GaitID: Robust Wi-Fi Based Gait Recognition

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectory and sufficient training data. In this paper, we present GaitID, a Wi-Fi based human identification system, to overcome above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitID first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitID reduces the training efforts in new deployment scenarios by transfer learning. Extensive experiments have been conducted on the implementation and the outcomes are satisfying. To the best of our knowledge, GaitID is the first gait-based identification approach without any restriction on walking trajectory and speed.