METHODOLOGY FOR ASSESSING TRAFFIC INTENSITY ON THE BASIS OF VIDEO SURVEILLANCE DATA

Abstract

The paper presents an approach to intelligent transport systems based on advanced machine learning algorithms, the purpose of which is to estimate the traffic flow on the road network. Data is obtained from traffic cameras located in a limited number of places. The approach includes two main algorithms. The first is a probabilistic algorithm for counting vehicles from low-quality images, which belongs to the category of unsupervised learning