Advertisement

Using CNN and Channel Attention Mechanism to Identify Driver’s Distracted Behavior

  • Lu YeEmail author
  • Cheng Chen
  • Mingwei Wu
  • Samuel Nwobodo
  • Annor Arnold Antwi
  • Chido Natasha Muponda
  • Koi David Ernest
  • Rugamba Sadam Vedaste
Chapter
  • 44 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11782)

Abstract

The driver’s distracted attention will cause a huge safety hazard to the traffic. In different types of distraction, it is illegal to make phone calls and smoke while driving, which will be fined in China. In order to solve this problem, a method of driver’s distracted behavior detection based on channel attention convolution neural network is proposed. SE module is added to the Xception network, which can distinguish the importance of different feature channels and enhance the expression ability of the network. SE module mainly assigns different weights to features to enhance more important features and suppress less influential features. The experiment uses Xception and SE-Xception for comparison. The experimental results show that the accuracy of SE-Xception is 92.60%, which has a good performance for the distracted driving behavior detection of drivers.

Keywords

Squeeze-and-Excitation Channel attention Convolution neural network Distracted driving 

References

  1. 1.
    Choidhary, P., Velaga, N.R.: Mobile phone use during driving: effects on speed and effectiveness of driver compensatory behavior. Accid. Anal. Prev. 106, 370–378 (2017)CrossRefGoogle Scholar
  2. 2.
    Kutila, M.H., Jokela, M., Mäkinen, T., Viitanen, J., Markkula, G., Victor, T.W.: Driver cognitive distraction detection: feature estimation and implementation. Proc. Inst. Mech. Eng. Part D: J. Automob. Eng. 221, 1027–1040 (2007)CrossRefGoogle Scholar
  3. 3.
    Sahayadhas, A., Sundaraj, K., Murugappan, M., Palaniappanb, R.: A physiological measures-based method for detecting inattention in drivers using machine learning approach. Biocybern. Biomed. Eng. 35, 198–205 (2015)CrossRefGoogle Scholar
  4. 4.
    Ebadi, Y., Fisher, D.L., Roberts, S.C.: Impact of cognitive distractions on drivers’ hazard anticipation behavior in complex scenarios. Transp. Res. Rec.: J. Transp. Res. Board 2673, 440–451 (2019)CrossRefGoogle Scholar
  5. 5.
    Le, T.H.N., Zheng, Y., Zhu, C., Luu, K., Savvides, M.: Multiple scale faster-RCNN approach to driver’s cell-phone usage and hands on steering wheel detection. In: The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas (2016)Google Scholar
  6. 6.
    Xing, Y., et al.: Identification and analysis of driver postures for in-vehicle driving activities and secondary tasks recognition. IEEE Trans. Comput. Soc. Syst. 5, 95–108 (2018)CrossRefGoogle Scholar
  7. 7.
    Masood, S., Rai, A., Aggarwal, A., Doja, M.N., Ahmad, M.: Detecting distraction of drivers using convolutional neural network. Pattern Recognit. Lett. (2018)Google Scholar
  8. 8.
    Celaya-Padilla, J.M., et al.: Texting & driving detection using deep convolutional neural networks. Appl. Sci. 9, 2962 (2019)CrossRefGoogle Scholar
  9. 9.
    Hu, J., Liu, W., Kang, J., Yang, W., Zhao, H.: Semi-cascade network for driver’s distraction recognition. Proc. Inst. Mech. Eng. Part D: J. Automob. Eng. 233, 2323–2332 (2019)CrossRefGoogle Scholar
  10. 10.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  11. 11.
    Szegedy, C., et al.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston (2015)Google Scholar
  12. 12.
    loffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. Proc. Mach. Learn. Res. 37, 448–456 (2015)Google Scholar
  13. 13.
    Szegedy, C., Vanhoucke, V., loffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas (2016)Google Scholar
  14. 14.
    Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: The Thirty-First AAAI Conference on Artificial Intelligence, San Francisco (2016)Google Scholar
  15. 15.
    Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu (2017)Google Scholar
  16. 16.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-Excitation networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City (2018)Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  • Lu Ye
    • 1
    • 2
    Email author
  • Cheng Chen
    • 2
  • Mingwei Wu
    • 1
    • 2
  • Samuel Nwobodo
    • 1
  • Annor Arnold Antwi
    • 1
  • Chido Natasha Muponda
    • 1
  • Koi David Ernest
    • 1
  • Rugamba Sadam Vedaste
    • 1
  1. 1.School of Information and Electronic EngineeringZhejiang University of Science and TechnologyHangzhouChina
  2. 2.School of Mechanical and Energy EngineeringZhejiang University of Science and TechnologyHangzhouChina

Personalised recommendations