RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation

arXiv:2404.18150v1 Announce Type: new
Abstract: Object detection in radar imagery with neural networks shows great potential for improving autonomous driving. However, obtaining annotated datasets from real radar images, crucial for training these networks, is challenging, especially in scenarios with long-range detection and adverse weather and lighting conditions where radar performance excels. To address this challenge, we present RadSimReal, an innovative physical radar simulation capable of generating synthetic radar images with accompanying annotations for various radar types and environmental conditions, all …

abstract arxiv autonomous autonomous driving cs.cv data datasets detection driving gap however images improving networks neural networks object radar real data shows simulation synthetic training type weather