Real life safty use of helmet for every one

Related projects

1. RAJA BALWANT SINGH ENGINEERING TECHNICAL CAMPUS DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING MAJOR PROJECT ON : HELMET COMPLIANCE ENFORCEMENT SYSTEM FOR TWO WHEELERS Under the Guidance of: Er. Rahul Agarwal Presented By:   Aryan Singh(2100040310009)    Khushi Agarwal(2100040310020) Ritik Verma(2100040310029)

2. CONTENT Project Description Objective Need Introduction Methodology References

3. PROJECT DESCRIPTION Motorcycle accidents have been rapidly growing throughout the years in many countries. Due to various social and economic factors, this type of vehicle is becoming increasingly popular.  Helmet is the main safety equipment of motorcyclists, but many riders do not use it. If an motorcyclist is without helmet an accident can be fatal. So what is the solution for this problem? It is certain that we cannot solve this problem fully but we can maximize the number of riders wearing helmets. There are many helmet applications introduced now a days with sensors for detection of alcohol and drowsiness, to check whether helmet has been wore using image processing, machine learning techniques.

4.  This project aims to explain if a rider is not wearing a helmet, the traffic signal will not turn green. This system would use cameras and artificial intelligence to detect whether a rider is wearing a helmet or not. If the rider is not wearing a helmet, the system would prevent the traffic signal from turning green, thereby preventing the rider from proceeding.

5. OBJECTIVES Detection system based on camera detector with in-built AI and Machine Learning algorithm. Dynamically adopts to changing traffic conditions in real time. To develop a real-time intelligent traffic management system that detects motorcyclists without helmets and automatically turns the traffic signal red to prevent accidents and ensure road safety.  The system also displays the motorcyclist on a screen using image processing .

6. NEED Improved Safety : The system helps to ensure that individuals are wearing helmets, reducing risk of head injuries . Public Awareness: The system can raise public awareness about the importance of wearing helmet while riding.

7. INTRODUCTION The USB camera captures an image of a motorcyclist approaching the intersection. The Raspberry pi processes the image using Open CV and detect whether the motorcyclist is wearing helmet or not. If the motorcyclist is not wearing a helmet , the Raspberry pi sends a signal to the traffic signal controller. The traffic signal controller receives the signal and turn the traffic signal red to prevent the motorcyclist from proceeding . The sensors and actuator alerts the motorcyclist and other road users that the traffic signal has turned red.

8. The motorcyclist is required to stop and wear helmet before proceeding. Once the motorcyclist has wear a helmet, the traffic signal control system turns the traffic signal green , and the motorcyclist can proceed. Image Processing : Image Capture: The USB camera captures an image of the motorcyclist. Image Processing:   The raspberry pi processes the image using open cv to detect the motorcyclist and the helmet. Helmet Detection:  The Raspberry Pi uses a machine learning algorithm to detect whether the motorcyclist is wearing a helmet or not. Image Display:  The Raspberry Pi displays the motorcyclist on the LCD display using OpenCV

9. IMAGE ACQUSITON ANNOTATION OF IMAGE TRAINING WITH YOLO LOAD THE TRAINED MODEL OBTAIN PERSONS AND HELMET COUNT IMAGE FRAME FROM VIDEO MOVE TO THE NEXT IMAGE FRAME DETECTION OF TRAINED CLASSES OBTAIN THE LISCENCE PLATE PERSON ON TWO WHEELER WITHOUT HELMET CHANGE THE TRAFFIC SIGNALS TO RED

10. LITERATURE REVIEW R. Silva, K. Aires, T. Santos, K. Abdala, R. Veras and A. Soares, "Automatic detection of motorcyclists without helmet",  2013  Latin American Computing Conference(CLEI) .  This paper aims to explain and illustrate an automatic method for motorcycles detection and classification on public roads and a system for automatic detection of motorcyclists without helmet. For this, a hybrid descriptor for features extraction is proposed based in Local Binary Pattern, Histograms of Oriented Gradients and the Hough Transform descriptors. Traffic images captured by cameras were used. The best result obtained from classification was an accuracy rate of 0.9767, and the best result obtained from helmet detection was an accuracy rate of 0.9423.

11. Lokesh Allamki , Manjunath Panchakshari, Ashish Sateesha and K S Pratheek, "Helmet Detection using Machine Learning and Automatic License Plate Recognition",  International Research Journal of Engineering and Technology (IRJET) , vol. 06, no. 12, Dec 2019.

12. Soumya Ashwath, Chidananda T, Ashwin Shenoy M, Santhosh S, Supreetha D R, "Enhancing Road Safety through Innovative Traffic Sign Detection and Recognition with YOLOv5",  2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) , pp.1-4, 2024.

13. METHOLOGY/PLANNING OF WORK The proposed method mainly uses the raspberry pi 2 board which is the main controller of the system. The new version of raspbian buster has been used on the board. At the beginning we need to install the operating system of the raspberry pi to the SD card. Once the operating system is installed we need to connect the components to the hardware and power supply should be switched on. Login through the raspberry pi board and check the network settings. Once the camera is enabled the image has to be captured. The captured image then has to be classified as a positive or negative image  using Haar classifier so  we need to run the python code.

14. START Install the Raspberry Pi OS to the SD card Connect the components to the hardware and switch on the power supply Login the Raspberry pi board Enable the camera & capture the image Run the code in python

15. REFRENCES HELMET DETECTION USING MACHINE LEARNING ,Chaitanya Srusti, Vibhav Deo, Dr. Rupesh C. Jaiswal ,Department of Electronics and Telecommunication, SCTR’s Pune Institute of Computer Technology, Pune India, 0ctober 2022. K. Dahiya, D. Singh, and C. K. Mohan, “Automatic detection of bike riders without helmet using surveillance videos in real-time,” in Proc. Int. Joint Conf. Neural Networks (IJCNN), Vancouver, Canada, 24–29 July 2017 Soumya Ashwath, Chidananda T, Ashwin Shenoy M, Santhosh S, Supreetha D R, "Enhancing Road Safety through Innovative Traffic Sign Detection and Recognition with YOLOv5",  2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) , pp.1-4, 2024