Manuscript Number : SHISRRJ24726

A Swin Transformer-Based Approach for Motorcycle Helmet Detection

Authors(2) :-Dr. K. Shanmugam, Kakimanu. Chandana

By supporting enforcement actions, automated video surveillance-based helmet wear identification among motorbike riders possesses the capacity to increase traffic safety. In spite of this, there are numerous drawbacks to the existing detection methods. For example, they can't distinguish between several passengers or work well in complicated environments. In this study, we combine computer vision and machine learning to tackle the difficult challenge of automated helmet use monitoring. We suggest a technique called transformers that is grounded in models of deep neural networks. The Swin transformer's base version serves as the foundation for feature extraction, and for final detection, we integrate the Cascade Area-based Convolution Framework for Neural Networks (RCNN) with a Neck of the Feature Pyramid Network (FPN). Our proposed strategy's effectiveness is validated by extensive testing and compared with current methods. Our model's mean average precision (mAP) was 30.4. approach performs better than existing methods for detection.

Authors and Affiliations

Dr. K. Shanmugam
Assistant Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India
Kakimanu. Chandana
Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India

Deep learning, intelligent transportation systems, transformers, motorbike safety, and helmet detection.

  1. (Jun. 2022). Road Traffic Injuries. WHO. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries
  2. H. A. Abdelali, O. Bourja, R. Haouari, H. Derrouz, Y. Zennayi, F. Bourzex, and R. O. H. Thami, ‘‘Visual vehicle tracking via deep learning and particle filter,’’ in Advances on Smart and Soft Computing, F. Saeed, T. Al-Hadhrami, F. Mohammed, and E. Mohammed, Eds. Singapore: Springer, 2021, pp. 517–526.
  3. H. Derrouz, A. Elbouziady, H. A. Abdelali, R. O. H. Thami, S. El Fkihi, and F. Bourzeix, ‘‘Moroccan video intelligent transport system: Vehicle type classification based on three-dimensional and two-dimensional features,’’ IEEE Access, vol. 7, pp. 72528–72537, 2019.
  4. Z. Charouh, A. Ezzouhri, M. Ghogho, and Z. Guennoun, ‘‘Video analysis and rule-based reasoning for driving maneuver classification at intersections,’’ IEEE Access, vol. 10, pp. 45102–45111, 2022.
  5. A. Ezzouhri, Z. Charouh, M. Ghogho, and Z. Guennoun, ‘‘Robust deep learning-based driver distraction detection and classification,’’ IEEE Access, vol. 9, pp. 168080–168092, 2021.
  6. J. Misachi. (Aug. 2019). Countries With the Highest Motorbike Usage. [Online]. Available: https://www.worldatlas.com/articles/countries-thatride-motorbikes.html
  7. A. Krizhevsky, I. Sutskever, and G. E. Hinton, ‘‘ImageNet classification with deep convolutional neural networks,’’ in Proc. Adv. Neural Inf. Process. Syst. (NIPS), vol. 25, Dec. 2012, pp. 1097–1105.
  8. K. Simonyan and A. Zisserman, ‘‘Very deep convolutional networks for large-scale image recognition,’’ 2014, arXiv:1409.1556.
  9. R. Girshick, J. Donahue, T. Darrell, and J. Malik, ‘‘Rich feature hierarchies for accurate object detection and semantic segmentation,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2014, pp. 580–587.
  10. Y. LeCun, Y. Bengio, and G. Hinton, ‘‘Deep learning,’’ Nature, vol. 521, no. 7553, pp. 436–444, 2015.

Publication Details

Published in : Volume 7 | Issue 2 | March-April 2024
Date of Publication : 2024-04-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 35-42
Manuscript Number : SHISRRJ24726
Publisher : Shauryam Research Institute

ISSN : 2581-6306

Cite This Article :

Dr. K. Shanmugam, Kakimanu. Chandana, "A Swin Transformer-Based Approach for Motorcycle Helmet Detection", Shodhshauryam, International Scientific Refereed Research Journal (SHISRRJ), ISSN : 2581-6306, Volume 7, Issue 2, pp.35-42, March-April.2024
URL : https://shisrrj.com/SHISRRJ24726

Article Preview