• Anirban Ashok Rudra
• Shrish Kiran Vaidya
• Kaushal Rajbahadur Singh

Motorcycle accidents have been on the rise in several countries over the years. Any smart traffic system must include automated detection of offenders of traffic rules. Motorcycles are one of the main ways of transportation in a country like India, where population density is considerable in all major cities. Over 37 million people in India ride two-wheelers. Most motorcyclists do not wear helmets in the city or even on highways, according to reports. In most motorcycle accident scenarios, wearing a helmet can lower the likelihood of a biker suffering a head or severe brain injury. As a result, a technology for automatically detecting helmets is required for road safety. As a result, using a CNN-based algorithm (YOLOv4), custom object detection models are built. The License Plate is retrieved and the License Registration number is recognized using an OCR whenever a Helmetless rider is detected. This project aims to develop a CNN-based automated detection system for helmet identification utilizing custom-trained models and datasets that will aid police departments in enforcing the law for the greater good of society.

YOLOv4(You Only Look Once) object detection algorithm, CNN(Convolutional Neural Network), OCR(Optical Character Recognition).

"DETECTION OF HELMET USING YOLOV4 AND GENERATION OF AN E-CHALLAN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.c477-c482, April-2022, Available :http://www.jetir.org/papers/JETIR2204268.pdf

"DETECTION OF HELMET USING YOLOV4 AND GENERATION OF AN E-CHALLAN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppc477-c482, April-2022, Available at : http://www.jetir.org/papers/JETIR2204268.pdf