Simulation of Urban Automotive Radar Measurements for Deep Learning Target Detection

Abstract

Frequency modulated continuous wave radars are an important component of modern driver assistance systems and enable safer automated driving. To achieve real time detection and classification of multiple road users in the range-Doppler map, the usage of neural target detection networks is proposed. Since the amount of labelled radar measurements available limits the training process, a new radar simulation framework is presented which generates arbitrary traffic scenarios with reflection models for pedestrians, bicyclists and vehicles. With an adaptive FMCW setup, sequences of dynamic urban multi-target radar measurements are simulated, maintaining minimum computational complexity. Solely trained on simulated measurement data, the neural network achieves an average precision above 87% on bicyclists and vehicles in real measurement data which is comparable to the performance of neural networks trained on real measurement datasets.