VOMTC: Vision Objects for Millimeter and Terahertz Communications

TL;DR

This paper introduces VOMTC, a large-scale vision dataset with RGB and depth images for wireless device detection, enabling improved beamforming in 6G communications through deep learning-based object detection.

Contribution

The paper presents a new dataset tailored for wireless applications and demonstrates its effectiveness in enhancing beamforming techniques in 6G networks.

Findings

VOMTC dataset contains over 20,000 labeled image pairs.

Object detection using VOMTC improves beamforming performance.

Deep learning-based CV methods outperform traditional techniques.

Abstract

Recent advances in sensing and computer vision (CV) technologies have opened the door for the application of deep learning (DL)-based CV technologies in the realm of 6G wireless communications. For the successful application of this emerging technology, it is crucial to have a qualified vision dataset tailored for wireless applications (e.g., RGB images containing wireless devices such as laptops and cell phones). An aim of this paper is to propose a large-scale vision dataset referred to as Vision Objects for Millimeter and Terahertz Communications (VOMTC). The VOMTC dataset consists of 20,232 pairs of RGB and depth images obtained from a camera attached to the base station (BS), with each pair labeled with three representative object categories (person, cell phone, and laptop) and bounding boxes of the objects. Through experimental studies of the VOMTC datasets, we show that the beamforming technique exploiting the VOMTC-trained object detector outperforms conventional beamforming techniques.