Abstract

Driver fatigue is one the leading causes of car accidents in the world. The system aims to reduce the number of road accidents by detecting drowsiness and alerting the driver. The purpose of this paper is to develop a driver fatigue detection system. This system uses eye blinking frequency and yawning frequency of the driver to analyze drowsy driver and based on the level of drowsiness system will alert the driver. Driver’s facial features are captured by using a camera then this video input is used by system to monitor the driver's eyes to detect early stages of sleep as well as short periods of sleep; for video capturing system uses mobile phone camera making system portable and cost effective. Working of proposed system is based on the driver drowsiness detection method using Haar Cascade frontal face Classifier to detect the frontal facial structure followed by using dlib and Convolutional Neural Networks (CNNs) to extract information from sequence of images (video frames) for predicting driver fatigue.

References

• National Highway Traffic Safety Administration. Research on Drowsy Driving External. Accessed October 20, 2015.
• Klauer SG, Dingus TA, Neale VL, Sudweeks JD, Ramsey DJ. The Impact of Driver Inattention on Near-Crash/Crash Risk: An Analysis Using the 100-Car Naturalistic Study Data, 2006.External Springfield, VA: DOT; year. DOT HS 810 594.
• Tefft BC, AAA Foundation for Traffic Safety. Prevalence of Motor Vehicle Crashes Involving Drowsy Drivers, United States, 2009 – 2013 [457 KB]External.Washington, DC: AAA Foundation for Traffic Safety; 2014. October 19, 2015.
• Driver drowsiness detection using Behavioural measures and machine learning techniques: A review of state-of-art techniques by Mkhuseli Ngxande, Jules-Raymond Tapamo and Michael Burk of South Africa.
• EEG Processing System for Detecting a State of Drowsy Driving by Malika D. Kedir-Talha, Sid Ahmed Talha, Feriel Celia Boumghar Karim Meddah, and Hadjar Zairi from Algeria, International Journal of Pharma Medicine and Biological Sciences Vol. 5, No. 3, July 2016.
• F In proceedings Kuamr2014AnalysisOR, ‘Analysis of Real Time Driver Fatigue Detection Based on Eye and Yawning’, Narender Kuamr and Dr. Nemi Chand Barwar, 2014.
• Dlib-ml: A Machine Learning Toolkit by Davis E. King, Journal of Machine Learning Research 10 (2009) 1755-1758.
• http://dlib.net/imaging.html#shape_predictor - Image Processing.
• http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2 - Image Processing.
• https://docs.opencv.org/trunk/d7/d8b/tutorial_py_face_detection.html - Facial Landmarks.
• https://magoosh.com/data-science/convolutional-neural-networks-explained/ - Convolutional Neural Networks Explained.
• Convolutional Neural Networks (CNN) - https://www.superdatascience.com/blogs/convolutional-neural-networks-cnn-step-1-convolution-operation
• International Conference on Advanced Data Mining and Applications ADMA 2017: Advanced Data Mining and Applications pp 33-48, ‘Fault Detection and Localization in Distributed Systems Using Recurrent Convolutional Neural Networks’ by Guangyang Qi, Lina Yao, Anton V. Uzunov.
• Activation Functions: Comparison of Trends in Practice and Research for Deep Learning by Chigozie Enyinna Nwankpa, Winifred Ijomah, Anthony Gachagan, and Stephen Marshall, arXiv:1811.03378v1 [cs.LG] 8 Nov 2018.
• http://parnec.nuaa.edu.cn/xtan/data/datasets/dataset_B_Eye_Images.rar - Eye images dataset.
• http://www.site.uottawa.ca/~shervin/yawning/ - Yawning video frames dataset.