Android-Based Real-Time Driver Drowsiness Detection and Alert System
Keywords:
Driver Drowsiness Detection, Real-time detection, android device, mobile devices, drowsy drivingAbstract
Traffic accidents cause millions of people to lose their lives every year. Statistics assert that most fatal accidents are due to driver drowsiness. So the rate of fatality due to accidents caused by drivers falling asleep is high. There have been various researches and developments on driver drowsiness and fatigue detection systems by industries and academic researchers over the years. However, the solutions produced are usually found on luxurious vehicles and are computationally expensive to be connected to embedded devices or mobile devices with operating systems such as Android. This paper proposes to a cost-effective and efficient driver drowsiness detection system that can be installed on mobile devices or smart embedded devices using state-of-the-art technological advancements in the area of machine learning and artificial intelligence to prevent or reduce accidents that occur due to drowsy driving.
References
Jang SW, Ahn B. Implementation of detection system for drowsy driving prevention using image recognition and IoT. Sustainability. 2020 Apr 10; 12 (7): 3037.
Schroeder, P., et al. National Survey on Distracted Driving Attitudes and Behaviours. Washington DC: United States National Highway Traffic Safety Administration, 2012.
Sleepiness and driving: the experience of uk car drivers. MayCock, G. 1996, Journal of Sleep Research, pp. 229–231.
World Health Organization. Road Traffic Injuries. World Health Organization Web site. [Online] February 7, 2020. [Cited: April 5, 2021.] http://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries.
National Highway Traffic Safety Administration. Fatal Crashes and Percent Alcohol-Impaired Driving, by Time of Day and Crash Type Report. National Highway Traffic Safety Administration
website. [Online] 2017. [Cited: August 5, 2021.] https://wwwfars.nhtsa.dot.gov/Crashes/ CrashesAlcohol.aspx.
Google Developers. Machine learning for mobile developers. Google Developers Web site. [Online] 2021. [Cited: June 19, 2021.] https://developers.google.com/ml-kit.
A contextual and temporal algorithm for driver drowsiness detection. A, D, McDonald, et al. s.l.: Accident Analysis & Prevention, 2018, Vol. 113, pp. 25–37.
PERCLOS: A Valid Psychophysiological Measure of Alertness As Assessed by Psychomotor Vigilance. U. S. F. M. C. S. A. T. Division. October 1998.
Toward Drowsiness Detection Using Non-hair-Bearing EEG-Based Brain-Computer Interfaces. C, S, Wei, et al. s.l.: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018.
Smart Real-Time Video Surveillance Platform for Drowsiness Detection Based on Eyelid Closure. M, Tayab Khan, et al. s.l.: Wireless Communications and Mobile Computing, 2019, Vol. 2019, pp. 1–9.
A sensor fusion approach for drowsiness detection in wearable ultra-low-power systems. V, J, Kartsch, et al. s.l.: Information Fusion, September 2018, Vol. 43, pp. 66–76.
Detecting Driver Drowsiness in Real Time Through Deep Learning Based Object Detection. M, F, Shakeel, et al. 2019.
Real Time Driver Fatigue Detection System Based on Multi-Task ConNN. B, K, Savaş and Y, Becerikli. s.l.: IEEE Acces, 2020, Vol. 8, pp. 12491–12498.
Real-Time Driver Drowsiness Detection System Based on Visual. Kunika, Chhaganbhai, Patel, Shafiullah, Atiullah, Khan and Vijaykumar, Nandkumar, Patil. 3, s.l.: IJESC, Vol. 8.
Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application. Rateb, Jabbar, et al. s.l.: IEEE International Conference on Informatics, IoT, and Enabling Technologies, 2020, pp. 237–242.
Mazda. DAA(DRIVER ATTENTION ALERT). Mazda Web site. [Online] 2021. [Cited: April 5, 2021.] https://www.mazda.com/en/innovation/technology/safety/active_safety/daa/.
BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs. Yury, Kartynnik, et al. Mountain View California: Google Research, 2019, ArXiv.
Driver Drowsiness Detection via a Hierarchical Temporal Deep Belief Network. Ching-Hua, Weng, Ying-Hsiu, Lai and Shang-Hong, Lai. Taipei Taiwan: s.n., 2016. Asian Conference on Computer Vision Workshop on Driver Drowsiness Detection from Video.
