Helmet Identification of Motorcycle Driver Using CNN

Abstract

To ensure the safety measures, the detection of traffic rule violators is a highly desirable but challenging task due to various difficulties such as occlusion, illumination, poor quality of surveillance video, varying weather conditions, etc. In this paper, we present a framework for the automatic detection of motorcyclists driving without helmets. In the proposed system, we have to detect Motorcyclists wearing a helmet or not, for detecting helmets we used a Tensorflow object detection hence we systematically studied the EfficientDetmodelwhich consistently achieves much better efficiency than prior art across a wide spectrum of resource constraints and fined tunned it to detect Helmets.