AUTOMATED HELMET MONITORING SYSTEM USING DEEP LEARNING

Abstract

Safety and compliance are the uppermost and fundamental concerns in the modern transport subsystems. As a result, the project is essentially designed to come up with an advanced solution by combining YOLOv8 for precise identification of objects and, on the other hand, EasyOCR for reading characters. The key goals are to detect helmets, those without helmets, and identify number plates of the respective motor vehicle. With YOLOv8, we start training the model to identify not only helmets but the lack of helmets, which is necessary for compliance monitoring based on the law. Further, YOLOv8 is also designed to determine the Regions of Interest . Regarding vehicles, the model focuses mainly on license plates which are key objects. After finding the appropriate areas, EasyOCR is designed for applying optical character recognition, helping to obtain vehicle numbers of any type in the most organized, quick way. Therefore, combining YOLOv8 at the stage of object detection and EasyOCR for the recognition of characters creates a novel but, at the same time susceptible system for a vehicle control company.

This integrated system is a sophisticated device for monitoring helmeted and unhelmeted riders, promoting a safe and stable journey gadget. By leveraging real-time records, our answers provide precious insights into protection compliance. In summary, the aggregate of YOLOv8 and EasyOCR presents a effective answer for item popularity and conduct reputation, so that our system contributes to the development of secure and green urban mobility by means of preserving rider protection and safety.