Physics Assisted Deep Learning for Indoor Imaging Using Phaseless Wi-Fi Measurements

A physics-assisted deep learning framework to perform accurate indoor imaging using phaseless Wi-Fi measurements is proposed. It can image objects that are larger than wavelength and have high permittivity that existing radio frequency (RF) inverse scattering techniques find very challenging. The technique utilizes a Rytov-based inverse scattering model and deep learning. The inverse scattering model is based on an extended Rytov approximation (xRA) that prereconstructs RF measurements. Under strong scattering conditions, this prereconstruction is related to the actual permittivity profile by a nonlinear function, which is learned by a modified U-Net model to obtain the permittivity profile. Thus, our proposed approach both reconstructs the shape of objects and estimates their permittivity values accurately. We demonstrate its performance using simulations and experiment results in actual indoor environments using 2.4 GHz Wi-Fi phaseless measurements. For incident wavelength
$\lambda _{0}$
, the framework can reconstruct objects with permittivity as high as 77 and electrical size up to
$40~\lambda $
, where
$\lambda =\lambda _{0}/\sqrt {77}$
as opposed to existing phaseless techniques, which cannot reconstruct permittivity beyond 3 or 4. Thus, our proposed method is the first inverse scattering-based deep learning framework, which can image large scatterers with high permittivity and achieve accurate indoor RF imaging using phaseless Wi-Fi measurements.