Environment Independent Gait Recognition Based on Wi-Fi Signals

Gait recognition plays a pivotal role in the area of mobile computing. While various research approaches leverage images, radar, RF signals, pressure sensors, wearables, and other methods, utilizing Wi-Fi signals for gait recognition offers distinct advantages such as a wide sensing range, simple deployment, and passive sensing capabilities. However, traditional gait recognition systems relying on Wi-Fi signals often suffer from performance degradation due to variations in walking directions and environmental conditions. To address this issue, in this paper we propose EIGait, a gait recognition system based on Wi-Fi signal time-frequency spectrograms. EIGait enhances the robustness and generalizability of extracted features through spectrogram augmentation, self-contrastive learning, and domain-adversarial training. Particularly, improvements to ResNet in EIGait yield a Spectrogram ResNet, which is better suited for time-frequency spectrograms. In addition, using merely a single pair of Wi-Fi transmitter and receiver, and by minimal signal denoising, we achieve the state-of-the-art performance. To evaluate the performance of EIGait, we conduct extensive experiments. In a typical indoor environment, EIGait achieves F1 scores ranging from 98.11% to 98.31% for four to eight individuals. In cross-direction gait recognition, we obtain F1 scores of 96.64% to 94.45% for four to eight individuals. Moreover, under the more challenging conditions of cross-room gait recognition, EIGait attains F1 scores of 92.09% to 89.61% for four to eight individuals. Additionally, we conduct experiments on the public dataset 3.0, and the results also demonstrate significant superiority.