Deep Learning-Based Computer Vision for Beam Selection and Proactive Blockage Prediction

TL;DR

This paper introduces a vision-aided beam selection and proactive blockage prediction framework for millimeter-wave communication, achieving high accuracy in beam prediction and blockage forecasting using deep learning techniques.

Contribution

It presents a novel integrated approach combining RGB imagery and object tracking for improved beam selection and blockage prediction in dynamic environments.

Findings

Achieves 98.96% top-5 beam prediction accuracy, outperforming state-of-the-art methods.

Predicts blockages up to three frames ahead with over 98% accuracy.

First analysis of simultaneous non-uniform mobility of transmitters and obstacles.

Abstract

Millimeter-wave communication faces two critical challenges: propagation losses requiring costly narrow-beam alignment, and penetration losses causing link failures from blocked line-of-sight paths. We address propagation loss through a novel vision-aided beam selection framework that integrates RGB imagery with received power profiles for efficient transmitter identification and beam prediction. This framework achieves 98.96% top-5 beam prediction accuracy, surpassing current state-of-the-art methods by at least 6% across all metrics. We address penetration loss through a proactive blockage prediction framework using a modified object tracker with weighted centroid-based depth estimation. This represents the first analysis of simultaneous non-uniform mobility of both transmitters and obstacles. Evaluated on completely unseen data, this framework achieves over 98% accuracy in predicting blockages up to three frames ahead, establishing strong performance benchmarks.