Ensuring the use of safety helmets is essential for reducing the risk of head injuries in both workplaces and on the road. However, workers and motorcycle riders often neglect wearing helmets due to discomfort or lack of awareness, leading to increased safety risks. To address this, a dual-purpose detection model has been developed to automatically detect helmet usage in construction sites and monitor motorcycle riders on the road. The system uses the YOLOv8 model to detect helmet usage, automatically capturing images, license plate numbers, and timestamps when helmets are not worn. The system also provides real-time monitoring, enabling authorities to act swiftly on safety violations. The model was tested with a diverse dataset, achieving high accuracy in detecting helmets, even in challenging conditions such as varying lighting and complex backgrounds. The results demonstrate that the system is highly efficient in monitoring helmet compliance, reducing the need for manual checks, and providing accurate, real-time data for enforcement.