3D Point Cloud Object Detection on Edge Devices for Split Computing
This addresses the challenge of deploying complex deep learning models on resource-constrained edge devices for autonomous driving, though it is incremental as it adapts an existing distributed inference method to a specific domain.
This paper tackles the problem of high computational burden and power consumption for 3D point cloud object detection on edge devices in autonomous driving by applying split computing, resulting in up to 70.8% reduction in inference time and 90.0% reduction in edge device execution time.
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%.