Live Helmet Detection System for Detecting Bikers without Helmet

Abstract

The higher death rate in motorbike accidents is credited to carelessness in wearing a head protector (helmet) by bike riders. Identification of helmetless riders continuously is a necessary task to forestall the event of such accidents. This paper presents an automated framework to distinguish motor bikers without a head protector (helmet) from traffic observation recordings progressively. In this paper, a Single shot multibox detector (SSD) model is applied to the helmet detection problem. This model can utilize just one single CNN system to distinguish the bounding box area of motorbike and rider. When the area is chosen we classify whether the biker is wearing or not wearing a helmet on real-time. Convolutional Neural Network is applied to select motorbikers among the moving objects and recognition of motorbikers without a helmet. Further applying the You only look once (YOLO) model, I recognize the License Plates of motorbikers without a helmet. So I have applied three models in all through the framework, the custom CNN Model, SSD Model and the YOLO model.

Keywords: CNN, Deep learning, Machine learning, OpenCV, YOLO.

View PDF