Radar-PointGNN: Graph Based Object Recognition for Unstructured Radar Point-cloud Data

Peter Svenningsson, Francesco Fioranelli, Alexander Yarovoy

202158 citationsDOI

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.

Topics & Concepts

Point cloudLidarComputer scienceArtificial intelligenceComputer visionRadarCognitive neuroscience of visual object recognitionRadar imaging3D single-object recognitionGraphObject detectionPattern recognition (psychology)Feature extractionRemote sensingGeographyTelecommunicationsTheoretical computer scienceAdvanced Neural Network ApplicationsRobotics and Sensor-Based LocalizationAdversarial Robustness in Machine Learning