A Review on Helmet Detection of Motorcyclists in Different Atmospheric Conditions

Abstract-Due to the rising population in emerging nations, the number of traffic fatalities is rising nowadays. A complex program called an intelligent transport system (ITS) supports many types of transportation and traffic management. As part of the ITS services, roadside units help monitor traffic laws and emergency rescue calls. It has been noticed that failure to wear a helmet is a common cause of fata motorcycle accidents. Automatically identifying helmet infractions by motorcycle riders from real-time recordings is a difficult application for ITS. It enables the identification and punishment of bikers who are not wearing helmets Therefore, it is necessary to create a system that can instantly identify and detain motorcycle riders who are not wearing helmets. Using different types of deep learning techniques such as CNN, RCNN, Faster-RCNN, and YOLO. These techniques process film’s input and detect helmet violations. This study proposes to automatically detect helmet violations using surveillance footage from cameras placed alongthe side of the road. This suggested technique detects helmet violations and penalizes traffic law breakers using footage as input. The method YOLO-v8 described in this article use surveillance filmcaptured by cameras positioned along the side of the road in a variety of weather situations such as cloudy, clear, rainy, foggy, windy, stormy, and snowy. In order to prosecute those who violate traffic laws, will be punishes by thecourt of law.