Optimasi Deteksi Nomor Lambung Truk Tambang Menggunakan YOLOv11 Berbasis Augmentasi Data

Tri Prianto; Muhammad Sobirin; Jemie Muliadi

doi:10.30595/jrre.v8i1.29522

Authors

Tri Prianto Universitas 17 Agustus 1945 Jakarta
Muhammad Sobirin Universitas 17 Agustus 1945 Jakarta
Jemie Muliadi Universitas 17 Agustus 1945 Jakarta

DOI:

https://doi.org/10.30595/jrre.v8i1.29522

Keywords:

YOLOv11, deteksi objek, augmentasi data, truk tambang, computer vision

Abstract

Identifikasi nomor lambung truk tambang secara manual masih banyak diterapkan pada operasi tambang terbuka dan rentan terhadap kesalahan manusia akibat debu, pencahayaan tidak stabil, serta sudut pandang kamera yang tidak ideal. Penelitian ini bertujuan mengoptimalkan deteksi nomor lambung truk menggunakan algoritma You Only Look Once versi 11 (YOLOv11) melalui tahapan preprocessing dan data augmentation. Preprocessing meliputi Auto-Orient dan Resize (Stretch to 640×640), sedangkan data augmentation menggabungkan manipulasi fotometrik (brightness, noise) dan geometrik (blur) untuk meningkatkan generalisasi model. Dataset sebanyak 11.664 citra dilatih menggunakan pretrained weights dengan batch size 16 dan 100 epochs. Hasil eksperimen menunjukkan bahwa augmentasi gabungan memberikan kinerja terbaik dengan [email protected] sebesar 0,931, precision 0,868, dan recall 0,890. Implementasi pada Raspberry Pi 5 menggunakan citra dan video uji secara offline menunjukkan sistem mampu mendeteksi dan membaca nomor lambung melalui integrasi EasyOCR serta pengiriman data ke Google Sheet dengan kecepatan rata-rata 3,1 frames per second (FPS). Hasil ini menunjukkan bahwa strategi preprocessing dan data augmentation berperan penting dalam meningkatkan akurasi dan ketangguhan YOLOv11, serta mendukung penerapan sistem berbasis computer vision pada perangkat edge computing sebagai prototipe awal menuju implementasi real-time di lingkungan tambang terbuka.

References

[1] D. Shan, F. Qu, Z. Wang, Y. Ji, and J. Xu, “A Review of the Application of Computer Vision Techniques in Sustainable Engineering of Open Pit Mines,” Sustain., vol. 17, no. 7, pp. 1–16, 2025, doi: 10.3390/su17073051.

[2] K. Hasözdemir, M. Meral, and M. M. Kahraman, “Revolutionizing Open-Pit Mining Fleet Management: Integrating Computer Vision and Multi-Objective Optimization for Real-Time Truck Dispatching,” Appl. Sci., vol. 15, no. 9, 2025, doi: 10.3390/app15094603.

[3] M. Kotthapalli, D. Ravipati, and R. Bhatia, “YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges,” pp. 1–13, 2025, [Online]. Available: http://arxiv.org/abs/2508.02067

[4] J. Guo and M. Zhang, “An Improved YOLOv11 Recognition Algorithm for Heavy-Duty Trucks on Highways,” pp. 1–18, 2025.

[5] L. He, Y. Zhou, L. Liu, and J. Ma, “Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites,” Buildings, vol. 14, no. 12, 2024, doi: 10.3390/buildings14123777.

[6] A. Oktarino, A. Subahi, N. A. Alghanmi, A. B. F. Mansur, A. Tenriawaru, and A. H. Basori, “Deep Learning-Based Generalized Efficient Layer Aggregation Network for the Detection of Coal Trucks,” TEM J., vol. 14, no. 1, pp. 416–428, 2025, doi: 10.18421/TEM141-37.

[7] X. Hao, L. Liu, R. Yang, L. Yin, L. Zhang, and X. Li, “A Review of Data Augmentation Methods of Remote Sensing Image Target Recognition,” Remote Sens., vol. 15, no. 3, 2023, doi: 10.3390/rs15030827

[8] H. Jianfeng, G. Cui, J. Du, C. Wang, and L. Zhang, “Enhanced YOLOv11 for Image-Based Anomaly Detection in Freight Train Gate Chains,” Int. J. Intell. Inf. Technol., vol. 21, no. 1, 2024, doi: https://doi.org/10.4018/IJIIT.386138.

[9] Z. Yang, R. O. Sinnott, J. Bailey, and Q. Ke, A survey of automated data augmentation algorithms for deep learning-based image classification tasks, vol. 65, no. 7. Springer London, 2023. doi: 10.1007/s10115-023-01853-2.

[10] E. P. Silmina and R. A. Y. Arjun, “Pemanfaatan Model YOLOv8 Untuk Mendeteksi Plat Nomor Kendaraan Mobil Pada Gerbang Masuk Universitas XYZ,” J. Sains dan Inform., vol. 11, no. 1, pp. 50–59, 2025, doi: 10.34128/jsi.v11i1.916.

[11] P. Kaur, “Data Augmentation for Object Detection : A Review,” pp. 537–543, 2021.

[12] L. He and Y. Zhou, “Real-Time Vision-Based Monitoring of Mining Vehicles for Intelligent Industrial Systems,” SSRN Electron. J., 2025, doi: 10.2139/ssrn.5355956.

[13] V. Balaska, I. T. Papapetros, K. M. Oikonomou, L. Bampis, and A. Gasteratos, “UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data,” vol. 14, no. 8, pp. 1–12, 2021.

[14] N. A. Kurniawan and C. A. Sari, “Automatic License Plate Detection System with YOLOv11 Algorithm,” vol. 9, no. 6, pp. 3097–3109, 2025.

[15] M. Yolov and D. Paddleocr, “Sistem Deteksi Dan Pengenalan Plat Nomor Kendaraan,” vol. 3, no. 2, pp. 1–6, 2025, doi: 10.26714/jkti.v3i2.18678.