Beyond Sub-6 GHz: Leveraging mmWave Wi-Fi for Gait-Based Person Identification

2025-10-09

AI Summary

Existing Wi-Fi gait recognition research predominantly focuses on sub-6 GHz bands, leaving the potential of millimeter-wave (mmWave) Wi-Fi systematically unexplored. This paper presents the first synchronized dual-band (mmWave + sub-6 GHz) gait dataset collected on commercial off-the-shelf (COTS) devices, and proposes an end-to-end deep learning framework integrating background noise suppression with dual-band collaborative signal processing. Through rigorously controlled comparative experiments, we demonstrate mmWave’s intrinsic advantages in spatial resolution and robustness: achieving 91.2% identification accuracy for 20 subjects in indoor settings at only 10 Hz sampling rate—significantly outperforming sub-6 GHz baselines. Our key contributions are: (1) the first empirical study of mmWave Wi-Fi gait recognition using COTS hardware; (2) validation of high-accuracy gait recognition feasibility under ultra-low sampling rates enabled by mmWave; and (3) open-sourcing of the synchronized dual-band dataset and processing pipeline, establishing a new paradigm for contactless identity authentication.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Person identification plays a vital role in enabling intelligent, personalized, and secure human-computer interaction. Recent research has demonstrated the feasibility of leveraging Wi-Fi signals for passive person identification using a person's unique gait pattern. Although most existing work focuses on sub-6 GHz frequencies, the emergence of mmWave offers new opportunities through its finer spatial resolution, though its comparative advantages for person identification remain unexplored. This work presents the first comparative study between sub-6 GHz and mmWave Wi-Fi signals for person identification with commercial off-the-shelf (COTS) Wi-Fi, using a novel dataset of synchronized measurements from the two frequency bands in an indoor environment. To ensure a fair comparison, we apply identical training pipelines and model configurations across both frequency bands. Leveraging end-to-end deep learning, we show that even at low sampling rates (10 Hz), mmWave Wi-Fi signals can achieve high identification accuracy (91.2% on 20 individuals) when combined with effective background subtraction.

Problem

• Comparing mmWave and sub-6 GHz Wi-Fi for gait identification
• Exploring mmWave's advantages in person identification accuracy
• Using synchronized dual-band measurements for fair performance evaluation

Innovation

• Uses mmWave Wi-Fi for gait identification
• Compares sub-6 GHz and mmWave performance
• Applies deep learning with background subtraction