This document summarizes a project that aims to develop a software system using computer vision and machine learning to detect whether motorcycle riders in Bangladesh are wearing helmets. It will use a camera to take photos of riders, apply object detection models like YOLO to identify bikes and people, and check if the riders are wearing helmets. If not, it will record the bike's license plate number. The document reviews similar existing works and compares the parameters of this project. It outlines that the project will be implemented in Python using YOLO and OpenCV for real-time object detection and helmet detection from images to help enforce road safety in Bangladesh.

1. 1.Fahim Faisal 1813114642
2. Sayed Ahmed Ashik 1813085642
3. Iftesam Amin Bhuiyan1621108642

2.  Road safety has been an issue in Bangladesh for a long time.
 Specially people in mega city like Dhaka are less likely to maintain
fundamental road safety like wearing helmet at the time of bike
riding.
 Every year we see a significant number of motor bike accident and
most of the time casualty increases only for not wearing helmet.
 Our goal is to make such a Python based project that will help
traffic control system with a view to increasing road safety.
 We want to build a software based project that will help traffic
control system to detect whether bike rider wears helmet or not.
Introduction

3.  It is about motorcycle riders. Camera will detect if the person is
wearing a helmet or not.
 If he or she does not wear helmet then camera will take the
vehicle’s license number plate and store the data for further legal
inquires.
Problem Statement

4. 1. Automatic Hardhat Wearing detection By Jixiu Wu.
Summery :This work tries to automate the monitoring of whether
people are wearing hardhat on the construction sites and identify the
corresponding colors.Detection success rate - 83.89%.
2. AI based helmet detection By Ayaz Saiyed
Summery :can detect the helmets from the images with 99%
accuracy . It is implemented using Opencv, Python,YOLOV3 . The
code can be implemented to detect helmets in real time.
Literature Review

5. Parameters Comaparison of our project with similar
works
Title Real time bike Rider’s
Helmet Detection
Automatic Hardhat
Wearing detection
Color detection Not required Required
Camera angle Riders Backside Not restricted to one
angle . i.e (side,front
,back)
Language Python C++ ,Python
Object Detection and
Model training tool
COCO, Open CV,YOLO Tensor Flow, SSD frame
work,YOLOV3,YOLOv4

6. 1. Jixiu Wu, Nian Cai, Wenjie Chen, Huiheng Wang, Guotian Wang ,
Automatic detection of hardhats worn by construction personnel: A deep
learning approach and benchmark dataset, Automation in Construction,
106(2019), 10.1016/j.autcon.2019.102894.
2. https://github.com/AyazSaiyed/Helmet-Detection
3. https://github.com/wujixiu/helmet-detection
References

7.  Will be implemented by Python.
• Yolo-Real time object detection for bike, car and person.
• Coco-Object detection by Dataset.
• OpenCV - Library for machine learning.
Application

8. THE END
ThankYou!!