Generating Synthetic Short-Range FMCW Range-Doppler Maps Using Generative Adversarial Networks and Deep Convolutional Autoencoders

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

In this paper, we discuss the usage of Generative Adversarial Networks (GANs) and Deep Convolutional Autoen-coders (CAE) for creating synthetic Range-Doppler (RD) maps of Frequency-Modulated Continuous-Wave (FMCW) radars for a short-range situation with moving objects, based on measured RD maps of pedestrians and cyclists. Instead of using regular mathematical functions or heavy radar simulations, we have used an Artificial Neural Network (ANN) model to generate new data. By using our synthetic data, we can automatically have ground-truth data without the need for manual labor; easily create large synthetic datasets; hardly use much computational power after training. To evaluate our method, we have trained a detector system with just synthetic data, and it was capable of detecting moving objects correctly, on actual Range-Doppler maps, 11.6% better than when using a small dataset.
Original languageEnglish
Title of host publication2020 IEEE Radar Conference (RadarConf20)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-7281-8942-0
ISBN (Print)978-1-7281-8943-7
DOIs
Publication statusPublished - 4 Dec 2020
EventIEEE Radar Conference 2020 - Virtual Conference
Duration: 21 Sep 202025 Sep 2020
https://www.radarconf20.org/

Conference

ConferenceIEEE Radar Conference 2020
Abbreviated titleRadarConf 2020
CityVirtual Conference
Period21/09/2025/09/20
Internet address

Keywords

  • Autoencoder
  • Convolutional
  • Deep Learning
  • Doppler-Range
  • FMCW
  • Generative Adversarial Networks
  • Neural Network
  • Radar
  • Synthetic Data

Fingerprint

Dive into the research topics of 'Generating Synthetic Short-Range FMCW Range-Doppler Maps Using Generative Adversarial Networks and Deep Convolutional Autoencoders'. Together they form a unique fingerprint.

Cite this