Development and Optimization of YOLOv12 for Autonomous Vehicle Navigation Systems
DOI:
https://doi.org/10.57152/malcom.v6i2.2634Keywords:
Autonomous Vehicles, Computer Vision, Intelligent Transportation Systems, Object Detection, YOLOv12Abstract
This study develops and enhances a YOLOv12-based object detection model for autonomous vehicle perception on Indonesian highways, addressing limitations of earlier research that lacked realistic traffic scenarios and field validation. The Roboflow dataset contains 29 object classes, including vehicles, pedestrians, and traffic signs, with existing annotations. Preprocessing included data quality assessment, image resizing, dataset split validation, annotation format conversion, and data augmentation to improve training performance. Eight training configurations were evaluated by varying learning rate, batch size, and optimizer. Initial comparisons showed YOLOv12 significantly outperformed SSD, achieving mAP50 of 0.978 and mAP50–95 of 0.831, compared to SSD’s 0.816 and 0.639. SGD consistently provided more stable and accurate performance than Adam. The best model used SGD with a learning rate of 0.001 and batch size of 16, achieving precision of 0.952, recall of 0.955, mAP50 of 0.974, and mAP50–95 of 0.834. Field testing confirmed strong detection of pedestrians and traffic signs, although challenges remained with small and overlapping objects. Future work should improve small-object detection, expand dataset diversity, and explore advanced architectures or hybrid optimization strategies. These findings support YOLOv12 as a reliable foundation for safer, more efficient self-driving perception systems tailored to Indonesia’s complex road environments in real conditions.
Downloads
References
M. A. R. Pohan, “Studi Literatur Sistematis Potensi Kendaraan Otonom dalam Transformasi Transportasi oleh Pemerintah Daerah di Indonesia,” Jurnal Teknologi dan Komunikasi Pemerintahan, Oct. 2025, doi: 10.33701/jtkp.v7i1.4958.
G. Velasco-Hernandez, D. J. Yeong, J. Barry, and J. Walsh, “Autonomous Driving Architectures, Perception and Data Fusion: A Review,” in Proceedings - 2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing, ICCP 2020, Institute of Electrical and Electronics Engineers Inc., Sep. 2020, pp. 315–321. doi: 10.1109/ICCP51029.2020.9266268.
F. M. Barbosa and F. S. Osório, “Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics,” Mar. 2023, doi: 10.48550/arXiv.2303.04302.
S. Akhauri, L. Zheng, T. Goldstein, and M. Lin, “Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving,” Sep. 2021, doi: 10.48550/arXiv.2103.08116.
B. Prastiyo, “Inspeksi Keselamatan Jalan di Ruas Jalan Nasional Kota Jambi,” Himpunan Pengembangan Jalan Indonesia, vol. 10, no. 1, pp. 45–52, 2024, doi: 10.26593/jhpji.v10i1.7647.45-52.
N. Y. A. Ula, B. R. Martha, and S. Hadi, “Inspeksi Keselamatan Jalan pada Jalan Ahmad Yani di Kota Magelang,” Jurnal Teknik Gradien, vol. 17, no. 01, pp. 13–24, 2025, doi: 10.47329/teknik_gradien.v17i01.1392.
Y. Zhu and W. Q. Yan, “Traffic sign recognition based on deep learning,” Multimed. Tools Appl., vol. 81, no. 13, pp. 17779–17791, May 2022, doi: 10.1007/s11042-022-12163-0.
O. V. Putra and I. N. Gustri, “Sistem Deteksi Marka Jalan Berbasis Convolutional Neural Network,” Journal of Computer Engineering, Network, and Intelligent Multimedia, vol. 1, no. 1, pp. 1–13, Feb. 2023, doi: 10.59378/jcenim.v1i1.2.
A. Mulyanto, W. Jatmiko, P. Mursanto, P. Prasetyawan, and R. I. Borman, “A new indonesian traffic obstacle dataset and performance evaluation of yolov4 for adas,” Journal of ICT Research and Applications, vol. 14, no. 3, pp. 285–298, 2021, doi: 10.5614/ITBJ.ICT.RES.APPL.2021.14.3.6.
