Subject-independent Human Pose Image Construction with Commodity Wi-Fi
This work is significant for improving the robustness of Wi-Fi-based human pose estimation for new, unseen individuals, which is crucial for privacy-preserving monitoring and human-computer interaction applications.
This paper addresses the challenge of subject generalization in human pose image construction using commodity Wi-Fi, where existing methods struggle with new subjects not present in training data. The authors developed a Domain-Independent Neural Network (DINN) that extracts subject-independent features, enabling the construction of fine-grained human pose images for new subjects in both visible and through-wall scenarios.
Recently, commodity Wi-Fi devices have been shown to be able to construct human pose images, i.e., human skeletons, as fine-grained as cameras. Existing papers achieve good results when constructing the images of subjects who are in the prior training samples. However, the performance drops when it comes to new subjects, i.e., the subjects who are not in the training samples. This paper focuses on solving the subject-generalization problem in human pose image construction. To this end, we define the subject as the domain. Then we design a Domain-Independent Neural Network (DINN) to extract subject-independent features and convert them into fine-grained human pose images. We also propose a novel training method to train the DINN and it has no re-training overhead comparing with the domain-adversarial approach. We build a prototype system and experimental results demonstrate that our system can construct fine-grained human pose images of new subjects with commodity Wi-Fi in both the visible and through-wall scenarios, which shows the effectiveness and the subject-generalization ability of our model.