DOI QR코드

DOI QR Code

Learning Model for Avoiding Drowsy Driving with MoveNet and Dense Neural Network

  • Jinmo Yang (Dept. of Physics, Korea University) ;
  • Janghwan Kim (Dept. of Software and Communication Engineering, Hongik University) ;
  • R. Young Chul Kim (Dept. of Software and Communication Engineering, Hongik University) ;
  • Kidu Kim (Telecommunications Technology Association)
  • 투고 : 2023.09.14
  • 심사 : 2023.09.26
  • 발행 : 2023.11.30

초록

In Modern days, Self-driving for modern people is an absolute necessity for transportation and many other reasons. Additionally, after the outbreak of COVID-19, driving by oneself is preferred over other means of transportation for the prevention of infection. However, due to the constant exposure to stressful situations and chronic fatigue one experiences from the work or the traffic to and from it, modern drivers often drive under drowsiness which can lead to serious accidents and fatality. To address this problem, we propose a drowsy driving prevention learning model which detects a driver's state of drowsiness. Furthermore, a method to sound a warning message after drowsiness detection is also presented. This is to use MoveNet to quickly and accurately extract the keypoints of the body of the driver and Dense Neural Network(DNN) to train on real-time driving behaviors, which then immediately warns if an abnormal drowsy posture is detected. With this method, we expect reduction in traffic accident and enhancement in overall traffic safety.

키워드

참고문헌

  1. Kwak, Seung-Hyun and Min, Byung-Chan, "Effect of sleepiness due to complete sleep deprivation on driving performance," Asia-pacific Journal of Multimedia Services Convergent with Art, Vol. 9, No. 1, pp. 615-623, 2019. DOI: 10.35873/ajmahs.2019.9.1.062
  2. Philip, P. and Akerstedt, T., "Transport and industrial safety, how are they affected by sleepiness and sleep restriction?," Sleep medicine reviews, Vol. 10, No. 5, pp. 347-356, 2006. DOI: 10.1016/j.smrv.2006.04.002
  3. Korea ROAD Traffic Authority, Constantly Drooping Eyelids Due to Allergies... Be Cautious of Drowsy Driving in the Spring Season. https://www.koroad.or.kr/synap/skin/doc.html?fn=BD_202303270808376881.pdf&rs=/upfilePath/koroadNew/synap/result/.
  4. Macalisang, J. R., Alon, A. S., Jardiniano, M. F., Evangelista, D. C. P., Castro, J. C., and Tria, M. L., "Drive-Awake: A YOLOv3 Machine Vision Inference Approach of Eyes Closure for Drowsy Driving Det ection," 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), pp. 1-5, 2021. DOI: 10.1109/IICAIET51634.2021.9573811
  5. Ikechukwu, V. A., Murali, S., Deepu, R., and Shivamurthy, R. C., "ResNet-50 vs VGG-19 vs training fro m scratch: A comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images," Global Transitions Proceedings, Vol. 2 No. 2, pp. 375-381, 2021. DOI: 10.1016/j.gltp.2021.08.02 7
  6. Tzutalin, LabelImg, https://github.com/HumanSignal/labelImg.
  7. Teyeb, I., Jemai, O., Zaied, M., and Ben Amar, C., "A novel approach for drowsy driver detection using head posture estimation and eyes recognition system based on wavelet network," The 5th International Conference on Information, Intelligence, Systems and Applications, pp. 379-384, 2014. DOI: 10.1109/IISA.2014.6878809.
  8. Viola, P., and Jones, M. J., "Robust real-time face detection", International Journal of Computer Vision, Vol. 57, pp. 137-154, 2004. DOI: 10.1023/B:VISI.0000013087.49260.fb
  9. Amar, C. B. and Jemai, O., "Wavelet networks approach for image compression," International Journal on Graphics, Vision and Image Processing, pp. 37-45, 2007.
  10. Kumar, P., Bhatnagar, R., Gaur, K., and Bhatnagar, A., "Classification of imbalanced data: review of methods and applications," IOP conference series, materials science and engineering, Vol. 1099, No. 1, 2021. DOI 10.1088/1757-899X/1099/1/012077
  11. TensorFlow, Next-Generation Pose Detection with Movenet and Tensorflow.Js, https://blog.tensorflow.org/2021/05/next-generation-pose-detection-with-movenet-and-tensorflowjs.html.
  12. Wang, C., Yao, C., Zhao, S., Zhao, S., and Li, Y., "A Comparative Study of a Fully-Connected Artificia l Neural Network and a Convolutional Neural Network in Predicting Bridge Maintenance Costs," Appl. Sc i, Vol. 12, 2022.
  13. LeCun, Y., Bengio, Y., and Hinton, G., "Deep Learning," Nature, Vol. 521, pp. 436-444, 2015. DOI: 10.1038/nature14539.
  14. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," Journal of Machine Learning Research, Vol. 15, No. 56, pp. 1929-1958, 2014. DOI: 10.5555/2627435.2670313
  15. Kingma, D. P., and Ba, J., "Adam: A Method for Stochastic Optimization," Conference Paper at the 3rd International Conference for Learning Representations, 2015. DOI: 10.48550/arXiv.1412.6980