DoRF:基于多普勒辐射场的Wi-Fi人体活动识别鲁棒方法
信号处理
2025-07-17 v1 计算机视觉与模式识别
摘要
Wi-Fi信道状态信息(CSI)已获得越来越多的关注,用于远程感知应用。最近的研究表明,从CSI中提取的多普勒速度投影可实现对人类活动识别(HAR)的鲁棒性,能够适应环境变化并推广到新用户。然而,尽管已取得这些进展,但实际部署的可通用性仍不足。灵感来自从二维图像中学习3D场景体积表示的神经辐射场(NeRF),本工作提出了一种新方法,从从Wi-Fi CSI中提取的一维多普勒速度投影重建信息丰富的3D潜在运动表示。 resulting latent representation is then used to construct a uniform Doppler radiance field (DoRF) of the motion, providing a comprehensive view of the performed activity and improving the robustness to environmental variability. The results show that the proposed approach noticeably enhances the generalization accuracy of Wi-Fi-based HAR, highlighting the strong potential of DoRFs for practical sensing applications.
引用
@article{arxiv.2507.12132,
title = {DoRF: Doppler Radiance Fields for Robust Human Activity Recognition Using Wi-Fi},
author = {Navid Hasanzadeh and Shahrokh Valaee},
journal= {arXiv preprint arXiv:2507.12132},
year = {2025}
}