Comparison of Different Approaches for Identification of Radar Ghost Detections in Automotive Scenarios
Yi Jin, Robert Prophet, Anastasios Deligiannis, Ingo Weber, Juan-Carlos Fuentes-Michel, Martin Vossiek
Abstract
This paper focuses on the frequently occurring issue of automotive radar sensors: ghost detection. Three data-based approaches, namely random forest, convolutional neural network (CNN), and PointNet++, are adopted to identify ghost detection. Evaluated with the same dataset, random forest and PointNet++, with more than 95% accuracy, are evidently better than CNN in not only city but also motorway scenarios. Furthermore, the influence of various features for each classifier is also analyzed.
Topics & Concepts
Convolutional neural networkComputer scienceRandom forestAutomotive industryArtificial intelligenceClassifier (UML)Identification (biology)RadarPattern recognition (psychology)Machine learningData miningEngineeringBiologyBotanyAerospace engineeringTelecommunicationsRadar Systems and Signal ProcessingMicrowave Imaging and Scattering AnalysisIndoor and Outdoor Localization Technologies