Exploiting Sparsity in Automotive Radar Object Detection Networks
This work addresses the need for efficient perception systems in autonomous driving, offering incremental improvements in radar object detection.
The paper tackles the problem of high computational resource requirements in CNN-based radar object detection networks for autonomous driving by proposing sparse convolutional networks, resulting in a 5.89% improvement in Car AP4.0 over the baseline and a 21.41% reduction in average scale error.
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.