Corrections to "Computer Vision Aided mmWave Beam Alignment in V2X Communications"

TL;DR

This paper revises previous simulation results on vision-based mmWave beam alignment in V2X communications, improving the assumptions and design of vehicle distribution features to better demonstrate method performance.

Contribution

It provides corrected simulation results with refined assumptions and an improved vehicle distribution feature design for vision-based beam alignment in V2X systems.

Findings

Revised simulation results reaffirm previous conclusions.

Enhanced vehicle distribution feature improves beam alignment performance.

More realistic assumptions lead to more accurate performance evaluation.

Abstract

In this document, we revise the results of [1] based on more reasonable assumptions regarding data shuffling and parameter setup of deep neural networks (DNNs). Thus, the simulation results can now more reasonably demonstrate the performance of both the proposed and compared beam alignment methods. We revise the simulation steps and make moderate modifications to the design of the vehicle distribution feature (VDF) for the proposed vision based beam alignment when the MS location is available (VBALA). Specifically, we replace the 2D grids of the VDF with 3D grids and utilize the vehicle locations to expand the dimensions of the VDF. Then, we revise the simulation results of Fig. 11, Fig. 12, Fig. 13, Fig. 14, and Fig. 15 in [1] to reaffirm the validity of the conclusions.