RESEARCH GROUP

“Theory is when you know everything but nothing works. Practice is when everything works but no one knowns why. In our lab, theory and practice are combined: nothing works and no one knows why.” – Unknown Quotes

SPOTLIGHT WORK | 团队工作

Human Motion Tracking via WiFi Signals (Sponsored by ChingMu Co. Ltd.)

WiFlow: Continuous Human Pose Estimation via WiFi Signals Existing WiFi-based human pose estimation methods often focus on discrete pose sample evaluation. Our work presents WiFlow, a novel framework for continuous human pose estimation using WiFi signals. Unlike vision-based approaches such as two-dimensional deep residual networks that treat Channel State Information (CSI) as images, WiFlow employs an encoder-decoder architecture. The encoder captures spatio-temporal features of CSI using temporal and asymmetric convolutions, preserving the original sequential structure of signals. It then refines keypoint features of human bodies to be tracked and capture their structural dependencies via axial attention. The decoder subsequently maps the encoded high-dimensional features into keypoint coordinates.