ABSTRACT
Road accidents are becoming a real global scourge because of the high number of victims involved and the severe consequences that affect road users as well as their families.
Despite the awareness campaigns on the vigilance and caution that must be undertaken on the road, deaths caused in road accidents are still increasing and are now considered as a major public health problem, more specifically in Morocco where the roads are among the most deadly.
To address this issue, vehicle manufacturers have made considerable progress in improving the intelligence and capacity of vehicles to perceive and analyze road environments to prevent accidents and secure passengers. However, with all these efforts, accident statistics show that in most cases, accidents are related to the inattention of the drivers and sometimes irresponsible behavior.
Therefore, considerable amount of research has recently been focused on the analysis and study of the general behaviors of drivers on the road, especially somnolence, as it is among the highest risk factors of accidents and is the leading cause of death on roads.
In this paper, we propose a new approach to analyze driver drowsiness by applying a new recurrent neural network architecture to frame sequences of a driver. We used a public data set to train and validate our model and applied a recurrent neural network architecture called "long short-term memory" to detect driver drowsiness.
- Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. TensorFlow: A System for Large-Scale Machine Learning.. In OSDI, Vol. 16. 265--283. Google ScholarDigital Library
- AMER Al-Rahayfeh and Miad Faezipour. 2013. Eye tracking and head movement detection: A state-of-art survey. IEEE journal of translational engineering in health and medicine 1 (2013), 2100212--2100212.Google Scholar
- Nawal Alioua, Aouatif Amine, Alexandrina Rogozan, Abdelaziz Bensrhair, and Mohammed Rziza. 2016. Driver head pose estimation using efficient descriptor fusion. EURASIP Journal on Image and Video Processing 2016, 1 (2016), 2.Google ScholarCross Ref
- Christopher JC Burges. 1998. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery 2, 2 (1998), 121--167. Google ScholarDigital Library
- François Chollet et al. 2015. Keras.Google Scholar
- National Tsuing Hua University Computer Vision Lab. 2016. Driver Drowsiness Detection Dataset. http://cv.cs.nthu.edu.tw/php/callforpaper/datasets/DDD/.Google Scholar
- Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell. 2015. Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2625--2634.Google ScholarCross Ref
- M El Ftouh, A Derradji, A Jniene, and M-T El Fassy Fihry. 2013. Étude de la prévalence et les facteurs de risque de la somnolence au volant dans une population marocaine. Médecine du Sommeil 10, 4 (2013), 141--145.Google ScholarCross Ref
- Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179--211.Google Scholar
- Yoav Freund, Robert E Schapire, et al. 1996. Experiments with a new boosting algorithm. In icml, Vol. 96. 148--156. Google ScholarDigital Library
- Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge. Google ScholarDigital Library
- Robert Hecht-Nielsen et al. 1988. Theory of the backpropagation neural network. Neural Networks 1, Supplement-1 (1988), 445--448.Google ScholarCross Ref
- Michael I Jordan. 1997. Serial order: A parallel distributed processing approach. In Advances in psychology. Vol. 121. Elsevier, 471--495.Google Scholar
- Victor Javier Kartsch, Simone Benatti, Pasquale Davide Schiavone, Davide Rossi, and Luca Benini. 2018. A sensor fusion approach for drowsiness detection in wearable ultra-low-power systems. Information Fusion 43 (2018), 66--76. Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Google ScholarDigital Library
- PS Jagadeesh Kumar. 2018. Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive Computer Gaming. In Progress in Advanced Computing and Intelligent Engineering. Springer, 91--102.Google Scholar
- Yuriy Kurylyak, Francesco Lamonaca, and Giovanni Mirabelli. 2012. Detection of the eye blinks for human's fatigue monitoring. In Medical Measurements and Applications Proceedings (MeMeA), 2012 IEEE International Symposium on. IEEE, 1--4.Google ScholarCross Ref
- Rainer Lienhart and Jochen Maydt. 2002. An extended set of haar-like features for rapid object detection. In Image Processing. 2002. Proceedings. 2002 International Conference on, Vol. 1. IEEE, II.Google Scholar
- Bappaditya Mandal, Liyuan Li, Gang Sam Wang, and Jie Lin. 2017. Towards detection of bus driver fatigue based on robust visual analysis of eye state. IEEE Transactions on Intelligent Transportation Systems 18, 3 (2017), 545--557. Google ScholarDigital Library
- World Health Organization. 2015. Global status report on road safety 2015. World Health Organization.Google Scholar
- MIT Technol. Rev. 2018. Dueling Neural Networks. https://www.technologyreview.com/lists/technologies/2018/. {Online; accessed 03-Mars-2018}.Google Scholar
- Jürgen Schmidhuber. 2015. Deep learning in neural networks: An overview. Neural networks 61 (2015), 85--117. Google ScholarDigital Library
- Pierre Sermanet, Koray Kavukcuoglu, Soumith Chintala, and Yann LeCun. 2013. Pedestrian detection with unsupervised multi-stage feature learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3626--3633. Google ScholarDigital Library
- Cleshain Solomon and Zenghui Wang. 2015. Driver Attention and Behavior Detection with Kinect. J. Image Graph 3, 2 (2015), 84--89.Google Scholar
- Nitish Srivastava, Elman Mansimov, and Ruslan Salakhudinov. 2015. Unsupervised learning of video representations using lstms. In International Conference on Machine Learning. 843--852. Google ScholarDigital Library
- Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112. Google ScholarDigital Library
- Ching-Hua Weng, Ying-Hsiu Lai, and Shang-Hong Lai. 2016. Driver Drowsiness Detection via a Hierarchical Temporal Deep Belief Network. In Asian Conference on Computer Vision. Springer, 117--133.Google Scholar
- Zhengyou Zhang. 2012. Microsoft kinect sensor and its effect. IEEE multimedia 19, 2 (2012), 4--10. Google ScholarDigital Library
Index Terms
- Driver Fatigue Detection using Recurrent Neural Networks
Recommendations
Vehicle driver drowsiness detection method using wearable EEG based on convolution neural network
AbstractVehicle drivers driving cars under the situation of drowsiness can cause serious traffic accidents. In this paper, a vehicle driver drowsiness detection method using wearable electroencephalographic (EEG) based on convolution neural network (CNN) ...
Driver State Monitoring System: A Review
BDIoT '19: Proceedings of the 4th International Conference on Big Data and Internet of ThingsTraffic crashes cause a lot of fatality and injuries every year. Robust and reliable driver monitoring system is an important step toward achieving higher vehicle autonomy level, as well as insuring the road safety and preventing road accidents. Driver ...
Real-time Driver Drowsiness Detection for Android Application Using Deep Neural Networks Techniques
AbstractRoad crashes and related forms of accidents are a common cause of injury and death among the human population. According to 2015 data from the World Health Organization, road traffic injuries resulted in approximately 1.25 million deaths worldwide,...
Comments