Citation :

Saravanakumar, V. Seethalakshmi, G. Paulraj, R. Sanjay Kumar, A. Nixsan, K. Jenseer, 2026. "Vision-Based Driver Fatigue Detection Using Convolutional Neural Networks and Behavioral Metrics" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 2: 1-10.

Abstract :

Driver drowsiness is a major cause of road accidents, especially during long-distance or late-night driving. This paper presents a real-time Driver Drowsiness Detection and Alert System that uses a webcam to monitor the driver’s facial behavior. YOLO (You Only Look Once) is employed for accurate face detection, and Convolutional Neural Networks (CNNs) analyze facial features. Two key metrics, Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR), are calculated using Dlib and OpenCV to detect prolonged eye closure and yawning. When thresholds are crossed, an alarm is triggered to alert the driver. The system also logs EAR and MAR values with timestamps in a CSV file and generates visual plots for analysis. A user interface developed with Flask and Tkinter provides control and ease of use. Experimental results show more than 90% detection accuracy under normal conditions with an alert delay of ~1–2 seconds. This work demonstrates an effective blend of computer vision and deep learning to enhance driver safety and reduce fatigue-related accidents.

References :

[1] R. Reddy and S. Ramesh, “Real-time driver drowsiness detection using machine learning on embedded platform,” in Proc. IEEE Int. Conf. Computing and Communication Systems (I3CS), 2021, pp. 112-118.

[2] P. Singh and A. Banerjee, “Drowsiness detection using transfer learning with MobileNetV2,” in Proc. IEEE Int. Conf. Intelligent Computing and Control Systems (ICICCS), 2022, pp. 543-549.

[3] D. Chen and L. Zhang, “Real-time drowsiness detection based on facial expression recognition,” IEEE Access, vol. 8, pp. 34,780–34,790, 2020.

[4] H. Wu and X. Feng, “Eye state classification for drowsiness detection using deep neural networks,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 5, pp. 1196–1208, 2019.

[5] T. Soukup and J. Riha, “The use of eye aspect ratio and mouth aspect ratio in driver monitoring systems,” J. Transportation Technologies, vol. 10, no. 2, pp. 134–146, 2020.

[6] G. B. Huang, et al., “Dlib-ml: A machine learning toolkit,” J. Mach. Learn. Res., vol. 10, pp. 1755– 1758, 2009.[7] G. Bradski, “The OpenCV library,” Dr. Dobb’s J.

[7] G. Bradski, “The OpenCV library,” Dr. Dobb’s J.<[7] G. Bradski, “The OpenCV library,” Dr. Dobb’s J.

[8] Software Tools, vol. 25, no. 11, pp. 120–125, 2000.

[9] A. Rosebrock, “Eye blink detection with OpenCV, Python, and dlib,” PyImageSearch Blog, 2017. [Online]. Available: https://www.pyimagesearch.com

[10] Python Software Foundation, “Python 3.8 documentation,” 2019. [Online]. Available: https://docs.python.org/3.8/

[11] D. King, “Dlib C++ library,” GitHub repository, 2019. [Online]. Available: https://github.com/davisking/dlib

[12] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi,

[13] “You only look once: Unified, real-time object

[14] detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788.

[15] S. Mallick, “Facial landmark detection,” LearnOpenCV Blog, 2018. [Online]. Available: https://www.learnopencv.com

[16] H. Abtahi, “Real-time eye detection and tracking using Face API,” Microsoft Research, 2016. [Online]. Available: https://www.microsoft.com

[17] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2001, pp. 511–518.

[18] J. Patel, “Drowsiness detection using OpenCV and Python,” Medium Tech Blog, 2020. [Online]. Available: https://medium.com

Keywords :

CNN, YOLO, driver drowsiness detection, Eye Aspect Ratio (EAR), Mouth Aspect Ratio (MAR), Computer vision, Real-time systems