Computer vision-based location-aware antenna system for 5G applications

Abstract

This article introduces an advanced location-aware antenna system that uses computer vision technology to monitor the real-time positions of potential users, terminals, or individuals within a given area. The system incorporates a machine learning-based computer vision algorithm, specifically the You Only Look Once (YOLO) model, and an optimisation technique for analysing visual data. This method identifies and extracts positional coordinates for potential users, allowing the antenna system—mounted on a rotating assembly—to adjust its orientation and accurately direct its beam toward the target objects determined by the algorithm. A rotated square patch antenna is designed to operate at dual frequencies of 3.7 GHz and 5.5 GHz within the sub-6 GHz range. A four-element Multi-Input, Multi-Output (MIMO) antenna is developed without additional decoupling structures, printed on an FR4 substrate of dimension 80 × 80 × 1.6 mm³. The performance metrics of the MIMO antennas demonstrate promising results, with isolation between elements exceeding 28 dB, an Envelope Correlation Coefficient (ECC) of less than 0.05, a Total Active Reflection Coefficient (TARC) below -10 dB, and the ratio of Mean Effective Gain (MEG) consistently within the specified range. This compliance indicates that the antennas can provide excellent diversity performance, which enhances signal reliability and overall communication quality. The proposed system significantly enhances wireless communication by effectively reducing interference, improving signal quality, and extending coverage range. These improvements contribute to a more reliable and efficient communication experience.