Journal of Research in Computer Science and Engineering ISSN: 2457-0818 (Online)

Authors: Omkar Javali, Varsha Desai, Snehal Kadolkar, Sapana Yakkundi

Abstract: Traffic law violations are a major cause of concern in our society. People’s irresponsible and careless attitudes towards driving laws has the potential to weaken the moral fiber of our society. While some progress has been made to update traffic laws, the human factor in our existing system remains a hurdle, resulting in dissatisfactory outcomes that could have been prevented. Legislation has mandated the use of safety belts and helmets by drivers, but with millions of drivers on the roads every day, it is difficult for police officers to monitor compliance. To ensure compliance with traffic regulations and improve road safety, an effective and efficient system for automatic traffic rule violation detection and fine collection is crucial in modern cities. Fortunately, the emergence of technological advancements has enabled Machine Learning techniques to provide solutions to this problem. By leveraging image processing and Machine Learning, our proposed system is able to analyze CCTV footage to detect traffic violations, such as the failure to wear seat belts or helmets. Machine Learning algorithms such as Convolutional Neural Network (CNN) and Automatic Number Plate Recognition (ANRP) can be used to increase the accuracy and efficiency of detecting traffic rule violations and thus improve compliance with the law and road safety.

Keywords:  Machine Learning, Violation Detection, ANRP, CNN