Graph-Based 3d Human Pose Estimation Using Wifi Signals

IEEE International Conference on Acoustics Speech and Signal Processing, pp. 19992–19996

Abstract

WiFi-based human pose estimation (HPE) has attracted increasing attention due to its resilience to occlusion and privacy-preserving compared to camera-based methods. However, existing WiFi-based HPE approaches often employ regression networks that directly map WiFi channel state information (CSI) to 3D joint coordinates, ignoring the inherent topological relationships among human joints. In this paper, we present GraphPose-Fi, a graph-based framework that explicitly models skeletal topology for WiFi-based 3D HPE. Our framework comprises a convolutional neural network (CNN) encoder shared across antennas for subcarrier–time feature extraction, a lightweight attention module that adaptively reweights features over time and across antennas, and a graph-based regression head that combines graph convolutional network (GCN) layers with self-attention to capture local topology and global dependencies. Our proposed method achieves state-of-the-art performance on the MM-Fi dataset in various settings.

Authors 4

1. Jichao Chen

   EURECOM

   Affiliation as printed

   EURECOM,Communication Systems Department,France

2. Yangyang Qu

   EURECOM

   Affiliation as printed

   EURECOM,Digital Security Department,France

3. Ruibo Tang Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Germany

4. Dirk T. M. Slock

   EURECOM

   Affiliation as printed

   EURECOM,Communication Systems Department,France