Detection of Road Violators Using Machine Learning

Abstract

The main idea behind this project is to develop a system which could detect people who do not wear helmet. Road transport, especially two-wheeler, is most commonly used. Accidents often occur in two-wheeler, and by the usage of helmet, a person can be saved from brain injury. In our project, we find the people who have not worn helmet and detect their number plate which is sent to the RTO to lessen the validity of the license. By using TensorFlow, persons' images were trained so that they can detect the two-wheeler riders without helmet. It is difficult for traffic police to catch everyone so our project will help police department to identify two-wheeler riders who are not wearing helmets. Hence, this system will be helpful in preventing accident and consequently human suffering.