TY - CHAP A1 - de Andrade, Mauren Louise S. C. A1 - Velloso Nogueira, Matheus A1 - Fidelis, Eduardo A1 - Aguiar Campos, Luiz Henrique A1 - Campos, Pietro A1 - Schön, Torsten A1 - de Abreu Faria, Lester ED - Radeva, Petia ED - Farinella, Giovanni Maria ED - Bouatouch, Kadi T1 - Exploiting GAN Capacity to Generate Synthetic Automotive Radar Data T2 - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 N2 - In this paper, we evaluate the training of GAN for synthetic RAD image generation for four objects reflected by Frequency Modulated Continuous Wave radar: car, motorcycle, pedestrian and truck. This evaluation adds a new possibility for data augmentation when radar data labeling available is not enough. The results show that, yes, the GAN generated RAD images well, even when a specific class of the object is necessary. We also compared the scores of three GAN architectures, GAN Vanilla, CGAN, and DCGAN, in RAD synthetic imaging generation. We show that the generator can produce RAD images well enough with the results analyzed. UR - https://doi.org/10.5220/0011672400003417 KW - Radar Application KW - Generative Adversarial Network KW - Ground-Based Radar Dataset KW - Synthetic Automotive Radar Data Y1 - 2023 UR - https://doi.org/10.5220/0011672400003417 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-32029 SN - 978-989-758-634-7 SP - 262 EP - 271 PB - SciTePress CY - Setúbal ER -