_SPA_2020__Optimization_of_the_PointPillars_network_for_3D_object_detection_in_point_clouds(1).pdf (328.48 kB)

Optimization of the PointPillars network for 3D object detection in point clouds

Download (328.48 kB)
posted on 02.07.2020 by Joanna Stanisz, Konrad Lis, Tomasz Kryjak, Marek Gorgon
In this paper we present our research on the optimisation of a deep neural network for 3D object detection in a point cloud. Techniques like quantisation and pruning available in the Brevitas and PyTorch tools were used. We performed the experiments for the PointPillars network, which offers a reasonable compromise between detection accuracy and calculation complexity. The aim of this work was to propose a variant of the network which we will ultimately implement in an FPGA device. This will allow for real-time LiDAR data processing with low energy consumption. The obtained results indicate that even a significant quantisation from 32-bit floating point to 2-bit integer in the main part of the algorithm, results in 5%-9% decrease of the detection accuracy, while allowing for almost a 16-fold reduction in size of the model.


Email Address of Submitting Author

ORCID of Submitting Author


Submitting Author's Institution

AGH University of Science and Technology

Submitting Author's Country