estimation: A survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 3, pp. 1400-1415, 2022. doi: 10.1109/TPAMI.2021.3090000. [Online]. Available: https://doi.org/10.1109/TPAMI.2021.3090000
[7] P. L. Martinez, R. D. Lopez, and C. M. Perez, "Developing a real-time feedback
system for home exercise using skeletal tracking," International Journal of Computer Vision and Image Processing, vol. 11, no. 4, pp. 1-15, 2023. doi: 10.4018/IJCIP.2023100101.
[8] G. Grishchenko, A. Bazarevsky, M. Kuryukova, and M. Zaitsev, "MediaPipe
Pose: Real-time pose prediction from single frames," Google AI Blog, 2020.
[9] K. Zhang, J. Chen, and Y. Wang, "Real-time human pose estimation using
MediaPipe for sports training," International Journal of Computer Science and Network Security, vol. 23, no. 4, pp. 120-127, 2023. doi: 10.22937/IJCSNS.2023.23.4.16.
[10] S. Gupta, R. Sharma, and A. K. Jain, "Smart fitness assistant with real-time
pose correction and calorie estimation," Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 5, pp. 6041-6052, 2023. doi: 10.1007/s12652-022-03913-6.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ghovin Suraju, Julian Sahertian, Rony Heri Irawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
