Deep learning-based car seatbelt classifier resilient to weather conditions

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Deep Learning is a very promising field in image classification. It leads to the automation of many real-world problems. Currently, Car seatbelt violation detection is done manually or partial manual. In this paper, an approach is proposed to make the seat belt detection process fully automated. To make the detection more accurate, sensors are set to detect the weather condition. When spe-cific weather condition is detected, the corresponding pre-trained model is assigned the detection task. In other words, a research is conducted to check the possibility of dividing the big-sized deep-learning model - that can classify car seatbelt, into sub-models each one can detect specific weather condition. Accordingly, a single specialized model is used for each weather condition, Deep convolutional neural network (CNN) model AlexNet is used in the detection/classification process. The proposed system is sensor based AlexNet (S-AlexNet). Results support our hypothesis that “Using single model for each weather condition is better than gen-eral model that support all weather conditions”. On average, previous approaches that trained single model for all weather condi-tions have accuracy less than 90%. The proposed S-AlexNet approach successfully reaches 90+% accuracy.



  • Keywords

    Seatbelt Detection; Deep Neural Network; Classification; True Positive.

  • References

      [1] Guo, H., Lin, H., Zhang, S., & Li, S. (2011, July). Image-based seat belt detection. In Vehicular Electronics and Safety (ICVES), 2011 IEEE International Conference on (pp. 161-164). IEEE.‏

      [2] G.Y. Song, K.Y. Lee, J.W. Lee, Vehicle detection by edge-based candidate gener- ation and appearance-based classification, in: Intelligent Vehicles Symposium, IEEE, 2008, pp. 428–433.

      [3] B. Sun, S. Li, moving cast shadow detection of vehicle using combined color models, in: Pattern Recognition, IEEE, 2010, pp. 1–5

      [4] BOERNSTEIN W. S. (1955). Classification of the human senses. The Yale journal of biology and medicine, 28(3-4), 208–215.

      [5] Bojarski, M., Yeres, P., Choromanska, A., Choromanski, K., Firner, B., Jackel, L., & Muller, U. (2017). Explaining how a deep neural network trained with end-to-end learning steers a car. arXiv preprint arXiv:1704.07911.‏

      [6] What is backpropagation really doing? | Deep learning, chapter 3, 3BLUE1BROWN SERIES S3 E3 (2019)

      [7] Rio-Alvarez, A., de Andres-Suarez, J., Gonzalez-Rodriguez, M., Fernandez-Lanvin, D., & López Pérez, B. (2019). Effects of Challenging Weather and Illumination on Learning-Based License Plate Detection in Noncontrolled Environments. Scientific Programming, 2019.‏

      [8] El-Melegy, M. T., El-Magd, K. M. A., Ali, S. A., Hussain, K. F., & Mahdy, Y. B. (2019, February). Ensemble of Multiple Classifiers for Automatic Multimodal Brain Tumor Segmentation. In 2019 International Conference on Innovative Trends in Computer Engineering (ITCE) (pp. 58-63). IEEE.‏

      [9] Sun, W., Du, H., Nie, S., & He, X. (2019). Traffic Sign Recognition Method Integrating Multi-Layer Features and Kernel Extreme Learning Machine Classifier.‏

      [10] Ershadi, N. Y., Menéndez, J. M., & Jimenez, D. (2018). Robust vehicle detection in different weather conditions: Using MIPM. PloS one, 13(3), e0191355.‏

      [11] Pavel Surmenok, “ResNet for Traffic Sign Classification with PyTorch”. Twords data science, Nov 2018.

      [12] A. Khammari , F. Nashashibi , Y. Abramson , C. Laurgeau , Vehicle detection com- bining gradient analysis and Adaboost classification, in: Intelligent Transporta- tion Systems Conference, IEEE, 2005, pp. 66–71

      [13] Li, W., Lu, J., Li, Y., Zhang, Y., Wang, J., & Li, H. (2013, December). Seatbelt detection based on cascade adaboost classifier. In 6th IEEE International Congress on Image and Signal Processing (CISP2013), (Vol. 2, pp. 783-787)

      [14] Xu, J., & Song, K. (2015, October). Study on Automatic Detection Method of Automobile Safety Belt Based on the Improvement of Adaboost Algorithm. In 2015 3rd International Conference on Mechatronics and Industrial Informatics (ICMII 2015). Atlantis Press.‏

      [15] J. Arróspide, L. Salgado, M. Nieto, “Video analysis based vehicle detection and tracking using an MCMC sampling framework”, EURASIP Journal on Advances in Signal Processing, vol. 2012, Article ID 2012:2, Jan. 2012

      [16] H. Grabner , C. Beleznai , H. Bischof , Improving Adaboost detection rate by wob- ble and mean shift, in: Proceedings of Computer Vision Winter Workshop, vol. 5, 2010, pp. 23–32.

      [17] Y. Gao, F. Gao, Edited Adaboost by weighted kNN, Neurocomputing 73 (16–18) (2010) 3079–3088.

      [18] Yu D, Zheng H, Liu C. (2013). Driver's Seat Belt Detection in Crossroad Based on Gradient Orientation. InInformation Science and Cloud Computing Companion (ISCC-C), International Conference on 2013 Dec 7 (pp. 618-622). IEEE.

      [19] Yusuf Artan et al, " Passenger Compartment Violation Detection in HOV/HOT Lanes", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 17, NO. 2, pp: 395: 405 FEBRUARY 2016

      [20] Zhang, D. (2018). Analysis and research on the images of drivers and passengers wearing seat belt in traffic inspection. Cluster Computing, 1-7.

      [21] Zhou, B., Chen, D., & Wang, X. (2017, August). Seat Belt Detection Using Convolutional Neural Network BN-AlexNet. In International Conference on Intelligent Computing (pp. 384-395). Springer, Cham.‏‏

      [22] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).

      [23] Yanxiang Chen, Gang Tao, Hongmei Ren, Xinyu Lin, Luming Zhang, Accurate seat belt detection in road surveillance images on CNN and SVM, Journal Neurocomputing Volume 274 Issue C, pp. 80-87, 2018

      [24] Mat Leonard, Code for the Deep Learning with PyTorch lesson, GitHub, May 2018

      [25] Kingma, D. P., & Ba, J. L. (2015). Adam: a Method for Stochastic Optimization. International Conference on Learning Representations, 1–13

      [26] Goh, "Why Momentum Really Works", Distill, 2017.

      [27] Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).‏




Article ID: 30050
DOI: 10.14419/ijet.v9i1.30050

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.