One of the major issues of road accidents all over the world is drowsiness state of the driver. It is a complex phenomenon to measure a driver’s consciousness in a direct manner. This work proposes with three deep neural architecture for learning facial features which consists of 68 attributes from the RGB video input of a driver. The experimentation is conducted by three different CNN models such as ResNet50, VGG16 and InceptionV3. These three networks are combined for representation learning which then put together the features to form a feature fused architecture(FFA). The trained features as well as facial movements such as eye blinking, yawning and head swaying are again trained with a softmax classifier to classify the drowsiness state of driver. Out of the three networks and FFA, InceptionV3 shows 78% accuracy.
JonesA., LangM., FyffeG., YuX., BuschJ., McDowallI., BolasM., DebevecP.Achieving eye contact in a oneto-many 3d video teleconferencing system, In: ACM Transactions on Graphics (TOG), Volume 28, ACM, 2009, p. 64.
2.
MittalA., KumarK., DhamijaS., KaurM., Head movement- based driver drowsiness detection: A review of state-of-art techniques, 2016 IEEE International Conference on Engineering and Technology (ICETECH), Coimbatore, 2016, pp. 903–908.
3.
AkinM., KurtM., SezginN., BayramM., Estimating vigilance level by using EEG and EMG signals, Neural Comput Appl17 (2008), 227–233.
4.
SzegedyC.et al., Going Deeper With Convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 1–9.
5.
WengC.-H., LaiY.-H., LaiS.-H., Driver Drowsiness Detection via a Hierarchical Temporal Deep Belief Network, Asian Conference, Computer Vision Workshop on Driver Drowsiness Detection from Video, Taipei, Taiwan, 2016.
6.
Conf. Ocular Measures of Driver Alertness, Washington, DC, 1999.
7.
MandicD.P., ChambersJ.Recurrent neural networks for prediction: Learning algorithms, architectures and stability, John Wiley Sons, Inc, 2001.
EdwardsD., SommerD., KrajewskiJ., GolzM., TrutschelU., Steering wheel behavior based estimation of fatigue, The fifth international driving symposium on human factors in driver assessment, training and vehicle design, 2009, pp. 118–124.
10.
HintonG.E., ZemelR.S., Autoencoders, minimum description length, and Helmholtz free energy, Advances in Neural Information Processing Systems (1994), pp. 3–3.
11.
HintonG.E., OsinderoS., TehY., A fast learning algorithm for deep belief nets, Neural Computation18 (2006), 1527–1554.
12.
GuoshengY., YingziL., PrabirB., A driver fatigue recognition model based on information fusion and dynamic Bayesian network, Inform Sci180 (2010), 1942–1954.
13.
ChenH., MurrayA.F., Continuous restricted Boltzmann machine with an implementable training algorithm, Vision, Image and Signal Processing, IEEE Proceedings150(3) (2003), 153–158. IET.
14.
HeK., ZhangX., RenS., SunJ.Deep residual learning for image recognition, In:, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 2013, pp. 27–30.
HeK., SunJ., Convolutional neural networks at constrained time cost, In CVPR (2015).
17.
MurataK., Noninvasive biological sensor system for detection of drunk driving, in IEEE Transactions on Information Technology in Biomedicine15(1) (2011), 19–25.
18.
SimonyanK., ZissermanA., Very deep convolutional networks for large-scale image recognition, In, ICLR2015.
19.
KhushabaR.N., KodagodaS., LalS., DissanayakeG., Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm, IEEE Trans Biomed Eng58 (2011), 121–131.
20.
KokonoziA.K., MichailE.M., ChouvardaI.C., MaglaverasN.M., A Study of Heart Rate and Brain System Complexity and Their Interaction in Sleep-Deprived Subjects, Proceedings of the Conference Computers in Cardiology, Bologna, Italy, 2008, pp. 969–971.
21.
LeeB.-G., ChungW.-Y., A smartphone-based driver safety monitoring system using data fusion, Sensors (Basel, Switzerland)12(12) (2012), 17536–17552.
22.
LiangW., YuanJ., SunD., LinM., Changes in physiological parameters induced by indoor simulated driving: Effect of lower body exercise at mid-term break, Sensors9 (2009), 6913–6933.
23.
LiuC.C., HoskingS.G., LennG., Predicting driver drowsiness using vehicle measures: Recent insights and future challenges, J Saf Res40 (2009), 239–245.
24.
LinM., ChenQ., YanS., Network in network, CoRR, abs/1312.44000, 2013.
25.
National Highway Traffic Safety Administration. Research on Drowsy Driving. Accessed October 20, 2015.
26.
AngelineP.J., SaundersG.M., PollackJ.B., An evolutionary algorithm that constructs recurrent neural networks, IEEE Transactions on Neural Networks5(1) (1994), 54–65.
SermanetP., EigenD., ZhangX., OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, 2013, CoRR, abs/1312.6229.
29.
SalakhutdinovR., HintonG.E., An efficient learning procedure for deep Boltzmann machines, Neural Computation August24(8) (2012), 1967–2003.
30.
SalakhutdinovR., MnihA., HintonG., Restricted Boltzmann machines for collaborative filtering, In Proc of the 24th International Conference on Machine Learning, ACM, 2007, pp. 791–798.
31.
TremaineR., DorrianJ., LackL., LovatoN., FergusonS., ZhouX., RoachG., The relationship between subjective and objective sleepiness and performance during a simulated night-shift with a nap countermeasure, Appl Ergon42 (2010), 52–61.
XiaoF., BaoC.Y., YanF.S., Yawning detection based on gabor wavelets and LDA, J Beijing Univ Technol35 (2009), 409–413.
34.
LeCunY., BengioY., Convolutional networks for images, speech, and time series, The handbook of brain theory and neural networks, 3361, 1995.
35.
YinB.-C., FanX., SunY.-F., Multiscale dynamic features based driver fatigue detection, Int J Pattern Recogn Artif Intell23 (2009), 575–589.
36.
ZhangZ., ZhangJ., A new real-time eye tracking based on nonlinear unscented Kalman filter for monitoring driver fatigue, J Contr Theor Appl8 (2010), 181–188.
