YOLO-Based Vehicle Detection and Classification for Multi-Lane Free Flow Systems
DOI:
https://doi.org/10.68129/jeis.v1i2.6Keywords:
You only look once version 9 (YOLOv9), Vehicle classification, Multi lane free flow (MLFF)Abstract
Multi-Lane Free Flow (MLFF) systems have emerged as a promising approach to reducing congestion at toll gates by enabling uninterrupted toll transactions without requiring vehicles to stop. To support this implementation, this study proposes a YOLOv9-based vehicle detection and classification system optimized using grid search and the SGD optimizer. The proposed system is designed for edge computing deployment and evaluated in a real multi-lane toll environment using an NVIDIA Jetson AGX Orin device. Experimental results show that the optimized model achieves a mean Average Precision at IoU threshold 0.50 (mAP@50) of 92.6%, an F1-score of 92.0%, and an inference time of 70.8 ms, corresponding to 14.1 FPS. These results indicate that the proposed system provides a balanced trade-off between detection accuracy and computational efficiency for edge-based MLFF applications. Unlike previous studies that primarily evaluated vehicle classification models using offline datasets, this study includes implementation and testing in a real multi-lane toll scenario. The findings demonstrate the potential of YOLO-based vehicle detection and classification to support practical MLFF deployment, although further evaluation under more diverse traffic, lighting, and environmental conditions is still required.
References
[1] A. A. Febriyansah and G. Kosala, "Classification of Vehicle Classes at Toll Gates Using YOLOv9 and Resnet50," in Proceedings of the 2025 International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS), Bandung, Indonesia, 2025, pp. 1-6, doi: 10.1109/ICADEIS65852.2025.10933473.
[2] A. M. S. Sufanir, D. R. Shaumi, and V. R. A. Siregar, “Pemeriksaan Standar Pelayanan Gerbang Tol Pasteur 1 Ditinjau Dari Kecepatan Transaksi,” Jurnal Rekayasa Sipil (JRS-Unand), vol. 18, no. 3, p. 194, Dec. 2022, doi: 10.25077/jrs.18.3.194-201.2022.
[3] N. Mujahidah, H. R. Azmi, A. N. Zaman, and F. Lestari, “Analysis of Automatic Toll Gate Payment Queue System,” in Proceedings of the Second Asia Pacific International Conference on Industrial Engineering and Operations Management, Surakarta, Indonesia, September 14-16, 2021.
[4] Harnanda, A. Y., Priyanto, S., & Irawan, M. Z. (2022). “Determining Factors Of Interest In The Use Of Technology Readness Based Multi Lane Free Flow (Mlff)”, International Journal of Economics, Business and Accounting Research (IJEBAR), vol. 6, no. 4, Dec. 2022. https://doi.org/10.29040/ijebar.v6i4.7565.
[5] Y. A. Saputra and Y. Latief, “Analytical hierarchy process on the implementation of multi lane free flow toll road transaction system in Indonesia,” Edelweiss Applied Science and Technology, vol. 9, no. 3, pp. 217–227, 2025, doi: 10.55214/25768484.v9i3.5181.
[6] O. F. Nurul Yudho Fauzan, R. S. Perdana, and T. Adiono, “Development of Vehicle Type Detection System on Multi Lane Free Flow Toll E-Collection,” in Proceedings of 2022 International Conference on Data and Software Engineering, ICoDSE 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 42–46.
[7] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2020.
[8] A. H. Rangkuti, A. Calvin, W. C. Kosasih, R. R. Febriano, D. R. Hermanus, and A. I. Arrahmah, “Enhanced Vehicle Classification via Axle-Based Deep Learning Models,” in Proceedings of 2024 7th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia, 2024, pp. 137-142, doi: 10.1109/ISRITI64779.2024.10963458.
[9] J. Vinod, D. T M and R. Rajesh, "Interactive YOLO-based Object Detection using a Polygonal Region of Interest for Airborne Surveillance Applications," in Proceedings of 2024 IEEE Space, Aerospace and Defence Conference (SPACE), Bangalore, India, 2024, pp. 901-905, doi: 10.1109/SPACE63117.2024.10668012..
[10] A. D. Sulistya Kurniawan, Y. Imanda Purnama, A. B. Wicaksono and H. Mahmudah, "Comparative Analysis and Optimization of Deep Learning Models for Object Detection Using Grid Search Hyperparameter Tuning," in Proceedings of 2024 International Electronics Symposium (IES), Denpasar, Indonesia, 2024, pp. 587-592, doi: 10.1109/IES63037.2024.10665797.
[11] S. Sveleba, I. Katerynchuk, I. Kunyo, V. Brygilevych, V. Franiv and O. Krychevets, "Convolutional Neural Network with Optimized Learning Parameters," in Proceedings of 2024 14th International Conference on Advanced Computer Information Technologies (ACIT), Ceske Budejovice, Czech Republic, 2024, pp. 170-173, doi: 10.1109/ACIT62333.2024.10712630.
[12] S. Makamo, “Optimization Algorithms in Deep Learning Models for Improving the Forecasting Accuracy in Sequential Datasets with Application in the South African Stock Market Index: A Review,” International Journal of Artificial Intelligence and Machine Learning, vol. 4, no. 2, pp. 1–8, Jul. 2024, doi: 10.51483/ijaiml.4.2.2024.1-8.
[13] D. Chattopadhyay, S. Rasheed, L. Yan, A. A. Lopez, J. Farmer and D. E. Brown, "Machine Learning for Real-Time Vehicle Detection in All-Electronic Tolling System," in Proceedings of 2020 Systems and Information Engineering Design Symposium (SIEDS), Charlottesville, VA, USA, 2020, pp. 1-6, doi: 10.1109/SIEDS49339.2020.9106682.
[14] P. Utomo, L. Fatmawati, and D. Nor Amadi, “Assessment of Toll User Satisfaction in East Java Using Simple Additive Weighting (SAW),” Journal of Information Systems and Informatics, vol. 4, no. 2, 2022. doi: https://doi.org/10.51519/journalisi.v4i2.259.
[15] H. Mahmudah, A. S. Aisjah, S. Arifin and C. Arif Prastyantyo, "iYOLOV7-TPE-SS: Leveraging Improved YOLO Model With Multilevel Hyperparameter Optimization for Road Damage Detection on Edge Devices," IEEE Access, vol. 13, pp. 79247-79263, 2025, doi: 10.1109/ACCESS.2025.3562612.
[16] C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information,” In Proceedings of European conference on computer vision, Cham: Springer Nature Switzerland, Feb. 2024, pp. 1-21. doi: https://doi.org/10.48550/arXiv.2402.13616.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nihayatus Sa'adah, Faridatun Nadziroh, Rahardhita Widyatra Sudibyo, Haniah Mahmudah, Fitri Fitriah, Hari Wahjuningrat Suparno, Muhammad Hendra Syahputra (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
