Obtaining the Data for Formation of 3D Road Scene from the Radar Data

Abstract

This paper considers the problems of designing of technical vision systems based on millimeter radar technology. The architecture of the software for simulating the millimeter radar operation using mathematical models that simulate various objects of the road scene is considered. 3D road scenes of various configurations, taking into account the impact of the underlying surface have been studied. The possibility to classify the road obstacles and mobile agents of the road scene has been shown by analyzing the radar data from a car radar. The architecture of a neural network classifier that solves the problem of classification of road objects have been proposed.