Motorcyclist's Helmet Wearing Detection Using Image Processing

Abstract

Motorcycle accidents have been rapidly growing throughout the years in many countries. Due to various social and economic factors, this type of vehicle is becoming increasingly popular. The helmet is the main safety equipment of motorcyclists but many drivers do not use it. If a motorcyclist is without helmet an accident can be fatal. This paper presented an automatic method for vehicle detection, motorcycles classification on public roads and a system for automatic detection of motorcyclists without helmet. For processing, in first step, we detect vehicles that moving real-time by extracting back ground out from front ground using back subtraction then enhancing it using threshold and mathematical morphology method. In the second step, we classify between motorcycle and other vehicles. Area is applied for feature extraction and neural network is applied for classification. In the final step, Hough transform is applied for detecting a helmet. From the experimental results, the accuracy rates of the motorcycle classification and helmet detection were 98.22% and 77%, respectively.