SC-MII: Infrastructure LiDAR-based 3D Object Detection on Edge Devices for Split Computing with Multiple Intermediate Outputs Integration

TL;DR

SC-MII introduces a split computing approach for LiDAR-based 3D object detection on edge devices, significantly reducing latency and device load while maintaining high accuracy in autonomous driving applications.

Contribution

It proposes a novel split computing framework with multiple intermediate outputs for LiDAR-based 3D detection, enhancing efficiency and privacy on edge devices.

Findings

2.19x speed-up in inference time

71.6% reduction in edge device processing load

At most 1.09% accuracy drop

Abstract

3D object detection using LiDAR-based point cloud data and deep neural networks is essential in autonomous driving technology. However, deploying state-of-the-art models on edge devices present challenges due to high computational demands and energy consumption. Additionally, single LiDAR setups suffer from blind spots. This paper proposes SC-MII, multiple infrastructure LiDAR-based 3D object detection on edge devices for Split Computing with Multiple Intermediate outputs Integration. In SC-MII, edge devices process local point clouds through the initial DNN layers and send intermediate outputs to an edge server. The server integrates these features and completes inference, reducing both latency and device load while improving privacy. Experimental results on a real-world dataset show a 2.19x speed-up and a 71.6% reduction in edge device processing time, with at most a 1.09% drop in accuracy.