Generative Adversarial Synthesis of Radar Point Cloud Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nawaz, Muhammad Saad, Dallmann, Thomas, Schoen, Torsten, Heberling, Dirk
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929547944919040
author Nawaz, Muhammad Saad
Dallmann, Thomas
Schoen, Torsten
Heberling, Dirk
author_facet Nawaz, Muhammad Saad
Dallmann, Thomas
Schoen, Torsten
Heberling, Dirk
contents For the validation and verification of automotive radars, datasets of realistic traffic scenarios are required, which, how ever, are laborious to acquire. In this paper, we introduce radar scene synthesis using GANs as an alternative to the real dataset acquisition and simulation-based approaches. We train a PointNet++ based GAN model to generate realistic radar point cloud scenes and use a binary classifier to evaluate the performance of scenes generated using this model against a test set of real scenes. We demonstrate that our GAN model achieves similar performance (~87%) to the real scenes test set.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13526
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative Adversarial Synthesis of Radar Point Cloud Scenes
Nawaz, Muhammad Saad
Dallmann, Thomas
Schoen, Torsten
Heberling, Dirk
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
For the validation and verification of automotive radars, datasets of realistic traffic scenarios are required, which, how ever, are laborious to acquire. In this paper, we introduce radar scene synthesis using GANs as an alternative to the real dataset acquisition and simulation-based approaches. We train a PointNet++ based GAN model to generate realistic radar point cloud scenes and use a binary classifier to evaluate the performance of scenes generated using this model against a test set of real scenes. We demonstrate that our GAN model achieves similar performance (~87%) to the real scenes test set.
title Generative Adversarial Synthesis of Radar Point Cloud Scenes
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2410.13526