Helmet Detection on Two Wheeler Riders using Machine Learning and Automatic Licence Plate Recognition for Identification

Abstract

Motorcycle accidents are growing throughout the years in all the countries, as there is a difference in social, economical and the transport conditions differ from place to place. The motorcycle is one of the prominent means of transport used by middle-class people. Wearing a helmet is the main safety equipment of motorcyclists, which might not be followed by all drivers. The existing video surveillance-based methods are passive and require significant human assistance. In general, such systems are infeasible due to the involvement of humans, whose efficiency decreases over a long duration. Automation of this process is highly desirable for reliable and robust monitoring of these violations as well as it also significantly reduces the number of human resources needed. This project aims at the prevention of accidents by automatically identifying the drivers not wearing helmets and storing their respective License Plates for future investigation. For this, we are using a classifier based on FasterR-CNN object detection architecture.