CNN Based Road User Detection Using the 3D Radar Cube

Journal article (2020)

Authors

A. Palffy Intelligent Vehicles - Mechanical, Maritime and Materials Engineering
Jiaao Dong Student
J.F.P. Kooij Intelligent Vehicles - Mechanical, Maritime and Materials Engineering
D. Gavrila Intelligent Vehicles - Mechanical, Maritime and Materials Engineering
Research Group
Intelligent Vehicles (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2020 A. Palffy, Jiaao Dong, J.F.P. Kooij, D. Gavrila
DOI
help_outline
https://doi.org/10.1109/LRA.2020.2967272
Sensor fusion Object detection Segmentation and categorization Deep learning in robotics and automation
More Info
expand_more

Published Date

2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Intelligent Vehicles

Abstract

This letter presents a novel radar based, single-frame, multi-class detection method for moving road users ( pedestrian, cyclist, car ), which utilizes low-level radar cube data. The method provides class information both on the radar target- and object-level. Radar targets are classified individually after extending the target features with a cropped block of the 3D radar cube around their positions, thereby capturing the motion of moving parts in the local velocity distribution. A Convolutional Neural Network (CNN) is proposed for this classification step. Afterwards, object proposals are generated with a clustering step, which not only considers the radar targets’ positions and velocities, but their calculated class scores as well. In experiments on a real-life dataset we demonstrate that our method outperforms the state-of-the-art methods both target- and object-wise by reaching an average of 0.70 (baseline: 0.68) target-wise and 0.56 (baseline: 0.48) object-wise F1 score. Furthermore, we examine the importance of the used features in an ablation study.