The notion of “road safety” represents the regulations and processes put in place to keep people using the roads from sustaining fatal or catastrophic injuries. Pedestrians, cyclists, drivers, passengers in vehicles, and riders of on-road public transport, particularly buses and trams, are examples of common road users. Modern road safety policies that emphasize preventing serious injuries and fatalities from car collisions and other incidents are known as optimal practices. Enhancing road safety directly benefits users by reducing the likelihood of accidents and improving the overall safety of public roads. Effective road safety measures ensure that commuting becomes more confident and secured, resulting in a reduction in frequency and severity of road traffic accidents. For law enforcers and city planners, improved road safety imparts much easier management of the flow of traffic, particularly a lesser burden on the health care system from road injuries. This project makes use of the deep learning model YOLOv7 to be used in an Intelligent Traffic Management System that detects motorcyclists for helmet usage and non-compliance with vehicle number plates. The system uses real-time traffic video feeds provided by high-definition cameras to detect violations through the incorporated YOLOv7. In this way, the very fast and accurate actions can be taken by the system to detect the violation through this mechanism of YOLOv7, which allows immediate and effective enforcement action. In this manner, it provides an improvement not only in road safety but also in a more systematic and data-driven traffic management and law enforcement lifestyle.