Intelligent Driver System Based on Convolutional Neural Network for Detecting Unsafe Driving Conditions
Intelligent Driver System Berbasis Convolutional Neural Network untuk Deteksi Kondisi Tidak Aman Berkendara
DOI:
https://doi.org/10.21070/ups.8589Keywords:
Convolution Neural Network, YOLOv8, Unsafe Condition, Detection, Digital ImageAbstract
This research addresses the high rate of traffic accidents caused by unsafe driving conditions, such as drowsiness, phone use, and smoking. The objective was to design and develop an intelligent system capable of detecting these unsafe conditions in real-time. The system was developed using a Convolutional Neural Network (CNN) and the You Only Look Once (YOLO) algorithm, specifically comparing versions 5, 8, and 11. A public dataset from Roboflow, containing 7,711 images across seven categories of driver behavior, was used for training the models. The models were trained for up to 200 epochs on the Kaggle platform. Results showed that YOLOv11 achieved the highest performance, with mAP50 score of 0.8166. Implemented prototype successfully detected unsafe behaviors in real-time and triggered alarm system. The research concludes that the YOLOv11-based system is effective, though future improvements are needed to enhance detection accuracy for diverse driver appearances, such as those wearing a hijab.
Downloads
References
Y. X. Chew, S. F. A. Razak, S. Yogarayan, and S. N. M. S. Ismail, “Dual-Modal Drowsiness Detection to Enhance Driver Safety,” Computers, Materials and Continua, vol. 81, no. 3, pp. 4397–4417, 2024, doi: 10.32604/cmc.2024.056367.
World Health Organization, “Global action plan on physical activity 2018–2030: more active people for a healthier world,” 2018. Accessed: Apr. 24, 2025. [Online]. Available: https://www.who.int/publications/i/item/9789241514187
B. Kanigoro and B. Asdyo, “Facial Landmark and YOLOv5 Drowsiness Detection System,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 548–554. doi: 10.1016/j.procs.2024.10.281.
T. Abuzairi, Nurdina Widanti, Arie Kusumaningrum, and Yeni Rustina, “Implementasi Convolutional Neural Network Untuk Deteksi Nyeri Bayi Melalui Citra Wajah Dengan YOLO,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 4, pp. 624–630, Aug. 2021, doi: 10.29207/resti.v5i4.3184.
M. C. Bonfante, I. H. Ruiz, J. C. Montes, E. A. Rodríguez, and A. Cama-Pinto, “Detection of elements of personal safety for the prevention of accidents at work with convolutional neural networks,” International Journal of Electrical and Computer Engineering, vol. 14, no. 5, pp. 5824–5833, Oct. 2024, doi: 10.11591/ijece.v14i5.pp5824-5833.
A. C. F. Lanyak, A. Prasetiadi, H. B. Widodo, M. H. Ghani, and A. Athallah, “Dental caries detection using faster region-based convolutional neural network with residual network,” IAES International Journal of Artificial Intelligence, vol. 13, no. 2, pp. 2025–2033, Jun. 2024, doi: 10.11591/ijai.v13.i2.pp2027-2035.
S. Giridhar et al., “An Intelligent System for Preventing Accidents Due to Driver Distractions,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 2196–2204. doi: 10.1016/j.procs.2024.04.208.
M. F. Ridho, F. Panca, W. Yandi, and A. A. Rachmani, “Electron : Jurnal Ilmiah Teknik Elektro Drowsiness Detection in the Advanced Driver-Assistance System using YOLO V5 Detection Model,” vol. 5, 2024.
Saujanya Shankar, “Drowsiness Computer Vision Project.” Accessed: Apr. 24, 2025. [Online]. Available: https://universe.roboflow.com/saujanya-shankar/drowsiness-sgvf2/
Ultralytics, “Ultralytics YOLO11.” Accessed: Apr. 24, 2025. [Online]. Available: https://docs.ultralytics.com/Models/yolo11/
M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (VOC) challenge,” Int J Comput Vis, vol. 88, no. 2, pp. 303–338, Jun. 2010, doi: 10.1007/s11263-009-0275-4.
Downloads
Additional Files
Posted
License
Copyright (c) 2025 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
