CSI-Net: Unified Human Body Characterization and Pose Recognition
This work addresses the problem of non-invasive human monitoring using WiFi signals, which could benefit healthcare and security applications, but it appears incremental as it builds on existing WiFi sensing methods.
The authors tackled the problem of using WiFi signals for human body characterization and pose recognition by developing CSI-Net, a unified deep neural network, which achieved biometrics estimation and person recognition, and demonstrated applications in hand sign and falling detection.
We build CSI-Net, a unified Deep Neural Network~(DNN), to learn the representation of WiFi signals. Using CSI-Net, we jointly solved two body characterization problems: biometrics estimation (including body fat, muscle, water, and bone rates) and person recognition. We also demonstrated the application of CSI-Net on two distinctive pose recognition tasks: the hand sign recognition (fine-scaled action of the hand) and falling detection (coarse-scaled motion of the body).