Hits:
Affiliation of Author(s):School of Computer Science and Information Engineering, Hefei University of Technology
Journal:2024 IEEE International Conference on Communications Workshops
Funded by:the National Natural Science Foundation of China under Grants 61971176, 62371180 and 62171474，Anhui
Key Words:Vision Image, Near-field, Beam Training
Abstract:In this paper, we develop a novel beam training scheme for extremely large-scale multiple-input-multiple-output (XL-MIMO) system by exploiting the visual image information. Different from the conventional beam training schemes that consumes a large number of in-band (time/frequency) resources, the proposed scheme only leverages the out-of-band (vision image) information, which can efficiently reduce the training overhead. Specifically, we proposed a vision image-aided beam training cascaded framework integrating YOLOv5 and ResNet18 networks, where the YOLOv5 uses the object detection technique to extract the size and location information of the mobile vehicles (MVs) and the ResNet18 based the extracted information infers the optimal beam index without occupying in-band overhead. The simulation results demonstrate that the proposed vision image aided beam training scheme outperforms the benchmark scheme.
Co-author:Xueqing Huang,Haiyang Zhang,Kunyang Sun,Caihong Kai,Shiwen He
First Author:Wei Huang
Indexed by:Essay collection
Discipline:Engineering
Document Type:C
Page Number:390-395
Translation or Not:no
Date of Publication:2024-06-09
Included Journals:EI