Pose Estimation for Distracted Driver Detection Using Deep Convolutional Neural Networks

Distracted driver has been a major issue in today’s world with more than 1.25 million road incidents of fatality. Almost 20% of all the vehicle crashes occur due to distracted driver. We attempt to create a warning system which will make the driver attentive again. This paper focuses on a simple yet effective Convolutional Neural Network technique which can help us to detect if the driver is safely driving or is distracted which is a binary classification task. It would help in improving the safety measures of the driver and vehicle. We propose two techniques for distracted driver detection achieving state of the art results. We achieve an accuracy of 96.16% for the 10 class classification. We propose to deconstruct the problem into a binary classification problem and achieve an accuracy of 99.12% for the same. We take advantage of recent techniques of transfer learning combined with regularization techniques to achieve these results.

[1]  Bailing Zhang,et al.  Recognition of driving postures by contourlet transform and random forests , 2012 .

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Mohan M. Trivedi,et al.  On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[7]  Mohan M. Trivedi,et al.  Head, Eye, and Hand Patterns for Driver Activity Recognition , 2014, 2014 22nd International Conference on Pattern Recognition.

[8]  Marios Savvides,et al.  Driver cell phone usage detection on Strategic Highway Research Program (SHRP2) face view videos , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[10]  Marios Savvides,et al.  Multiple Scale Faster-RCNN Approach to Driver’s Cell-Phone Usage and Hands on Steering Wheel Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Frans Coenen,et al.  Driving posture recognition by convolutional neural networks , 2016, IET Comput. Vis..

[12]  Hesham M. Eraqi,et al.  Real-time Distracted Driver Posture Classification , 2017, ArXiv.

[13]  Sanjay N. Talbar,et al.  Detection of Distracted Driver Using Convolutional Neural Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Andreas Savakis,et al.  Distracted Driver Detection: Deep Learning vs Handcrafted Features , 2017 .

[15]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[16]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[17]  Nanning Zheng,et al.  Visual recognition of driver hand-held cell phone use based on hidden CRF , 2011, Proceedings of 2011 IEEE International Conference on Vehicular Electronics and Safety.

[18]  Bailing Zhang,et al.  Erratum to: Recognition of driving postures by combined features and random subspace ensemble of multilayer perceptron classifiers , 2012, Neural Computing and Applications.