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

As the number of bikes in India is increasing daily compared to that of the human population. The danger of demise has increased 2.5 times among the riders without using a helmet contrasted with person wearing a helmet. The presented video observation based system may be powerful but still it needs critical human help whose productivity diminishes with time and human biasing additionally comes into the image. This paper plans to unwind this issue by automating the technique for distinguishing the riders with and without helmets. The system takes a video of traffic on an open street as an information and recognizes the moving items inside the scene. This work proposes a system based on the location of individual or different riders taking a trip on bikes with no helmets. Inside the proposed approach, from the beginning stage, bike riders are recognized with the use of YOLOv3 model which is a consistent type of YOLO model, the forefront methodology for object distinguishing helps as such in distinguishing the riders with and without helmet. The vertical projection of binary image is used for counting the number of riders if it exceeds two.