Exploiting Sparsity in Automotive Radar Object Detection Networks

TL;DR

This paper introduces sparse convolutional networks for radar object detection in autonomous driving, achieving higher accuracy and efficiency by addressing radar-specific challenges with novel architectures.

Contribution

It proposes SKPP and DVPC architectures tailored for radar data, improving detection accuracy and reducing scale error compared to existing methods.

Findings

Outperforms baseline by 5.89% in Car AP4.0

Reduces average scale error by 21.41%

Achieves state-of-the-art results on nuScenes dataset

Abstract

Having precise perception of the environment is crucial for ensuring the secure and reliable functioning of autonomous driving systems. Radar object detection networks are one fundamental part of such systems. CNN-based object detectors showed good performance in this context, but they require large compute resources. This paper investigates sparse convolutional object detection networks, which combine powerful grid-based detection with low compute resources. We investigate radar specific challenges and propose sparse kernel point pillars (SKPP) and dual voxel point convolutions (DVPC) as remedies for the grid rendering and sparse backbone architectures. We evaluate our SKPP-DPVCN architecture on nuScenes, which outperforms the baseline by 5.89% and the previous state of the art by 4.19% in Car AP4.0. Moreover, SKPP-DPVCN reduces the average scale error (ASE) by 21.41% over the baseline.