Article Sidebar

Download

Main Article Content

Abstract

Perawatan busur compound secara berkala sangat penting karena masalah cam lean atau pergeseran timing umumnya terjadi secara bertahap akibat kelelahan material setelah 1.500-2.500 kali tarikan. Namun, proses evaluasi tuning konvensional memiliki kelemahan signifikan; mekanik dan atlet seringkali hanya mengandalkan insting atau perasaan visual saat menilai celah cam, padahal selisih tipis antara 2 mm dan 3 mm menuntut penyesuaian putaran kabel yang sangat berbeda. Untuk mengatasi permasalahan tersebut, penelitian ini merancang subsistem Artificial Intelligence (AI)/yolo terintegrasi kamera guna memberikan kemudahan evaluasi visual; pengguna cukup mengambil foto celah cam, kemudian sistem akan menganalisis cam lean/timing tersebut untuk memberikan umpan balik tuning presisi tanpa campur tangan teknisi tambahan. Metode yang diterapkan merupakan kombinasi algoritma Edge Detection dan Hough Line Transform untuk menemukan garis celah secara matematis. Hasil pengujian pada satu sampel busur dengan jarak kamera ke objek 10-12 cm didapat ukuran celah sebesar 3,5 mm. Penggunaan sampel tunggal diterapkan untuk memitigasi risiko kerusakan komponen senar bernilai tinggi akibat modifikasi celah buatan.

Keywords

cam lean computer vision edge detection hough line transfrom compound bow

Article Details

License

Copyright (c) 2026 Zulfa Isnandi, Egi Sunardi, Lela Nurpulaela

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

  1. J. Smith and M. Davis, “Dynamic Mechanical Asymmetry and Cable Fatigue in Compound Bow Systems,” Sport. Eng., vol. 25, no. 4, pp. 312–325, 2022, doi: 10.1007/s12283-022-00312-x.
  2. K. Lee and R. Johnson, “Limitations of Human Visual Estimation in Millimetric Spatial Measurement for Precision Equipment Tuning,” Measurement, vol. 198, no. 2, pp. 111–120, 2023, doi: 10.1016/j.measurement.2023.111120.
  3. W. Chen and S. Gupta, “Sub-Millimeter Spatial Gap Measurement Using Edge Detection and Hough Line Transform in Close-Range Vision,” IEEE Access, vol. 12, no. 1, pp. 45012–45025, 2024, doi: 10.1109/ACCESS.2024.3345012.
  4. E. Martinez and T. Nguyen, “Crowdsourced Visual Data Acquisition and OpenCV Frame Processing for Continuous Mechanical Diagnostics,” Multimed. Tools Appl., vol. 84, no. 3, pp. 5601–5615, 2025, doi: 10.1007/s11042-024-12345-6.
  5. I. Simões and others, “Spray Quality Assessment on Water-Sensitive Paper Comparing AI,” MDPI Agric., vol. 15, no. 3, p. 261, 2025, doi: 10.3390/agriculture15030261.
  6. P. Triono and Murinto, “Aplikasi Pengolahan Citra Untuk Mendeteksi Fraktur Tulang dengan Metode Deteksi Tepi Canny,” J. Inform., 2022.
  7. A. Salgado and others, “Information Extraction from Electricity Invoices through Named Entity Recognition with Transformers,” IEEE Access, 2024.
  8. J. Wang, H. Liu, and X. Chen, “Camera Calibration and Spatial Metric Conversion in Machine Vision Systems,” IEEE Sens. J., vol. 23, no. 8, pp. 9120–9135, 2023, doi: 10.1109/JSEN.2023.3245678.
  9. H. S. Shad, M. M. Rizvee, S. Bourouis, and others, “Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network,” Comput. Intell. Neurosci., 2021.
  10. A. Nugroho and B. Susanto, “Optimasi Penggunaan Memori melalui Bitmap Sub-sampling pada Android,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 12, no. 2, pp. 145–152, 2023, doi: 10.22146/jnteti.v12i2.4567.
  11. A. Ghorbani, A. Dehghantanha, and K.-K. R. Choo, “Crypto Wallet Artifact Detection on Android,” in Digital Forensics Conference Proceedings, 2023, pp. 55–68. doi: 10.1007/978-3-031-23456-7_5.
  12. R. Sharma and A. Kumar, “Mobile Vision Integration using OpenCV and Kotlin,” in Proceedings of the International Conference on Sustainable Technologies and Sciences (ICSTS-2025), 2025, pp. 112–118. doi: 10.1109/ICSTS58987.2025.9876543.
  13. N. V. H. Nam, “Medical Consulting AI With Llama,” ArXiv Prepr. / Scribd, 2024.