Sleep Sense

Abstract

There is a large number of cases of road accidents across the world out of which a significant number of accidents are caused due to driver fatigue and drowsy behavior .A system which is reliable in detection of drowsy behavior and signs of fatigue can help in preventing such road accidents by monitoring driver behavior and generating alerts to them when signs of fatigue detected. This paper presents a machine learning approach that uses real-time image and processing it by taking insights from its processing like closing eyes ,facial expressions, calculating the closing and open eye-aspect ratios using different machine learning algorithms and generating alerts if it detects driver drowsy behavior . Experimental research shows that our system is effective and reliable in detection of drowsy behavior of drivers and it generates timely alerts to drivers if it is found drowsy and makes the driver safe.

Introduction

Drowsy driving is a major cause of road accidents, comparable in danger to drunk driving, due to reduced focus and slower reactions. Traditional methods to stay awake, like coffee or fresh air, often fail. To combat this, modern Drowsiness Detection Systems such as "Sleep Sense" use AI-powered cameras to monitor drivers’ facial features—especially eyes and head position—in real time. These systems analyze eye closure, blinking patterns, and facial expressions using digital image processing and machine learning algorithms like OpenCV and convolutional neural networks (Inception V3).

When signs of fatigue are detected, the system alerts the driver through alarms, vibrations, or voice warnings to prevent accidents. This technology is increasingly integrated into vehicles, trucks, buses, and workplaces requiring alertness.

The project detailed involves developing a simulation of such a system that captures images, processes them to detect drowsiness via eye aspect ratio (EAR) calculations, and promptly notifies drivers. It uses Python programming, Jupyter Lab, and libraries like TensorFlow, Keras, and OpenCV. The system must work effectively in various lighting conditions and provide accurate, real-time alerts to ensure safety.

Conclusion

Drowsiness detection is easily helpful to analyse the person’s eye while he/she is driving. It can be done when we can train the model that can identify the driver’s eye in the current situation. The model’s main motive is to see eye aspect ratio (EAR) for detecting whether the person’s eye is closed or open during driving. If we come to know that the EAR value lies below a certain threshold for a period,the detection counter will increase.Once this counter tries to exceeds the predefined limit then the alert is triggered to warm the driver. The goal of this project is to minimum the number of road accidents caused due to drowsy person,this may make road safe while driving.

References

[1] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. 32, no. 9, pp. 1627–1645, Sep. 2010. [2] E. Zhou, H. Fan, Z. Cao, Y. Jiang, and Q. Yin, “Extensive facial landmark localization with coarse-to-fine convolutional network cascade,” in *Proc. IEEE Int. Conf. Comput. Vis. Workshops*, Dec. 2013, pp. 386–391. [3] R. Grace et al., “A drowsy driver detection system for heavy vehicles,” in *Proc. 17th AIAA/IEEE/SAE Digit. Avion. Syst. Conf. (DASC)*, Oct. 1998, vol. 2, pp. I36-1–I36-8. [4] Y. Sun, X. Wang, and X. Tang, “Deep convolutional network cascade for facial point detection,” in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit.*, Jun. 2013, pp. 3476–3483. [5] D. F. R. Ferreira, “A system for driver drowsiness detection,” *Int. J. Comput. Vis. Intell. Syst.*, vol. 6, no. 4, pp. 203–217, 2018. [6] M. A. D. Siddik and M. S. Rahman, “Drowsiness and lethargy detection using machine learning techniques,” *Int. J. Artif. Intell. Res.*, vol. 8, no. 1, pp. 45–62, 2020. [7] S. Vitabile, “Bright pupil detection in an embedded, real-time drowsiness detection system,” *Sens. Actuators B Chem.*, vol. 254, pp. 210–218, 2017. [8] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit.*, 2001, vol. 1, pp. 511–518. [9] OpenCV Documentation, “Face and eye detection using Haar cascades,” *Open Source Comput. Vis. Libr.*, 2023. [Online]. Available: https://docs.opencv.org [10] D. E. King, “Dlib-ml: A machine learning toolkit,” *J. Mach. Learn. Res.*, vol. 10, pp. 1755–1758, 2009. [11] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Improving neural networks by preventing co-adaptation of feature detectors,” *arXiv preprint arXiv:1207.0580*, 2012. [12] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit.*, 2016, pp. 770–778. [13] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in *Adv. Neural Inf. Process. Syst.*, 2012, pp. 1097–1105. [14] A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” *arXiv preprint arXiv:1704.04861*, 2017. [15] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” *arXiv preprint arXiv:1409.1556*, 2014. [16] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit.*, 2016, pp. 779–788. [17] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit.*, 2017, pp. 1251–1258. [18] M. Li and Y. Li, “A real-time driver drowsiness detection system using deep learning,” *IEEE Trans. Intell. Transp. Syst.*, vol. 23, no. 7, pp. 1345–1356, 2022. [19] T. Baltrušaitis, P. Robinson, and L. P. Morency, “OpenFace: An open source facial behavior analysis toolkit,” in *Proc. IEEE Winter Conf. Appl. Comput. Vis.*, 2016, pp. 1–10. [20] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in *Int. Conf. Mach. Learn.*, 2015, pp. 448–456.

Copyright

Copyright © 2025 Shiv Bhardwaj, Swati Pandit, Yash Kaundinya, Tusha Singh , Gauri , Shruti Varshney. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.