Helmet usage Analysis using Deep Learning

Abstract

Head protector examination is utilized to recognize the utilization of caps. Street traffic wounds are a significant general medical issue and a main source of death and injury around the globe. In the proposed frameworks, edge location calculation is utilized to distinguish the edges of the bikes and moment object division calculation is utilized to isolate the objects of the equivalent. Protective caps are prepared utilizing the Convolutional Neural Networks (CNN) calculation. Lastly Single Shot Detection (SSD) calculation is utilized to recognize the head protectors and motorbike. Relu work is utilized to figure the exactness. The general proficiency got is 95.4%. This work is basic, powerful and costproficient that can spare numerous lives and decrease the stunning weight of street car accidents occurring in everyday life.

Keywords

Deep Learning; Convolutional Neural Networks; Single Shot Detection; Optical character

References

1. Siebert FW, Lin H. Detecting motorcycle helmet use with deep learning. Accident Analysis & Prevention 2020;134:105319.
2. Duan B, Liu W, Fu P, Yang C, Wen X, Yuan H. Real-time on -road vehicle and motorcycle detection using a single camera. Procs. of the IEEE Int. Conf. on Industrial Technology, 10-13 Feb 2009, pp. 1-6.
3. Bhatia A. Wearing hel mets - A choice between life and death. Team NDTV article, Dec 9, 2016.
4. Wen CY, Chiu SH, Liaw JJ, Lu CP. The safety helmet detection for ATM's surveillance system v ia the modified hough transform. I EEE 37th Annual International Carnahan Co nference on Secur ity Technology, 2003, pp- 364-369.
5. Chiu CC, Ku MY, Chen HT. Motorcycle detection and tracking system with occlusion segm entation. Proceeding of International Workshop on Image Analysis for Multimedia Interactive Services , Santorini , Greece, 6 -8 June 2007, pp. 32-32.
6. Chiverton J. Helmet presence classification with motorcycle detection and tracking . IET Intelligence Transport Systems 2012;6:259- 69.
7. Dahiya K, Singh D, Mohan CK. Automatic detection of bike riders without helmet using surveillance videos in real – time. Proceeding of International Joint Conference Neural Networks , Vancouver, Canada. 24-2 July 2016, pp.3046-3051.
8. Doughmala P, Klubsuwan K. Half and Full Helmet Detection in Thailand using Haar Like Feature and Circle Hough Transform on Image Processing. Proceeding of IEEE International Conference on Computer and Information Technology, Thailand, Bangkok, 2016, pp. 611-614.
9. Karwal H, Girdhar A. Vehicle Number Plate Detection System for Indian Ve hicles. Proceeding of IEEE International Conference on Computational Intelligen ce and Communication Technology, 2015, pp. 8-12.
10. Sulaiman N. Development of Auto matic Vehicle Plate Detection System. Proceeding of IEEE 3rd International Conference on System Engineering and Technology 17 -20 Aug 2013.
11. Shaikh S, Lahiri B, Bhatt G, Raja N. A novel approach for Automatic Number Plate Recognition. Proceeding of International Conference on Intelligent Syst ems and Signal Processing, 2013, pp. 375-380.
12. B. Yogameena ; K. Menaka ; S. Saravana Perumaal,” Deep learning -based helmet wear analysis of a motorcycle rider for intelligent surveillance system”, in proceeding of Interna - tional Conference on Intelligent Systems, Vol- ume 7,July 2019.
13. Silva R, K. Aires, T. Santos, K. Abdala, R. Veras, and A. Soares, “Automatic det ection of motorcyclists without he lmet,” in Computing Conference, XXXIX Latin American, Oct 2013, pp. 1-7.
14. Rodrigues Veloso e Silva R, Teixeira Aires K, De Melo Souza Veras R. Helmet detection on motorcyclists using image descrip- tion and classifiers . Procs. of th e Graphics, Patterns and Images , Aug 2014, pp. 141-148.
15. Dalal N, Triggs B. Histograms of ori - ented gradients for human detection. Procs. of the IEEE Computer Society Conf. on Com - puter Vision and Patter n Recognition, J une 2005, pp. 886-893.