RadarPillars: Efficient Object Detection from 4D Radar Point Clouds

TL;DR

RadarPillars introduces a novel 3D point cloud-based object detection method tailored for 4D radar data, effectively handling sparsity and velocity information to achieve real-time performance with fewer parameters.

Contribution

The paper presents RadarPillars, a new pillar-based detection network specifically designed for 4D radar point clouds, incorporating velocity decomposition and attention mechanisms for improved accuracy and efficiency.

Findings

Outperforms state-of-the-art on View-of-Delft dataset

Reduces parameter count significantly

Enables real-time detection on edge devices

Abstract

Automotive radar systems have evolved to provide not only range, azimuth and Doppler velocity, but also elevation data. This additional dimension allows for the representation of 4D radar as a 3D point cloud. As a result, existing deep learning methods for 3D object detection, which were initially developed for LiDAR data, are often applied to these radar point clouds. However, this neglects the special characteristics of 4D radar data, such as the extreme sparsity and the optimal utilization of velocity information. To address these gaps in the state-of-the-art, we present RadarPillars, a pillar-based object detection network. By decomposing radial velocity data, introducing PillarAttention for efficient feature extraction, and studying layer scaling to accommodate radar sparsity, RadarPillars significantly outperform state-of-the-art detection results on the View-of-Delft dataset. Importantly, this comes at a significantly reduced parameter count, surpassing existing methods in terms of efficiency and enabling real-time performance on edge devices.