Robustness Analysis of YOLOv7 for Motorcycle Traffic Violation Detection Across Multi-Density CCTV Scenarios
Article Sidebar
Main Article Content
Abstract
Traffic violations committed by motorcycle riders remain a significant challenge in Indonesia’s transportation sector and contribute to an increased risk of traffic accidents. Common violations include riding without helmets and carrying more than one passenger. This study proposes a motorcycle traffic violation detection approach using the YOLOv7 object detection model applied to CCTV monitoring data. The dataset used in this study was obtained from CCTV recordings at Jalan Gapura DPRD, Bandar Lampung, and consists of images representing three traffic density scenarios: low, medium, and high. The research methodology includes frame extraction, image preprocessing, object labeling, model training, testing, and performance evaluation using standard object detection metrics, namely Precision, Recall, and mean Average Precision (mAP). Experimental results show that the YOLOv7 model achieves consistently high detection performance across different traffic density conditions. The best performance was obtained using a learning rate of 0.01 with 100 training epochs, achieving 99.66% mAP in low traffic conditions, 98.75% in medium traffic conditions, and 97.08% in high traffic conditions. These results indicate that the proposed approach has strong potential for implementation in CCTV-based traffic monitoring systems and may support automated traffic violation detection as part of Electronic Traffic Law Enforcement (ETLE) initiatives.
Article Details
References
[1] R. Nurfauziah and H. Krisnani. Perilaku pelanggaran lalu lintas. Jurnal Kolaborasi Resolusi Konflik, 3(1):75–84, 2021 (in Indonesia).
[2] A. W. Suryanto and A. R. Kardian. Deteksi pelanggaran lalu lintas berbasis cctv. Jurnal Teknik Komputer, 2023 (in Indonesia).
[3] A. Santoso and G. Ariyanto. Implementasi deep learning untuk deteksi objek. EMITOR: Jurnal Teknik Elektro, 18(1):15–21, 2018 (in Indonesia).
[4] K. Agarwal, A. Sanyo, S. Bakshi, and M. Vinay. Performance evaluation of yolo-based object detection in real-time applications. In Proceedings of the IEEE International Conference on Computational Intelligence, 2023.
[5] M. R. Assidiqi. Deteksi pelanggaran lalu lintas menggunakan metode yolov5. Master’s thesis, Universitas Lampung, 2023 (in Indonesia).
[6] I. Fazri. Deteksi dan pengenalan jenis pelanggaran lalu lintas menggunakan metode yolo. Master’s thesis, Universitas Gadjah Mada, 2022 (in Indonesia).
[7] A. A. Halliwal. Sistem pendeteksi dan penghitung pelanggaran lalu lintas berbasis cctv. Master’s thesis, Universitas Lampung, 2023 (in Indonesia).
[8] M. Ilyas. Deteksi pelanggaran berkendara menggunakan metode yolo (you only look once). Master’s thesis, Universitas Komputer Indonesia, 2020 (in Indonesia).
[9] E. Maulana, C. Setianingsih, et al. Sistem deteksi pelanggaran lalu lintas berbasis deep learning. Jurnal Teknik Informatika, 2023 (in Indonesia).
[10] R. Sholehurrohman and B. Setiyono. Pengembangan yolov3 dengan mobilenetv2 untuk deteksi dan klasifikasi kendaraan bergerak. Jurnal Ilmiah, 2021 (in Indonesia).
[11] A. W. Sudjana and H. Supeno. Implementasi deep learning pada rambu lalu lintas di indonesia, 2021 (in Indonesia).
[12] J. Zophie and H. Triharminto. Implementasi artificial intelligence pada pengawasan lalu lintas. Jurnal Penerbangan dan Antariksa, 1(1):98–109, 2023 (in Indonesia).
[13] R. Sholehurrohman, K. Muludi, and J. Triloka. Optimizing transportation surveillance with yolov7: Detection and classification of vehicle license plate colors. Journal of Information Technology and Knowledge, 10(4):812–819, 2025.
[14] S. Chung, K. Shek, J. Butterfield, and A. Murphy. Current trends in object detection for autonomous systems. In Proceedings of IMC37 Conference, 2021.
[15] R. Sholehurrohman, A. Junaidi, T. N. Dewi, R. Andrian, I. Sabda, and M. R. Habibi. Yolov5s for traffic prohibition sign detection in bandar lampung. International Journal of Electronic Communication Systems, 6(1):29–40, 2026.
[16] R. Sholehurrohman, Muhaqiqin, I. S. Ilman, and R. Habibi. Vehicle license plate color detection using yolov5, yolov7, yolov8, and yolov9. Jurnal Pepadun, 7(1):67–79, 2026.
[17] R. Sholehurrohman and H. M. Reza. Implementasi restorasi citra derau salt & pepper, gaussian dan speckle secara spasial dengan matlab. Jurnal INSTEK, 8(2):369–379, 2023 (in Indonesia).
[18] G. K. N. G., A. Kishore, and A. Krishna. Real-time traffic sign recognition using convolutional neural networks. Multimedia Tools and Applications, 84:43119–43154, 2025.
[19] A. Ali, A. Nadeem, N. Zafar, and M. Shiraz. Weather-aware traffic congestion prediction using deep learning. Frontiers in Communication Networks, 6:1666487, 2025.
[20] O. Rainio, J. Teuho, and R. Klén. Evaluation metrics for machine learning. Scientific Reports, 14, 2024.
[21] V. Hendriko and D. Hermanto. Performance comparison of yolov10, yolov11, and yolov12 on human detection datasets. Brilliance: Research of Artificial Intelligence, 5(1), 2025.
[22] R. Padilla, S. L. Netto, and E. A. B. da Silva. Performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), 2020.
[23] R. Padilla, W. L. Passos, T. L. B. Dias, S. L. Netto, and E. A. B. da Silva. A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics, 10(3):279, 2021.