Improving the efficiency of neural networks with virtual training data

Authors

  • János Hollósi
  • Rudolf Krecht
  • Norbert Markó
  • Áron Ballagi

DOI:

https://doi.org/10.33927/hjic-2020-02

Keywords:

neural network, virtual training data, autonomous vehicle

Abstract

At Széchenyi István University, an autonomous racing car for the Shell Eco-marathon is being developed. One of the main tasks is to create a neural network which segments the road surface, protective barriers and other components of the racing track. The difficulty with this task is that no suitable dataset for special objects, e.g. protective barriers, exists. Only a dataset limited in terms of its size is available, therefore, computer-generated virtual images from a virtual city environment are used to expand this dataset. In this work, the effect of computer-generated virtual images on the efficiency of different neural network architectures is examined. In the training process, real images and computer-generated virtual images are mixed in several ways. Subsequently, three different neural network architectures for road surfaces and the detection of protective barriers are trained. Past experiences determine how to mix datasets and how they can improve efficiency.

Author Biographies

János Hollósi

Department of Information Technology, Széchenyi István University, Egyetem tér 1, Győr, 9026, HUNGARY, Research Center of Vehicle Industry, Széchenyi István University, Egyetem tér 1, Győr, 9026, HUNGARY

Rudolf Krecht

Research Center of Vehicle Industry, Széchenyi István University, Egyetem tér 1, Győr, 9026, HUNGARY

Norbert Markó

Research Center of Vehicle Industry, Széchenyi István University, Egyetem tér 1, Győr, 9026, HUNGARY

Áron Ballagi

Department of Automation, Széchenyi István University, Egyetem tér 1, Győr, 9026, HUNGARY

Downloads

Published

2020-07-06

How to Cite

Hollósi, J., Krecht, R., Markó, N., & Ballagi, Áron. (2020). Improving the efficiency of neural networks with virtual training data. Hungarian Journal of Industry and Chemistry, 48(1), 3–10. https://doi.org/10.33927/hjic-2020-02