Exploiting Sparsity in Automotive Radar Object Detection Networks

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. Although CNN-based object detectors have shown good performance in this context, they require significant computational 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 convolution (DVPC) networks 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.