TWO WHEELERS TRAFFIC VIOLATION FINDER AND WARNING SYSTEM
NAGARAJAN M (1903038) MS.POOMA,,M.E,
Department Of Computer Science And Engineering Assistant Professor,
PSN College Of Engineering And Technology Department Of Computer Science And Engineering,
Tirunelveli. PSN College Of Engineering And Technology,
TIrunelveli.
Abstract—In recent years, riding a motorcycle has become one of the most convenient ways for consumers to go to their destination. The safety of riders depends greatly on their wearing helmets. Helmets are very important and necessary for the safety of motorcyclists, however, officers find it difficult to enforce the laws regarding the wearing of authorized helmets. In recent years, the real-time video monitoring of helmet wearing based on deep learning has attracted extensive attention. This project presents an automatic surveillance system for detecting two-wheeler drivers without helmets and recognizes their License plate numbers in the system. The proposed system is to solve this problem by automating the process of detecting the riders who are riding without helmets. The automated system for Helmet and Number Plate Detection and Recognition were to first detect if someone is wearing a helmet or not, if he is wearing it, no problem, but if not, detect his number plate and send an e-challan to him.The license plate is provided as the output in case the rider is not wearing a helmet. Theextracted registration numbers are then stored in a database for further identification of the bikers without helmets. This project can help local authorities to quantify the compliance levels of motorcyclists and prevent irreversible damage to them. To achieve an efficient helmet detection model, machine learning classifier is applied to the moving object to identify if the moving object is a two- wheeler. And then the system used the Faster Region Convolution Neural Network object detection model using transfer learning.For number plate recognition the system usesEasyOCR. As a result, the model with the best training received a mAP(Mean Average Precision) of 97%. The proposed system outperforms other related real-time helmet detection systems and license plate recognition models. This proposed system may be used on any CCTV camera to monitor motorcyclists to see if they are wearing a helmet or not