betaFeedback

WorksEngineering

Enabling Versatile Human Sensing through Wi-Fi Beamforming Feedback

Abstract

Wi-Fi sensing enables contactless human sensing, while most existing systems rely on Channel State Information, which is accessible only on a limited range of Wi-Fi chipsets. In contrast, Beamforming Feedback Information (BFI) is standardized in modern Wi-Fi and readily accessible on a wide range of commodity devices, offering new opportunities for human sensing. In this paper, we present BeamLens, a Wi-Fi sensing system that extracts fine-grained spatial information from BFI to enable versatile human sensing. Specifically, we jointly estimate the angle of departure and relative time of flight from BFI to extract fine-grained spatial information and leverage two AP-STA links to capture complementary azimuth and elevation views. We further design a sparse physical antenna array and construct a uniform virtual antenna array to enhance spatial resolution. Moreover, we fuse complementary views through self-supervised learning, combining temporally aware cross-view contrastive learning and temporal masked reconstruction to learn a versatile backbone for diverse human sensing tasks. Extensive evaluations demonstrate that BeamLens achieves 90.16% accuracy in human activity recognition, a mean per-joint position error of 8.64,cm in 3D human pose estimation, and 70.64% intersection over union in human silhouette estimation, while exhibiting strong generalization to unseen environments and subjects.

Paper details

vlnc:W_nex9by7w
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 8

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Engineering

Not recorded for this paper

View statement
Looking for related papers…