Published Paper Details:

Bikers who do not wear helmets pose a major threat to themselves. A UN Motorcycle study done in 2021 showed that around fifteen thousand deaths of bike riders could be avoided annually in India with safety measures. It also mentions that wearing helmets improves the chances of surviving accidents by 42 % and helps riders to avoid injuries by 69 %. Due to large vehicular traffic, manual monitoring of vehicles has become a problem. This can be automated using Deep Learning, which is the purpose of our work. Motorcycles have always been the primary mode of transportation in developing countries. Motorcycle accidents have increased in recent years. One of the main reasons for fatalities in accidents is that a motorcyclist does not wear a protective helmet. The most common way to ensure that motorcyclists wear a helmet is by traffic police to manually monitor motorcyclists at road junctions or through CCTV footage and to penalize those without a helmet. But it requires human intervention and effort. So this system Proposes an automated system for detecting motorcyclists who do not wear a helmet and retrieving their motorcycle number plates from CCTV video footage First, the system classifies moving objects as motorcycling or non motorcycling. In the case of a classified motorcyclist, the head portion is located and classified as a helmet or non-helmet. Finally, for the motorcyclist identified without a helmet, the number plate of the motorcycle is detected and the characters on it are extracted by using the OCR algorithm.