Open Access Open Access  Restricted Access Subscription Access

HeadSafe: AI-Powered Helmet Detection System

I.V. Dwaraka Srihith

Abstract


With more and more motorcycles on the roads, we're seeing more accidents, often because riders aren't wearing helmets. We can use CCTV footage from nearby buildings or crosswalks to check if people are wearing helmets. It's really important to use this technology to catch those who aren't following the rules. The idea is to use computers to automatically tell if someone's wearing a helmet or not. We're looking at a system that works a bit like a smart machine, using advanced computer vision techniques based on the YOLO-Darknet principle. This method combines computer vision with special types of neural networks trained on big datasets of everyday objects. By using YOLO's trained layers, which can quickly spot different things as the camera scans, we can make sure the system is really good at spotting whether someone's wearing a helmet or not.


Full Text:

PDF

References


Zhao, Liquan, and Shuaiyang Li. "Object detection algorithm based on improved YOLOv3." Electronics 9, no. 3 (2020): 537.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826.

Zhou, Fangbo, Huailin Zhao, and Zhen Nie. "Safety helmet detection based on YOLOv5." In 2021 IEEE International conference on power electronics, computer applications (ICPECA), pp. 6-11. IEEE, 2021.

F. W. Siebert, D. Albers, U. Aung Naing, P. Perego, and S. Chamaiparn, “Patterns of motorcycle helmet use - A naturalistic observation study in Myanmar,” Accident Analysis Prevention, vol. 124, pp. 146–150, 2019

F. W. Siebert and H. Lin, “Detecting motorcycle helmet use with deep learning,” Accident Analysis Prevention,. IEEE, June 2020.

Li, Kang, et al. "Automatic safety helmet wearing detection." arXiv preprint arXiv:1802.00264 (2018).

R. D. Ledesma, S. S. L´opez, J. Tosi, and F. M. Po´o, “Motorcycle helmet use in mar del plata, argentina: prevalence and associated factors,” International journal of injury control and safety promotion, vol. 22, no. 2, pp. 172–176, 2015.

A. Shen, “Beaverdam: Video annotation tool for computer vision training labels,” Master’s thesis, EECS Department, University of California, Berkeley, Dec 2016. [Online]. Available: http://www2.eecs.berkeley.edu/ Pubs/TechRpts/2016/EECS-2016-193.html

Bharathi, M., and T. Aditya Sai Srinivas. "Exploring Ant Colony Optimization for Enhanced Routing in IoT Networks: A Survey." Advancement in Image Processing and Pattern Recognition 7, no. 1 (2024): 68-83.

N. Boonsirisumpun, W. Puarungroj, and P. Wairotchanaphuttha, “Automatic detector for bikers with no helmet using deep learning,” in 2018 22nd International Computer Science and Engineering Conference (ICSEC). IEEE, 2018, pp. 1– 4


Refbacks

  • There are currently no refbacks.