Comparison of Different Approaches for Identification of Radar Ghost Detections in Automotive Scenarios

Jin Y, Prophet R, Deligiannis A, Weber I, Fuentes-Michel JC, Vossiek M (2021)

Publication Language: English

Publication Type: Journal article, Review article

Publication year: 2021

Journal

IEEE National Radar Conference - Proceedings Institute of Electrical and Electronics Engineers

DOI: 10.1109/RadarConf2147009.2021.9454980

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.

Authors with CRIS profile

Yi Jin Lehrstuhl für Hochfrequenztechnik (LHFT) Robert Prophet Lehrstuhl für Hochfrequenztechnik (LHFT) Martin Vossiek Lehrstuhl für Hochfrequenztechnik (LHFT)

How to cite

APA:

Jin, Y., Prophet, R., Deligiannis, A., Weber, I., Fuentes-Michel, J.-C., & Vossiek, M. (2021). Comparison of Different Approaches for Identification of Radar Ghost Detections in Automotive Scenarios. IEEE National Radar Conference - Proceedings. https://doi.org/10.1109/RadarConf2147009.2021.9454980

MLA:

Jin, Yi, et al. "Comparison of Different Approaches for Identification of Radar Ghost Detections in Automotive Scenarios." IEEE National Radar Conference - Proceedings (2021).

BibTeX: Download