Using CNN for Detection of Driver Drowsiness
Vivek Kakarla
Student, Independence High School, Ashburn, Virginia
Download PDF
http://doi.org/10.37648/ijps.v16i01.005
Abstract
This study presents a Convolutional Neural Network (CNN) based Driver Drowsiness Detection system. The device determines a driver's level of attention by analysing face features captured in real-time by in-car cameras. The CNN model is appropriate for use in the real world because it has been trained on various datasets and exhibits good accuracy in recognising indicators of tiredness. This device helps to keep drivers safe on the road by sending out timely alerts to stop tired drivers from causing accidents. Building intelligent technologies to reduce driver-related dangers is essential because road safety is still a significant concern. One of the leading causes of traffic accidents is driver fatigue, which highlights the necessity for reliable and quick detection systems. This study presents a novel method for driver drowsiness detection with convolutional neural networks (CNN). The suggested method uses CNN architecture to analyze facial features taken from in-car cameras' real-time video streams. The driver's degree of awareness is deduced by analysing their facial expressions and landmarks. The CNN model is trained on various datasets, including awake and sleepy facial expressions, guaranteeing its flexibility to various driving scenarios and personal traits. Extensive tests use different datasets and scenarios to assess the system's efficiency. The outcomes show how well the CNN can detect indicators of driver fatigue, with high recall and precision rates. Moreover, due to its real-time processing capabilities, the model can be deployed in realistic on-road settings. By promptly alerting drivers when indicators of Drowsiness are identified, the suggested Driver sleepiness Detection system offers a possible approach to improve road safety. By incorporating artificial intelligence into car safety systems; this research helps to lower the likelihood of accidents brought on by tired drivers.
Keywords:
Convolutional Neural Network (CNN); Driver Drowsiness Detection system; road safety
References
- J. May and C. Baldwin, “Driver fatigue: The importance of identifying causal factors of fatigue when considering detection and countermeasure technologies,” Transp. Res. F, Traffic Psychol. Behav., vol. 12, no. 3, pp. 218–224, 2009.
- S. Lal and A. Craig, “A critical review of the psychophysiology of driver fatigue,” Biol. Psychol., vol. 55, no. 3, pp. 173–194, 2001.
- E. Hitchcock and G. Matthews, “Multidimensional assessment of fatigue: A review and recommendations,” in Proc. Int. Conf. Fatigue Manage. Transp. Oper., Seattle, WA, USA, Sep. 2005.
- Williamson, A. Feyer, and R. Friswell, “The impact of work practices on fatigue in long distance truck drivers,” Accident Anal. Prevent., vol. 28, no. 6, pp. 709–719, 1996.
- W. Dement and M. Carskadon, “Current perspectives on daytime sleepiness: The issues,” Sleep, vol. 5, no. S2, pp. S56–S66, 1982
- L. Hartley, T. Horberry, N. Mabbott, and G. Krueger, “Review of fatigue detection and prediction technologies,” Nat. Road Transp. Commiss., Melbourne, Vic., Australia, Tech. Rep., 2000.
- Sahayadhas, K. Sundaraj, and M. Murugappan, “Detecting driver drowsiness based on sensors: A review,” Sensors, vol. 12, pp. 16 937–16 953, 2012.
- S. Kee, S. Tamrin, and Y. Goh, “Driving fatigue and performance among occupational drivers in simulated prolonged driving,” Global J. HealthSci., vol. 2, no. 1, pp. 167–177, 2010.
- M.-H. Sigari, M.-R.Pourshahabi, M. Soryani, and M. Fathy, “A review on driver face monitoring systems for fatigue and distraction detection”, Int. J. Adv. Sci. Technol., vol. 64, pp. 73–100, 2014.
