Vehicle Classification and Traffic Violation Monitoring using Convolutional Neural Networks with ResNet and AlexNet

  • S.Priya, ManavPatel, Vaibhav Patil

Abstract

In today’s environment, traffic violations play a detrimental role in the society. A large

number of vehicles cause disturbances in areas like malls, parking places and toll areas. Management of such types of vehicles is a burdensome task. Traffic law violation monitoring and vehicle classification is proposed which recognizes whether the vehicle has undergone a violation and later checks for the vehicle’s license plate and act accordingly to the user. The input for the system is given as video streams and it can check for any violation done by the driver of the vehicle and identify the details of the drivers. Four major steps are involved in the proposed method. Initially, the classification of vehicle is based on Faster R-CNN with ResNet model i.e. detecting whether the vehicle is car or a motorcycle; then the detection of helmet violation by AlexNet CNN is proposed followed by the detection of car violation based on car speed; Finally if the violation is detected, it recognizes the license plate number using Optical Character Recognition for further process. This system has a lot of positive impact and help in normal functioning of the society.

Keywords: Faster-RCNN, ResNet, AlexNet, Optical Character Recognition.

Published
2020-05-05
How to Cite
S.Priya, ManavPatel, Vaibhav Patil. (2020). Vehicle Classification and Traffic Violation Monitoring using Convolutional Neural Networks with ResNet and AlexNet . International Journal of Advanced Science and Technology, 29(06), 2161 - 2168. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/13502