MoSeFi: Duration Estimation Robust Human Motion Sensing via Commodity WiFi Device

Accurate motion interval segmentation is the basic and crucial step in advanced human perception based on WiFi signals. However, previous works have rarely considered duration, which one of important parameters for complete description motion. On this basis, we deeply investigate properties CSI ratio from perspective Mobius transformation construct a novel indicator using its complementary real imaginary parts. The new can attenuate impact fragmentation under short-window conditions significantly reduce duration error while ensuring detection accuracy. Moreover, propose universal subcarrier screening method response sensitivity shape similarity, provides more accurate information perception. Furthermore, present MoSeFi—a estimation robust system an existing commercial device. Detailed experimental results demonstrate that MoSeFi lightweight yet effective compared to state-of-the-art systems.