Deep Learning based Discovery of Non-Helmet Riders and License Plate Number using Yolo v3 and OCR system

Abstract

In current situation, we come across various problems in traffic regulations in India which can be solved with 
different ideas. Riding motorcycle/mopeds without wearing helmet is a traffic violation which has resulted in 
increase in number of accidents and deaths in India. Existing system monitors the traffic violations primarily 
through CCTV recordings, where the traffic police have to look into the frame where the traffic violation is 
happening, zoom into the license plate in case rider is not wearing helmet. But this requires lot of manpower and 
time as the traffic violations frequently and the number of people using motorcycles is increasing day-by-day. 
What if there is a system, which would automatically look for traffic violation of not wearing helmet while riding 
motorcycle/moped and if so, would automatically extract the vehicles‟ license plate number. Recent research has 
successfully done this work based on CNN, R-CNN, LBP, HoG, Haar features. But these works are limited with 
respect to efficiency, accuracy or the speed with which object detection and classification is done. In this research 
work, a Non-Helmet Rider detection system is built which attempts to satisfy the automation of detecting the 
traffic violation of not wearing helmet and extracting the vehicles‟ license plate number. The main principle 
involved is Object Detection using Deep Learning at three levels. The objects detected are person, 
motorcycle/moped at first level using YOLOv2, helmet at second level using YOLOv3, License plate at the 
last level using YOLOv2. Then the license plate registration number is extracted using OCR (Optical Character 
Recognition). All these techniques are subjected to predefined conditions and constraints, especially the license 
plate number extraction part. Since, this work takes video as its input, the speed of execution is crucial. We have 
used above said methodologies to build a holistic system for both helmet detection and license plate number 
extraction.