Machine Learning-based Surveillance System for Detection of Bike Riders without Helmets and Triple Rides

Motorcycle accidents have been rapidly growing through the years in many countries. In India more than 37 million people use two wheelers. Therefore, it is necessary to develop a system for automatic detection of helmet wearing and triple rides for road safety. Therefore, a custom object detection model is created using a Machine learning based algorithm which can detect Motorcycle riders. On the detection of a Helmetless rider and triple rides, if the bike riders didn’t wear helmets and if they are going with triple rides then at that time the License Plate is extracted and the license Plate number is recognized using an Optical Character Recognizer. This Application can be implemented in real-time using a Webcam.

In this project, we can classify the image which consists of three riders using a deep learning process. In this, a CNN based architecture is designed to classify the image. The process of this project is first we train the image taken from the webcam. Then by considering input from the webcam the network will generate the output based on the trained data. This will get an accuracy of 70 %. 

Keywords: Raspberry Pi, MATLAB, WSN, Zigbee, IOT.