Can WiFi Estimate Person Pose?
This work addresses the challenge of enabling WiFi devices to perform vision-like tasks such as pose estimation, which could benefit applications in indoor sensing and privacy-preserving monitoring, though it is incremental as it builds on prior WiFi sensing research.
The paper tackles the problem of estimating human pose using WiFi signals, proposing a fully convolutional network (WiSPPN) that achieves positive results on a dataset of over 80k images across 16 sites and 8 persons.
WiFi human sensing has achieved great progress in indoor localization, activity classification, etc. Retracing the development of these work, we have a natural question: can WiFi devices work like cameras for vision applications? In this paper We try to answer this question by exploring the ability of WiFi on estimating single person pose. We use a 3-antenna WiFi sender and a 3-antenna receiver to generate WiFi data. Meanwhile, we use a synchronized camera to capture person videos for corresponding keypoint annotations. We further propose a fully convolutional network (FCN), termed WiSPPN, to estimate single person pose from the collected data and annotations. Evaluation on over 80k images (16 sites and 8 persons) replies aforesaid question with a positive answer. Codes have been made publicly available at https://github.com/geekfeiw/WiSPPN.