AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi
This work addresses the domain shift issue for WiFi-based pose estimation, enabling broader application in smart homes and cities, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of WiFi-based human pose estimation failing in new environments due to domain shift, proposing AdaPose, a domain adaptation algorithm that achieves robustness by aligning source and target domains with a Mapping Consistency Loss, resulting in effective elimination of domain shift as demonstrated in experiments on self-collected datasets.
WiFi-based pose estimation is a technology with great potential for the development of smart homes and metaverse avatar generation. However, current WiFi-based pose estimation methods are predominantly evaluated under controlled laboratory conditions with sophisticated vision models to acquire accurately labeled data. Furthermore, WiFi CSI is highly sensitive to environmental variables, and direct application of a pre-trained model to a new environment may yield suboptimal results due to domain shift. In this paper, we proposes a domain adaptation algorithm, AdaPose, designed specifically for weakly-supervised WiFi-based pose estimation. The proposed method aims to identify consistent human poses that are highly resistant to environmental dynamics. To achieve this goal, we introduce a Mapping Consistency Loss that aligns the domain discrepancy of source and target domains based on inner consistency between input and output at the mapping level. We conduct extensive experiments on domain adaptation in two different scenes using our self-collected pose estimation dataset containing WiFi CSI frames. The results demonstrate the effectiveness and robustness of AdaPose in eliminating domain shift, thereby facilitating the widespread application of WiFi-based pose estimation in smart cities.