Sevimli, R. A.Ucuncu, M.Koç, Aykut2024-03-142024-03-142023-10-25https://hdl.handle.net/11693/114725The need for visual perception systems providing situational awareness to autonomous vehicles has grown significantly. While traditional deep neural networks are effective for solving 2-D Euclidean problems, point cloud analysis, particularly for radar data, contains unique challenges because of the irregular geometry of point clouds. This letter proposes a novel transformer-based architecture for radar point clouds adapted to the graph signal processing (GSP) framework, designed to handle non-Euclidean and irregular signal structures. We provide experimental results by using well-established benchmarks on the nuScenes and RadarScenes datasets to validate our proposed method.enCC BYhttps://creativecommons.org/licenses/by/4.0/Automotive RADARGraph signal processing (GSP)Point cloud processingSegmentationSensor applicationsTransformersArticle10.1109/LSENS.2023.33275932475-1472