Real-Time Drowsiness Detection System for Driver Safety Based on Computer Vision
Article Sidebar
Main Article Content
Abstract
This study proposes a lightweight real-time driver drowsiness detection system based on traditional computer vision and machine learning techniques for resource-constrained environments. The proposed framework integrates Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) for face detection, followed by facial landmark analysis and Eye Aspect Ratio (EAR) computation using Euclidean distance to estimate eye closure and detect drowsiness. The system was evaluated using real-world driving video datasets collected from multiple drivers under practical driving conditions, including variations in illumination, head pose, and driver behavior. Experimental results demonstrate that the proposed method achieves an average accuracy of 82% with a low False Negative Rate (FNR) of 0.099 while maintaining low computational complexity. The proposed approach provides a practical balance between detection performance and hardware efficiency, making it suitable for real-time deployment on CPU-based and low-cost embedded systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Journal of TCI is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence, unless otherwise stated. Please read our Policies page for more information...
References
N.Jianbunjongkit, W.Nattarangsi, P. Teerawanittrakul, and S. Sookdee, “Road traffic accidents, sleepiness, and Obstructive sleep apnea: A cross sectional study among public transport drivers in Chonburi province,” 2021.
G. S. Lozano-Reyes and C. A. Mugruza-Vassallo, “A vision-based drowsiness detection system for railway operators using lightweight convolutional neural networks,” Frontiers in FutureTransportation, vol. 6, 2025, doi: 10.3389/ffutr.2025.1677442.
A. Yadav et al., “Enhancing convolutional neural networks in electroencephalogram driver drowsiness detection using human inspired optimizers,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-93765-0.
S. E. Bekhouche, Y. Ruichek, and F. Dornaika, “Driver drowsiness detection in video sequences using hybrid selection of deep features,” Knowl. Based. Syst., vol. 252, p. 109436, 2022, doi: 10.1016/j.knosys.2022.109436.
R. Malik, M. Vijarania, and M. Malik, “A Comprehensive Review of Deep Learning and IoT in Driver Drowsiness Detection for Safer Roads,” in Proceedings of the 2024 3rd Edition of IEEE Delhi Section Flagship Conference, DELCON 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/DELCON64804.2024.10866889.[6] X. Lin, Z. Huang, W. Ma, and W. Tang, “EEG-based driver drowsiness detection based on simulated driving environment,” Neurocomputing, vol. 616, Feb. 2025, doi: 10.1016/j.neucom.2024.128961.
Z. Lan, J. Zhao, P. Liu, C. Zhang, N. Lyu, and L. Guo, “Driving fatigue detection based on fusion of EEG and vehicle motion information,” Biomed. Signal Process. Control, vol. 92, Jun. 2024, doi: 10.1016/j.bspc.2024.106031.
S. Bakheet and A. Al-Hamadi, “A framework for instantaneous driver drowsiness detection based on improved HOG features and naïve bayesian classification,” Brain Sci., vol. 11, no. 2, pp. 1–15, Feb. 2021, doi: 10.3390/brainsci11020240.
S. A. El-Nabi, K. F. Ramadan, E. S. M. El-Rabaie, A. Emam, and W. El-Shafai, “A real-time design and implementation of intelligent drowsiness and fatigue recognition system for enhancing driver safety,” Eng. Appl. Artif. Intell., vol. 162, Dec. 2025, doi: 10.1016/j.engappai.2025.112665.
B. Asdyo, B. Kanigoro, and Rojali, “Drowsy Detection System by Facial Landmark and Light Gradient Boosting Machine Method,” in Procedia Computer Science, Elsevier B.V., 2023, pp. 500–507. doi: 10.1016/j.procs.2023.10.551.
M. Venkateswarlu and V. R. R. Chirra, “CNN-ViT: A multi-feature learning based approach for driver drowsiness detection,” Array, vol. 27, Sep. 2025, doi: 10.1016/j.array.2025.100425.
Y. Albadawi, M. Takruri, and M. Awad, “A Review of Recent Developments in Driver Drowsiness Detection Systems,” Mar. 01, 2022, MDPI. doi: 10.3390/s22052069.
M. M. Desai, K. Kathad, and N. Modi, “Real-Time Driver Drowsiness Detection Using Hybrid CNN-LSTM Model with Facial Feature and Behavioral Analysis,” in Proceedings of the 4thInternational Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 197–202. doi: 10.1109/ICUIS64676.2024.10866692.
Taufiya Fathima and Dr. H Girisha, “Real-Time Driver Drowsiness Detection Using Eye Aspect Ratio and Facial Landmark Analysis,” International Research Journal on Advanced Engineering Hub (IRJAEH), vol. 3, no. 09, pp. 3432–3438, Sep. 2025, doi: 10.47392/irjaeh.2025.0503.
M. Z. Yazdi and M. Soryani, “Driver Drowsiness Detection by Identification of Yawning and Eye Closure,” Int. J. Automot. Eng., vol. 9, no. 3, pp. 3033–3044, 2019, doi: 10.22068/ijae.9.3.3033.
J. Lyu, Z. Yuan, and D. Chen, “Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection,” Jan. 2018, [Online]. Available: http://arxiv.org/abs/1801.02325
M. F. Yusri, P. Mangat, and O. Wasenmüller, “Detection of Driver Drowsiness by Calculating the Speed of Eye Blinking.”
M. W. Gomaa, R. O. Mahmoud, and A. M. Sarhan, “A CNN-LSTM-based Deep Learning Approach for Driver Drowsiness Prediction,” 2022.
S. Cao, P. Feng, W. Kang, Z. Chen, and B. Wang, “Optimized driver fatigue detection method using multimodal neural networks,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-86709-1.
