Pemodelan Identifikasi Objek Kendaraan Bermotor Menggunakan Faster Region based Convolutional Neural Network (R-CNN) Berbasis Python

Abstract

The vehicles are currently experiencing a surge in number and variation. This is evident from the kinds of vehicles that are passing through the highway area. The rise in the number of motorized vehicles will surely give a squeeze to the traffic density. The increase in the number of motor vehicles is one of the biggest factors in the impact of the congestion. The congestion can also cause damage to the highway. It's supposed to be the focus of the local government in dealing with the problem. Each road point has its own potential, so it is necessary to have a calculation in identifying the number of vehicles and the type of vehicles that are slipped on the road. Motor vehicle identification can be solved using the Faster Region based Convolutional Neural Network approach. Faster R-CNN is a deep learning architecture used to detect inside computers. Research will run at several highway points to take samples of video at a certain time, for identified the type of vehicle. Vehicle labelling will facilitate the calculation of the number of vehicles crossing the road in a given unit of time. The vehicle identification needs are used to see the density of the highway so that it can help the local government in making the right decision or solution to reduce the traffic density. The results of research such as quantitative data can be easily used to give the right picture and decision.