Object Detection using Learning Algorithm and IoT

To reduce accidents and safeguard the lives of drivers, it is crucial to ensure road safety. Helmets are essential for preventing brain injuries during car accidents and must be worn properly. In this research, we offer a Helmets Detection device for Road Safety that makes use of IoT (Internet of Things) and the cutting-edge object detection algorithms YOLO (You Only Look Once).The proposed system makes use of the Raspberry Pi 3 and the IoT (Internet of Things) to gather real-time information from the camera. If the driver is wearing a helmet, the camera will gather an image of the helmet and if the ignition is successful, the engine will start. If the driver is not wears a helmet, our camera will capture an image and the engine fails to ignite. After being submitted into a reliable CNN (Convolutional Neural Network) model that was trained on an extensive collection of annotated helmet photos, the gathered data is then used. On a real-world dataset, we analysed this, and we were able to reach a high detection reliability of over 95%. The outcomes show that the suggested strategy is beneficial in enhancing road by recognising motorcyclists who neglect to put on helmets, accidents and injuries can be avoided. This information is sent to a central computer, where the YOLO technique is used to locate and identify motorcyclists’ helmets from collected photos.