Helmet Detection and Number Plate Extraction using Machine Learning

The continual motorization of traffic has led to an increase in road accidents across the globe. The government is trying hard to make people follow driving rules to reduce accidents and fatal deaths, especially in India. In our country, the motorcycle is the most used vehicle. As a recommendation,...

Full description

Saved in:
Bibliographic Details
Published in2021 5th International Conference on Trends in Electronics and Informatics (ICOEI) pp. 947 - 951
Main Authors Sarma, D.Soma Sekhar, Varun, D.Mani, Posonia, A. Mary
Format Conference Proceeding
LanguageEnglish
Published IEEE 03.06.2021
Subjects
closed-circuit television (CCTV)
Head
Integrated optics
Machine learning
Motorcycles
Optical Character Recognition (OCR)
Road accidents
Safety
Online AccessGet full text

Cover

More Information
Summary:The continual motorization of traffic has led to an increase in road accidents across the globe. The government is trying hard to make people follow driving rules to reduce accidents and fatal deaths, especially in India. In our country, the motorcycle is the most used vehicle. As a recommendation, a system for automatically detecting helmet wear is mandatory for road safety. Where a significant number of people resulted in the death of not wearing a helmet. This project's main aim is to automatically detect bike-riders without helmets using CCTV videos. As a result, a machine learning-based algorithm is used to generate a unique object detection model that can specify motorcycle riders. The first step is to use the background subtraction technique to identify the bike riders. Then it detects whether the rider is wearing a helmet or not. If the person who is riding the motorcycle without the helmet is detected then the number plate is extracted from the video frame. Then with the help of an Optical character recognizer, the number plate is recognized.
DOI:10.1109/ICOEI51242.2021.9453054