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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Noguchi, Taisuke, Azumi, Takuya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908626793267200
author Noguchi, Taisuke
Azumi, Takuya
author_facet Noguchi, Taisuke
Azumi, Takuya
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02293
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D Point Cloud Object Detection on Edge Devices for Split Computing
Noguchi, Taisuke
Azumi, Takuya
Distributed, Parallel, and Cluster Computing
Computer Vision and Pattern Recognition
C.2.4; I.2.10
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%.
title 3D Point Cloud Object Detection on Edge Devices for Split Computing
topic Distributed, Parallel, and Cluster Computing
Computer Vision and Pattern Recognition
C.2.4; I.2.10
url https://arxiv.org/abs/2511.02293