Reconstructing Depth Images of Moving Objects from Wi-Fi CSI Data
Guanyu Cao, Takuya Maekawa, Kazuya Ohara, Yasue Kishino
TL;DR
This work addresses reconstructing depth images of moving objects from Wi-Fi CSI data, enabling privacy-preserving, device-free sensing in scenarios where RGB imaging is undesirable. It introduces Wi-Depth, a VAE-based teacher-student framework that decomposes a depth image into shape, depth, and position, training auxiliary tasks derived from CSI primitives to ensure coherent outputs. The approach targets consistent reconstructions by regularizing the latent space and aligning CSI-derived cues (such as AoA, ToF, and Doppler shifts) with the three core image components. The proposed method has potential applications in security and elder care by providing depth-based situational awareness without exposing identifiable visual textures.
Abstract
This study proposes a new deep learning method for reconstructing depth images of moving objects within a specific area using Wi-Fi channel state information (CSI). The Wi-Fi-based depth imaging technique has novel applications in domains such as security and elder care. However, reconstructing depth images from CSI is challenging because learning the mapping function between CSI and depth images, both of which are high-dimensional data, is particularly difficult. To address the challenge, we propose a new approach called Wi-Depth. The main idea behind the design of Wi-Depth is that a depth image of a moving object can be decomposed into three core components: the shape, depth, and position of the target. Therefore, in the depth-image reconstruction task, Wi-Depth simultaneously estimates the three core pieces of information as auxiliary tasks in our proposed VAE-based teacher-student architecture, enabling it to output images with the consistency of a correct shape, depth, and position. In addition, the design of Wi-Depth is based on our idea that this decomposition efficiently takes advantage of the fact that shape, depth, and position relate to primitive information inferred from CSI such as angle-of-arrival, time-of-flight, and Doppler frequency shift.