3D Point Cloud Object Detection on Edge Devices for Split Computing

TL;DR

This paper explores using Split Computing to optimize 3D point cloud object detection on edge devices, significantly reducing inference time and power consumption while enhancing data security.

Contribution

It introduces a novel application of Split Computing to 3D object detection, achieving substantial efficiency improvements on edge devices.

Findings

Splitting after voxelization reduces inference time by 70.8%.

Splitting within the network reduces edge device execution time by 69.5%.

Method enhances security by transmitting only intermediate data.

Abstract

The field of autonomous driving technology is rapidly advancing, with deep learning being a key component. Particularly in the field of sensing, 3D point cloud data collected by LiDAR is utilized to run deep neural network models for 3D object detection. However, these state-of-the-art models are complex, leading to longer processing times and increased power consumption on edge devices. The objective of this study is to address these issues by leveraging Split Computing, a distributed machine learning inference method. Split Computing aims to lessen the computational burden on edge devices, thereby reducing processing time and power consumption. Furthermore, it minimizes the risk of data breaches by only transmitting intermediate data from the deep neural network model. Experimental results show that splitting after voxelization reduces the inference time by 70.8% and the edge device execution time by 90.0%. When splitting within the network, the inference time is reduced by up to 57.1%, and the edge device execution time is reduced by up to 69.5%.