N. Yinkfu, S. Nwovu, J. Kayizzi, and A. Uwamahoro, “Comparative Analysis of YOLOv5, Faster R-CNN, SSD, and RetinaNet for Motorbike Detection in Kigali Autonomous Driving Context,” Oct. 2025, doi: 10.48550/arXiv.2510.04912.
R. Khanam and M. Hussain, “A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions,” arXiv preprint arXiv, Apr. 2025, doi: 10.48550/arXiv.2504.11995.
M. A. R. Alif and M. Hussain, “YOLOv12: A Breakdown of the Key Architectural Features,” arxiv preprint, Feb. 2025, doi: 10.48550/arXiv.2502.14740.
G. D. Deepak and S. K. Bhat, “Optimizing YOLOv4 Hyperparameters for Enhanced Vehicle Detection in Intelligent Transportation Systems,” International Journal of Intelligent Transportation Systems Research, Dec. 2025, doi: 10.1007/s13177-025-00519-3.
S. Y. Mohammed, “Architecture review: Two-stage and one-stage object detection,” Sep. 01, 2025, Elsevier B.V. doi: 10.1016/j.fraope.2025.100322.
M. Carranza-García, J. Torres-Mateo, P. Lara-Benítez, and J. García-Gutiérrez, “On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data,” Remote Sens. (Basel)., vol. 13, no. 1, pp. 1–23, Jan. 2021, doi: 10.3390/rs13010089.
Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-Centric Real-Time Object Detectors,” arXiv preprint arXiv, 2025, doi: 10.48550/arXiv.2502.12524.
T. Yu and H. Zhu, “Hyper-Parameter Optimization: A Review of Algorithms and Applications,” arXiv preprint arXiv, Mar. 2020, doi: 10.48550/arXiv.2003.05689.
B. Bischl et al., “Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges,” WIREs Data Mining and Knowledge Discovery, vol. 13, Nov. 2021, doi: 10.48550/arXiv.2107.05847.
O. G. Ajayi, P. O. Ibrahim, and O. S. Adegboyega, “Effect of Hyperparameter Tuning on the Performance of YOLOv8 for Multi Crop Classification on UAV Images,” Applied Sciences (Switzerland), vol. 14, no. 13, Jul. 2024, doi: 10.3390/app14135708.
R. Farid Abdillah and D. Ramadhani, “Nominal Detection of Rupiah Banknotes with Audio Output Using MobileNetV2 Transfer Learning Method,” Jurnal Ilmu Komputer dan Informasi, vol. 19, no. 1, pp. 99–106, Mar. 2026.
G. Y. Kim and M.-H. Oh, “Adam Optimization with Adaptive Batch Selection,” arXvic, Dec. 2025, doi: 10.48550/arXiv.2512.06795.
H. Guo, J. Jin, and B. Liu, “Stochastic Weight Averaging Revisited,” Applied Sciences (Switzerland), vol. 13, no. 5, Mar. 2023, doi: 10.3390/app13052935.
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 (Switzerland), vol. 10, no. 3, pp. 1–28, Feb. 2021, doi: 10.3390/electronics10030279.
P. Zhou, J. Feng, C. Ma, C. Xiong, S. Hoi, and W. E, “Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning,” arXiv preprint arXiv, Nov. 2021, doi: 10.48550/arXiv.2010.05627.
Y. Shi, Y. Jia, and X. Zhang, “FocusDet: an efficient object detector for small object,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-61136-w.
Y. Li, K. Wu, W. Kang, Y. Zhou, and F. Di, “Multi-object detection for crowded road scene based on ML-AFP of YOLOv5,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-43458-3.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Dian Ramadhani, Muhammad Muttakin, Hidayat Hatta Irsyad, Edi Susilo, Rahmat Rizal Andi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
