Helmet Detection System for Two-Wheeler Riders Using Yolo Machine Learning Algorithms
Keywords:
Object detection, helmet, YOLO, Machine learning, Two wheelersAbstract
Helmets are essential safety measures for anyone using two-wheeled vehicles (motorcycles, bicycles, and e-scooters), and the absence of protective helmets may result in serious or fatal injuries. The principal technique for helmet detection is now a series of Convolutional Neural Network methods. Detection accuracy, speed prediction, and ease of deployment are essential criteria for achieving road safety. Conventional object identification methods often fail to provide consistent performance across all domains. This study presents a helmet identification application using the latest You only look once version 7 (YOLOv7) algorithm enhanced by an attention-based approach. The model's performance was assessed using a collection of helmet test photos, achieving an average accuracy (mAP@0.5) of 91.4%. The findings demonstrate great detection accuracy and minimal computing requirements, making the model appropriate for practical use. Consequently, the suggested model may aid in addressing the issue of helmet detection on two-wheeled vehicles.
Downloads
Metrics
References
J. C. Useche, F. Alonso, and S. Montoro, "Validation of the Walking Behavior Questionnaire (WBQ): A tool for measuring risky and safe walking under a behavioral perspective," Journal of Transport & Health, vol. 22, p. 101088, 2021. doi: 10.1016/j.jth.2021.101088.
C. Störmann, M. Klug, M. Nau, M. Verboket, M. Leiblein, and T. Marzi, "Characteristics and injury patterns in electric-scooter related accidents—a prospective two-center report from Germany," Journal of Clinical Medicine, vol. 9, no. 5, p. 1569, 2020. doi: 10.3390/jcm9051569.
National Transportation Safety Board (NTSB), "Bicyclist Safety on US Roadways: Crash Risks and Countermeasures," NTSB Report NTSB/SS-19/01, 2019. [Online]. Available: https://www.ntsb.gov/safety/safety-studies/Documents/SS1901.pdf.
M. Lacinák and J. Ristvej, "Smart city, safety and security," Procedia Engineering, vol. 192, pp. 522–527, 2017. doi: 10.1016/j.proeng.2017.06.090.
J. Ristvej, M. Lacinák, and M. Zagorecki, "Decision support systems in crisis management: A survey of current approaches and future challenges," International Journal of Disaster Risk Reduction, vol. 31, pp. 1013–1021, 2018. doi: 10.1016/j.ijdrr.2018.09.001.
M. Zabovsky, M. Bučko, and J. Ristvej, "The use of ontologies in crisis management," in Proceedings of the 8th International Scientific Conference on Crisis Management: Challenges and Solutions, Žilina, Slovakia, 2010, pp. 1–6.
M. Bučko, M. Zabovsky, and J. Ristvej, "Ontology-based approach to intelligent data processing for crisis management," Communications - Scientific Letters of the University of Žilina, vol. 21, no. 1, pp. 3–9, 2019.
D. Tong, Y. Zhang, and H. Liu, "Helmet detection based on improved YOLOv3," in Proceedings of the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2020, pp. 799–803. doi: 10.1109/ITOEC49072.2020.9141770.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed, "SSD: Single shot multibox detector," in Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 2016, pp. 21–37. doi: 10.1007/978-3-319-46448-0_2.
J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018. [Online]. Available: https://arxiv.org/abs/1804.02767.
W. Zhou, Y. Zhang, and J. Wang, "Safety helmet detection based on YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 611–614. doi: 10.1109/CEI53227.2021.00099.
Z. Jia, Y. Zhang, and J. Wang, "Improved YOLOv5 algorithm for helmet detection," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 615–618. doi: 10.1109/CEI53227.2021.00100.
Y. Zhang, W. Zhou, and J. Wang, "Safety helmet detection based on improved YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 619–622. doi: 10.1109/CEI53227.2021.00101.
G. Cheng, Y. Zhang, and J. Wang, "Safety helmet detection based on improved YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 627–630. doi: 10.1109/CEI53227.2021.00103.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464–7475, 2023. doi: 10.1109/CVPRW53098.2023.00256.
S. Woo, J. Park, J.-Y. Lee, and I. Kweon, "CBAM: Convolutional block attention module," in Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018, pp. 3–19. doi: 10.1007/978-3-030-01234-2_1.
J. C. Useche, F. Alonso, and S. Montoro, "Validation of the Walking Behavior Questionnaire (WBQ): A tool for measuring risky and safe walking under a behavioral perspective," Journal of Transport & Health, vol. 22, p. 101088, 2021. doi: 10.1016/j.jth.2021.101088.
C. Störmann, M. Klug, M. Nau, M. Verboket, M. Leiblein, and T. Marzi, "Characteristics and injury patterns in electric-scooter related accidents—a prospective two-center report from Germany," Journal of Clinical Medicine, vol. 9, no. 5, p. 1569, 2020. doi: 10.3390/jcm9051569.
National Transportation Safety Board (NTSB), "Bicyclist Safety on US Roadways: Crash Risks and Countermeasures," NTSB Report NTSB/SS-19/01, 2019. [Online]. Available: https://www.ntsb.gov/safety/safety-studies/Documents/SS1901.pdf.
M. Lacinák and J. Ristvej, "Smart city, safety and security," Procedia Engineering, vol. 192, pp. 522–527, 2017. doi: 10.1016/j.proeng.2017.06.090.
J. Ristvej, M. Lacinák, and M. Zagorecki, "Decision support systems in crisis management: A survey of current approaches and future challenges," International Journal of Disaster Risk Reduction, vol. 31, pp. 1013–1021, 2018. doi: 10.1016/j.ijdrr.2018.09.001.
M. Zabovsky, M. Bučko, and J. Ristvej, "The use of ontologies in crisis management," in Proceedings of the 8th International Scientific Conference on Crisis Management: Challenges and Solutions, Žilina, Slovakia, 2010, pp. 1–6.
M. Bučko, M. Zabovsky, and J. Ristvej, "Ontology-based approach to intelligent data processing for crisis management," Communications - Scientific Letters of the University of Žilina, vol. 21, no. 1, pp. 3–9, 2019.
D. Tong, Y. Zhang, and H. Liu, "Helmet detection based on improved YOLOv3," in Proceedings of the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2020, pp. 799–803. doi: 10.1109/ITOEC49072.2020.9141770.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed, "SSD: Single shot multibox detector," in Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 2016, pp. 21–37. doi: 10.1007/978-3-319-46448-0_2.
J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018. [Online]. Available: https://arxiv.org/abs/1804.02767.
W. Zhou, Y. Zhang, and J. Wang, "Safety helmet detection based on YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 611–614. doi: 10.1109/CEI53227.2021.00099.
Z. Jia, Y. Zhang, and J. Wang, "Improved YOLOv5 algorithm for helmet detection," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 615–618. doi: 10.1109/CEI53227.2021.00100.
Y. Zhang, W. Zhou, and J. Wang, "Safety helmet detection based on improved YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 619–622. doi: 10.1109/CEI53227.2021.00101.
G. Cheng, Y. Zhang, and J. Wang, "Safety helmet detection based on improved YOLOv5," in Proceedings of the 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 2021, pp. 627–630. doi: 10.1109/CEI53227.2021.00103.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464–7475, 2023. doi: 10.1109/CVPRW53098.2023.00256.
S. Woo, J. Park, J.-Y. Lee, and I. Kweon, "CBAM: Convolutional block attention module," in Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018, pp. 3–19. doi: 10.1007/978-3-030-01234-2_1.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
