Print Email Facebook Twitter Radar-PointGNN: Graph Based Object Recognition for Unstructured Radar Point-cloud Data Title Radar-PointGNN: Graph Based Object Recognition for Unstructured Radar Point-cloud Data Author Svenningsson, P.O. (TU Delft Microwave Sensing, Signals & Systems) Fioranelli, F. (TU Delft Microwave Sensing, Signals & Systems) Yarovoy, Alexander (TU Delft Microwave Sensing, Signals & Systems) Date 2021 Abstract Perception systems for autonomous vehicles are reliant on a comprehensive sensor suite to identify objects in the environment. While object recognition systems in the LiDAR and camera modalities are reaching maturity, recognition models on sparse radar point measurements have remained an open research challenge. An object recognition model is here presented which imposes a graph structure on the radar point-cloud by connecting spatially proximal points and extracts local patterns by performing convolutional operations across the graph’s edges. The model’s performance is evaluated by the nuScenes benchmark and is the first radar object recognition model evaluated on the dataset. The results show that end-to-end deep learning solutions for object recognition in the radar domain are viable but currently not competitive with solutions based on LiDAR data. Subject object detectionobject recognitionradargeo-metric deep learningnuScenesgeometric deep learning To reference this document use: http://resolver.tudelft.nl/uuid:f63c09e0-38a4-459d-ac5c-b327c4869109 DOI https://doi.org/10.1109/RadarConf2147009.2021.9455172 Publisher IEEE Embargo date 2021-12-18 ISBN 978-1-7281-7610-9 Source 2021 IEEE Radar Conference: Radar on the Move, RadarConf 2021 Event 2021 IEEE Radar Conference (RadarConf21), 2021-05-07 → 2021-05-14, Atlanta, United States Series IEEE National Radar Conference - Proceedings, 1097-5659, 2021-May Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2021 P.O. Svenningsson, F. Fioranelli, Alexander Yarovoy Files PDF 09455172.pdf 4.67 MB Close viewer /islandora/object/uuid:f63c09e0-38a4-459d-ac5c-b327c4869109/datastream/OBJ/view