Development of an Application for Vehicle Classification Using Neural Networks Technologies

Abstract

Nowadays, millions of people use the car as a mean of transport on a daily basis, whether it is taxi or personal transport. The automotive industry is actively developing, and more people are using the products of their activities. The number of car owners is increasing every day. Statistics show that every hour a new driver moves out in a brand new car. Detection of vehicles, mentioning categories of video data sequence, is an important but challenging task in terms of observing city traffic. The main difficulty of this task is that it requires the accurate localization of relatively small vehicles in complex scenes and must detect them in real time. The paper discusses the development of an application for the classification of vehicles in a video stream using neural network technologies.